Repository Analysis

run-llama/llama_index

LlamaIndex is the leading document agent and OCR platform

23.2 Moderate AI signal View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of run-llama/llama_index, a Python project with 50,828 GitHub stars. SynthScan v2.0 examined 634,728 lines of code across 6544 source files, recording 10552 pattern matches distributed across 24 syntactic categories. The overall adjusted score of 23.2 places this repository in the Moderate AI signal band.

The scanner applied 160+ deterministic lexical heuristics, multi-line block detectors, abstract syntax tree depth profilers, and a cross-file Jaccard similarity matrix to construct a statistically normalised synthetic code estimate. All matches are individually weighted by severity coefficient and contextual multiplier before summation, and the resulting headline score is temporally discounted to account for the repository's development history relative to the commercial emergence of large language model coding tooling (November 2022 onward).

23.2
Adjusted Score
23.2
Raw Score
100%
Time Factor
2026-07-13
Last Push
50.8K
Stars
Python
Language
634.7K
Lines of Code
6.5K
Files
10.6K
Pattern Hits
2026-07-14
Scan Date
0.12
HC Hit Rate

What These Metrics Mean

Adjusted Score
Primary synthetic code indicator. Raw score normalised per 1,000 lines of code and multiplied by the temporal discount factor. This is the definitive comparative metric — use it to rank repositories by AI authorship density.
Raw Score
The unmodified sum of all severity-weighted, context-multiplied pattern match scores before temporal discounting. Reflects the absolute signal strength independent of when the repository was last active.
Time Factor
The temporal discount multiplier (0–100%) applied to the raw score. Repositories last updated before ChatGPT's launch (Nov 2022) receive a 5% factor. Full signal is only assigned to repositories active in the post-adoption era (Jan 2024+).
Pattern Hits
Total count of individual pattern matches across all files and categories. A high hit count with a low score may indicate a very large codebase with isolated AI snippets; a low count with a high score indicates dense, concentrated AI signatures.
HC Hit Rate
High+Critical pattern hits per file, averaged across the repository. This orthogonal signal catches repositories where a few files are densely packed with high-severity AI tells — a strong indicator even when the normalised score appears moderate due to codebase size.
Lines of Code / Files
Total lines and files analysed. The scanner examines 94 file extensions. These denominators are used to normalise the score, enabling fair comparison between repositories of vastly different sizes.

Score History

This chart maps the temporal evolution of the adjusted synthetic code score across successive scan runs. An upward trajectory indicates ongoing incorporation of AI-generated code or expanding LLM-assisted scaffolding; a stable or declining trajectory may reflect active human refactoring, code removal, or the adoption of stricter authorship policies. The dashed secondary line (right axis) independently tracks total raw pattern hit count, which can diverge from the normalised score when codebase size changes significantly between scans.

Severity Breakdown

Classifies detected patterns by their diagnostic confidence and structural impact. CRITICAL patterns (coefficient 10) represent definitive synthetic signatures — hallucinated imports, explicit LLM attribution metadata — virtually never produced by human authors. HIGH (5) indicates strong structural tells such as cross-file repetition or cross-linguistic idioms. MEDIUM (2) covers recognisable conversational padding and AI-specific vocabulary. LOW (1) captures subtle indicators like tautological comments and generic boilerplate that require density to carry independent signal.

CRITICAL 35HIGH 732MEDIUM 482LOW 9303

Directory Score Breakdown

This horizontal bar chart decomposes the repository's raw synthetic code score by top-level directory, allowing you to pinpoint precisely which modules or components carry the highest AI authorship density. Directories with disproportionately high scores relative to their size warrant targeted manual review: concentrated AI signatures often trace back to mass-generated configuration layers, auto-ported test suites, LLM-scaffolded boilerplate classes, or entire subsystems authored under heavy copilot assistance. Use this view to prioritise your human code-review effort.

Pattern Findings

The scanner identified 10552 distinct pattern matches across 24 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a statistically significant AI authorship indicator. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the diagnostic confidence level (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — comment-context matches receive a ×1.5 weight because LLMs systematically over-annotate. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier as dense clusters constitute far stronger evidence of synthetic authorship than isolated hits.

Hyper-Verbose Identifiers4155 hits · 4161 pts
SeverityFileLineSnippetContext
LOWllama-index-instrumentation/tests/test_shutdown.py12def test_shutdown_drops_all_open_spans():CODE
LOWllama-index-instrumentation/tests/test_shutdown.py32def test_shutdown_calls_close_on_handlers():CODE
LOWllama-index-instrumentation/tests/test_shutdown.py47def test_shutdown_walks_parent_chain():CODE
LOWllama-index-instrumentation/tests/test_shutdown.py75def test_shutdown_is_idempotent():CODE
LOWllama-index-instrumentation/tests/test_shutdown.py87def test_close_default_is_noop():CODE
LOWllama-index-instrumentation/tests/test_manager.py4def test_root_manager_add_dispatcher():CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py806def test_span_decorator_is_idempotent(mock_span_enter):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py813def test_span_decorator_is_idempotent_with_pass_through(mock_span_enter):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py821def test_mixin_decorates_abstract_method(mock_span_enter):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py113def func_with_event_backwards_compat(a, b=3, **kwargs):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py149 def func_with_event_backwards_compat(self, a, b=3, **kwargs):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py157def test_dispatcher_span_args(mock_uuid, mock_span_enter, mock_span_exit):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py193def test_dispatcher_span_args_with_instance(mock_uuid, mock_span_enter, mock_span_exit):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py231def test_dispatcher_span_drop_args(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py269async def test_dispatcher_async_span_args(mock_uuid, mock_span_enter, mock_span_exit):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py306async def test_dispatcher_async_span_args_with_instance(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py347async def test_dispatcher_async_span_drop_args(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py386async def test_dispatcher_async_span_drop_args_with_instance(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py424def test_dispatcher_fire_event(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py456async def test_dispatcher_async_fire_event(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py491async def test_dispatcher_attaches_tags_to_events_and_spans(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py512def test_dispatcher_attaches_tags_to_concurrent_events(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py550def test_dispatcher_fire_event_with_instance(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py580async def test_dispatcher_async_fire_event_with_instance(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py747def test_dispatcher_fire_event_backwards_compat(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py779def test_dispatcher_fire_event_with_instance_backwards_compat(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py833def test_mixin_decorates_overridden_method(mock_span_enter):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py847def test_span_naming_with_inheritance(mock_uuid, mock_span_enter, mock_span_exit):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py898async def test_async_span_naming_with_inheritance(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py935def test_span_naming_regular_functions_unchanged(CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py960def test_span_naming_complex_inheritance(mock_uuid, mock_span_enter, mock_span_exit):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py1011def test_span_naming_with_method_override(mock_uuid, mock_span_enter, mock_span_exit):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py1046def test_span_naming_with_nested_classes(mock_uuid, mock_span_enter, mock_span_exit):CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py1078def test_aevent_with_sync_handlers():CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py1094async def test_aevent_with_async_handlers():CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py1111async def test_aevent_concurrent_handlers():CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py1134async def test_aevent_error_isolation():CODE
LOWllama-index-instrumentation/tests/test_dispatcher.py1194async def test_aevent_no_propagation():CODE
LOWllama-index-instrumentation/tests/test_propagation.py15 def capture_propagation_context(self) -> Dict[str, Any]:CODE
LOWllama-index-instrumentation/tests/test_propagation.py18 def restore_propagation_context(self, context: Dict[str, Any]) -> None:CODE
LOWllama-index-instrumentation/tests/test_propagation.py22def test_capture_propagation_context_basic():CODE
LOWllama-index-instrumentation/tests/test_propagation.py32def test_capture_includes_instrument_tags():CODE
LOWllama-index-instrumentation/tests/test_propagation.py45def test_capture_omits_instrument_tags_when_empty():CODE
LOWllama-index-instrumentation/tests/test_propagation.py54def test_restore_propagation_context_basic():CODE
LOWllama-index-instrumentation/tests/test_propagation.py64def test_restore_sets_instrument_tags():CODE
LOWllama-index-instrumentation/tests/test_propagation.py75def test_capture_walks_parent_chain():CODE
LOWllama-index-instrumentation/tests/test_propagation.py97def test_restore_walks_parent_chain():CODE
LOWllama-index-instrumentation/tests/test_propagation.py120def test_capture_stops_at_propagate_false():CODE
LOWllama-index-instrumentation/tests/test_propagation.py142def test_roundtrip_capture_restore():CODE
LOWllama-index-instrumentation/tests/test_propagation.py164def test_capture_swallows_handler_exceptions():CODE
LOWllama-index-instrumentation/tests/test_propagation.py166 def capture_propagation_context(self) -> Dict[str, Any]:CODE
LOWllama-index-instrumentation/tests/test_propagation.py177def test_restore_swallows_handler_exceptions():CODE
LOWllama-index-instrumentation/tests/test_propagation.py179 def restore_propagation_context(self, context: Dict[str, Any]) -> None:CODE
LOW…entation/src/llama_index_instrumentation/dispatcher.py275 def capture_propagation_context(self) -> Dict[str, Any]:CODE
LOW…entation/src/llama_index_instrumentation/dispatcher.py294 def restore_propagation_context(self, context: Dict[str, Any]) -> None:CODE
LOW…/src/llama_index_instrumentation/span_handlers/base.py144 def capture_propagation_context(self) -> Dict[str, Any]:CODE
LOW…/src/llama_index_instrumentation/span_handlers/base.py153 def restore_propagation_context(self, context: Dict[str, Any]) -> None:CODE
LOW…ocs/framework/understanding/agent/structured_output.md107async def structured_output_parsing(CODE
LOW…ama-index-utils-azure/llama_index/utils/azure/table.py51def validate_table_property_count(num_properties: int) -> None:CODE
LOW…ama-index-utils-azure/llama_index/utils/azure/table.py63def validate_table_total_property_size(CODE
4095 more matches not shown…
Unused Imports1965 hits · 1889 pts
SeverityFileLineSnippetContext
LOW…llama_index_instrumentation/event_handlers/__init__.py1CODE
LOW…llama_index_instrumentation/event_handlers/__init__.py2CODE
LOW…ation/src/llama_index_instrumentation/span/__init__.py4CODE
LOW…ation/src/llama_index_instrumentation/span/__init__.py5CODE
LOW…/llama_index_instrumentation/span_handlers/__init__.py1CODE
LOW…/llama_index_instrumentation/span_handlers/__init__.py2CODE
LOW…/llama_index_instrumentation/span_handlers/__init__.py3CODE
LOW…ation/src/llama_index_instrumentation/base/__init__.py1CODE
LOW…ation/src/llama_index_instrumentation/base/__init__.py2CODE
LOW…-index-utils-azure/llama_index/utils/azure/__init__.py1CODE
LOW…-index-utils-azure/llama_index/utils/azure/__init__.py1CODE
LOW…-index-utils-azure/llama_index/utils/azure/__init__.py1CODE
LOW…-index-utils-azure/llama_index/utils/azure/__init__.py1CODE
LOW…ex-utils-qianfan/llama_index/utils/qianfan/__init__.py1CODE
LOW…ex-utils-qianfan/llama_index/utils/qianfan/__init__.py2CODE
LOW…ex-utils-qianfan/llama_index/utils/qianfan/__init__.py2CODE
LOW…ex-utils-qianfan/llama_index/utils/qianfan/__init__.py2CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py1CODE
LOW…-utils-oracleai/llama_index/utils/oracleai/__init__.py1CODE
LOW…ndex-utils-oracleai/llama_index/utils/oracleai/base.py10CODE
LOW…ed/llama_index/sparse_embeddings/fastembed/__init__.py1CODE
LOW…ma-index-sparse-embeddings-fastembed/tests/conftest.py2CODE
LOW…db/llama_index/vector_stores/singlestoredb/__init__.py1CODE
LOW…es-qdrant/llama_index/vector_stores/qdrant/__init__.py1CODE
LOW…inecone/llama_index/vector_stores/pinecone/__init__.py1CODE
LOW…wsdocdb/llama_index/vector_stores/awsdocdb/__init__.py1CODE
LOW…llama-index-vector-stores-awsdocdb/tests/test_docdb.py3CODE
LOW…es-duckdb/llama_index/vector_stores/duckdb/__init__.py1CODE
LOW…upabase/llama_index/vector_stores/supabase/__init__.py1CODE
LOW…-upstash/llama_index/vector_stores/upstash/__init__.py1CODE
LOW…-lancedb/llama_index/vector_stores/lancedb/__init__.py1CODE
LOW…ch/llama_index/vector_stores/elasticsearch/__init__.py1CODE
LOW…ch/llama_index/vector_stores/elasticsearch/__init__.py3CODE
LOW…ch/llama_index/vector_stores/elasticsearch/__init__.py3CODE
LOW…ch/llama_index/vector_stores/elasticsearch/__init__.py3CODE
LOW…ch/llama_index/vector_stores/elasticsearch/__init__.py3CODE
LOW…ma-index-vector-stores-elasticsearch/tests/conftest.py2CODE
LOW…lasticsearch/tests/test_vector_stores_elasticsearch.py1CODE
LOW…ostgres/llama_index/vector_stores/postgres/__init__.py1CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py17CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py18CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py20CODE
LOW…s/llama-index-vector-stores-postgres/tests/conftest.py2CODE
LOW…ma-index-vector-stores-postgres/tests/test_postgres.py51CODE
LOW…ma-index-vector-stores-postgres/tests/test_postgres.py52CODE
LOW…ma-index-vector-stores-postgres/tests/test_postgres.py54CODE
LOW…ma-index-vector-stores-postgres/tests/test_postgres.py55CODE
LOW…-vectorx/llama_index/vector_stores/vectorx/__init__.py1CODE
1905 more matches not shown…
Cross-File Repetition335 hits · 1675 pts
SeverityFileLineSnippetContext
HIGH…toredb/llama_index/vector_stores/singlestoredb/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…es-pinecone/llama_index/vector_stores/pinecone/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…es-supabase/llama_index/vector_stores/supabase/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…ores-vectorx/llama_index/vector_stores/vectorx/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…ordb/llama_index/vector_stores/tencentvectordb/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…-vector-stores-s3/llama_index/vector_stores/s3/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…es-weaviate/llama_index/vector_stores/weaviate/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…stores-jaguar/llama_index/vector_stores/jaguar/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…stores-chroma/llama_index/vector_stores/chroma/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…lickhouse/llama_index/vector_stores/clickhouse/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…r-stores-txtai/llama_index/vector_stores/txtai/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…ores-hnswlib/llama_index/vector_stores/hnswlib/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…atabricks/llama_index/vector_stores/databricks/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…-typesense/llama_index/vector_stores/typesense/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…-cassandra/llama_index/vector_stores/cassandra/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…es-astra-db/llama_index/vector_stores/astra_db/base.py0add nodes to index. args: nodes: list[basenode]: list of node with embeddingsSTRING
HIGH…toredb/llama_index/vector_stores/singlestoredb/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…es-pinecone/llama_index/vector_stores/pinecone/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…stores-duckdb/llama_index/vector_stores/duckdb/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…ores-lancedb/llama_index/vector_stores/lancedb/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…-cassandra/llama_index/vector_stores/cassandra/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…ma_index/vector_stores/alibabacloud_opensearch/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…es-deeplake/llama_index/vector_stores/deeplake/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…es-weaviate/llama_index/vector_stores/weaviate/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…ashvector/llama_index/vector_stores/dashvector/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…stores-jaguar/llama_index/vector_stores/jaguar/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…res-faiss/llama_index/vector_stores/faiss/map_store.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…r-stores-faiss/llama_index/vector_stores/faiss/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…ores-mongodb/llama_index/vector_stores/mongodb/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…stores-chroma/llama_index/vector_stores/chroma/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…lickhouse/llama_index/vector_stores/clickhouse/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…r-stores-txtai/llama_index/vector_stores/txtai/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…ores-epsilla/llama_index/vector_stores/epsilla/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…es-hologres/llama_index/vector_stores/hologres/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…ores-hnswlib/llama_index/vector_stores/hnswlib/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…es-moorcheh/llama_index/vector_stores/moorcheh/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…ngo/llama_index/vector_stores/azurecosmosmongo/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…-typesense/llama_index/vector_stores/typesense/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…pensearch/llama_index/vector_stores/opensearch/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…-oceanbase/llama_index/vector_stores/oceanbase/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…es-dynamodb/llama_index/vector_stores/dynamodb/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…sql/llama_index/vector_stores/azurecosmosnosql/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…ma-index-core/llama_index/core/vector_stores/simple.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…ores-vectorx/llama_index/vector_stores/vectorx/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…es-astra-db/llama_index/vector_stores/astra_db/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…-vector-stores-s3/llama_index/vector_stores/s3/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…stores-vearch/llama_index/vector_stores/vearch/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…r-stores-awadb/llama_index/vector_stores/awadb/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…atabricks/llama_index/vector_stores/databricks/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…es-bigquery/llama_index/vector_stores/bigquery/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…r-stores-redis/llama_index/vector_stores/redis/base.py0delete nodes using the ref_doc_id. args: ref_doc_id (str): the doc_id of the document to delete.STRING
HIGH…es-pinecone/llama_index/vector_stores/pinecone/base.py0base vector store index. an index that is built on top of an existing vector store.STRING
HIGH…es-weaviate/llama_index/vector_stores/weaviate/base.py0base vector store index. an index that is built on top of an existing vector store.STRING
HIGH…res-faiss/llama_index/vector_stores/faiss/map_store.py0base vector store index. an index that is built on top of an existing vector store.STRING
HIGH…r-stores-faiss/llama_index/vector_stores/faiss/base.py0base vector store index. an index that is built on top of an existing vector store.STRING
HIGH…ores-mongodb/llama_index/vector_stores/mongodb/base.py0base vector store index. an index that is built on top of an existing vector store.STRING
HIGH…r-stores-txtai/llama_index/vector_stores/txtai/base.py0base vector store index. an index that is built on top of an existing vector store.STRING
HIGH…-firestore/llama_index/vector_stores/firestore/base.py0base vector store index. an index that is built on top of an existing vector store.STRING
HIGH…ores-hnswlib/llama_index/vector_stores/hnswlib/base.py0base vector store index. an index that is built on top of an existing vector store.STRING
HIGH…r-stores-awadb/llama_index/vector_stores/awadb/base.py0base vector store index. an index that is built on top of an existing vector store.STRING
275 more matches not shown…
Modern Structural Boilerplate1128 hits · 1130 pts
SeverityFileLineSnippetContext
LOW…llama_index_instrumentation/event_handlers/__init__.py4__all__ = ["BaseEventHandler", "NullEventHandler"]CODE
LOW…ation/src/llama_index_instrumentation/span/__init__.py11__all__ = ["BaseSpan", "SimpleSpan", "active_span_id"]CODE
LOW…/llama_index_instrumentation/span_handlers/__init__.py5__all__ = [CODE
LOW…ation/src/llama_index_instrumentation/base/__init__.py4__all__ = [CODE
LOW…-index-utils-azure/llama_index/utils/azure/__init__.py8__all__ = ["ServiceMode", "deserialize", "sanitize_table_name", "serialize"]CODE
LOW…ndex-utils-qianfan/llama_index/utils/qianfan/client.py26logger = logging.getLogger(__name__)CODE
LOW…ex-utils-qianfan/llama_index/utils/qianfan/__init__.py4__all__ = ["Client", "APIType", "get_service_list", "aget_service_list"]CODE
LOW…-huggingface/llama_index/utils/huggingface/__init__.py17__all__ = [CODE
LOW…-utils-oracleai/llama_index/utils/oracleai/__init__.py4__all__ = ["OracleSummary"]CODE
LOW…ndex-utils-oracleai/llama_index/utils/oracleai/base.py22logger = logging.getLogger(__name__)CODE
LOW…ed/llama_index/sparse_embeddings/fastembed/__init__.py3__all__ = ["FastEmbedSparseEmbedding"]CODE
LOW…db/llama_index/vector_stores/singlestoredb/__init__.py3__all__ = ["SingleStoreVectorStore"]CODE
LOW…toredb/llama_index/vector_stores/singlestoredb/base.py20logger = logging.getLogger(__name__)CODE
LOW…es-qdrant/llama_index/vector_stores/qdrant/__init__.py3__all__ = ["QdrantVectorStore"]CODE
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py57logger = logging.getLogger(__name__)CODE
LOW…inecone/llama_index/vector_stores/pinecone/__init__.py3__all__ = ["PineconeVectorStore"]CODE
LOW…wsdocdb/llama_index/vector_stores/awsdocdb/__init__.py3__all__ = ["AWSDocDbVectorStore"]CODE
LOW…es-awsdocdb/llama_index/vector_stores/awsdocdb/base.py29logger = logging.getLogger(__name__)CODE
LOW…es-duckdb/llama_index/vector_stores/duckdb/__init__.py4__all__ = ["DuckDBVectorStore"]CODE
LOW…stores-duckdb/llama_index/vector_stores/duckdb/base.py45logger = logging.getLogger(__name__)CODE
LOW…upabase/llama_index/vector_stores/supabase/__init__.py3__all__ = ["SupabaseVectorStore"]CODE
LOW…es-supabase/llama_index/vector_stores/supabase/base.py24logger = logging.getLogger(__name__)CODE
LOW…-upstash/llama_index/vector_stores/upstash/__init__.py3__all__ = ["UpstashVectorStore"]CODE
LOW…ores-upstash/llama_index/vector_stores/upstash/base.py30logger = logging.getLogger(__name__)CODE
LOW…-lancedb/llama_index/vector_stores/lancedb/__init__.py3__all__ = ["LanceDBVectorStore"]CODE
LOW…ch/llama_index/vector_stores/elasticsearch/__init__.py10__all__ = [CODE
LOW…ostgres/llama_index/vector_stores/postgres/__init__.py3__all__ = ["PGVectorStore"]CODE
LOW…-vectorx/llama_index/vector_stores/vectorx/__init__.py3__all__ = ["VectorXVectorStore"]CODE
LOW…a_index/vector_stores/vertexaivectorsearch/__init__.py9__all__ = [CODE
LOW…-lindorm/llama_index/vector_stores/lindorm/__init__.py6__all__ = ["LindormVectorStore", "LindormVectorClient"]CODE
LOW…dex-vector-stores-lindorm/tests/test_lindorm_client.py23logger = logging.getLogger(__name__)CODE
LOW…sandra/llama_index/vector_stores/cassandra/__init__.py3__all__ = ["CassandraVectorStore"]CODE
LOW…store/llama_index/vector_stores/tablestore/__init__.py4__all__ = ["TablestoreVectorStore"]CODE
LOW…r-stores-zep/llama_index/vector_stores/zep/__init__.py3__all__ = ["ZepVectorStore"]CODE
LOW…ector-stores-zep/llama_index/vector_stores/zep/base.py21logger = logging.getLogger(__name__)CODE
LOW…ksetdb/llama_index/vector_stores/rocksetdb/__init__.py3__all__ = ["RocksetVectorStore"]CODE
LOW…ores-kdbai/llama_index/vector_stores/kdbai/__init__.py4__all__ = ["KDBAIVectorStore"]CODE
LOW…-stores-kdbai/llama_index/vector_stores/kdbai/utils.py4logger = logging.getLogger(__name__)CODE
LOW…r-stores-kdbai/llama_index/vector_stores/kdbai/base.py30logger = logging.getLogger(__name__)CODE
LOW…ureDB/llama_index/vector_stores/ApertureDB/__init__.py3__all__ = ["ApertureDBVectorStore"]CODE
LOW…ndex/vector_stores/alibabacloud_opensearch/__init__.py6__all__ = ["AlibabaCloudOpenSearchConfig", "AlibabaCloudOpenSearchStore"]CODE
LOW…ma_index/vector_stores/alibabacloud_opensearch/base.py36logger = logging.getLogger(__name__)CODE
LOW…/llama_index/vector_stores/tencentvectordb/__init__.py7__all__ = ["TencentVectorDB", "CollectionParams", "FilterField"]CODE
LOW…ama_index/vector_stores/alibabacloud_mysql/__init__.py5__all__ = ["AlibabaCloudMySQLVectorStore"]CODE
LOW…es-milvus/llama_index/vector_stores/milvus/__init__.py3__all__ = ["MilvusVectorStore", "IndexManagement"]CODE
LOW…tores-milvus/llama_index/vector_stores/milvus/utils.py28logger = logging.getLogger(__name__)CODE
LOW…stores-milvus/llama_index/vector_stores/milvus/base.py53logger = logging.getLogger(__name__)CODE
LOW…ticdb/llama_index/vector_stores/analyticdb/__init__.py3__all__ = ["AnalyticDBVectorStore"]CODE
LOW…tor-stores-s3/llama_index/vector_stores/s3/__init__.py3__all__ = ["S3VectorStore"]CODE
LOW…-vector-stores-s3/llama_index/vector_stores/s3/base.py32logger = logging.getLogger(__name__)CODE
LOW…racledb/llama_index/vector_stores/oracledb/__init__.py3__all__ = ["OraLlamaVS", "DistanceStrategy"]CODE
LOW…es-oracledb/llama_index/vector_stores/oracledb/base.py50logger = logging.getLogger(__name__)CODE
LOW…ctor/llama_index/vector_stores/neo4jvector/__init__.py3__all__ = ["Neo4jVectorStore"]CODE
LOW…eeplake/llama_index/vector_stores/deeplake/__init__.py3__all__ = ["DeepLakeVectorStore"]CODE
LOW…es-deeplake/llama_index/vector_stores/deeplake/base.py320logger = logging.getLogger(__name__)CODE
LOW…chbase/llama_index/vector_stores/couchbase/__init__.py12__all__ = [CODE
LOW…-couchbase/llama_index/vector_stores/couchbase/base.py34logger = logging.getLogger(__name__)CODE
LOW…eaviate/llama_index/vector_stores/weaviate/__init__.py7__all__ = [CODE
LOW…db/llama_index/vector_stores/baiduvectordb/__init__.py7__all__ = ["BaiduVectorDB", "TableParams", "TableField"]CODE
LOW…ctordb/llama_index/vector_stores/baiduvectordb/base.py24logger = logging.getLogger(__name__)CODE
1068 more matches not shown…
Docstring Block Structure194 hits · 970 pts
SeverityFileLineSnippetContext
HIGH…stores-qdrant/llama_index/vector_stores/qdrant/base.py73 Qdrant Vector Store. In this vector store, embeddings and docs are stored within a Qdrant collection. STRING
HIGH…stores-qdrant/llama_index/vector_stores/qdrant/base.py569 Asynchronous method to add nodes to Qdrant index. Args: nodes: List[BaseNode]: List of nodSTRING
HIGH…ores-lancedb/llama_index/vector_stores/lancedb/base.py96 The LanceDB Vector Store. Stores text and embeddings in LanceDB. The vector store will open an existing STRING
HIGH…search/llama_index/vector_stores/elasticsearch/base.py125 Elasticsearch vector store. Args: index_name: Name of the Elasticsearch index. es_client: OptiSTRING
HIGH…search/llama_index/vector_stores/elasticsearch/base.py295 Add nodes to Elasticsearch index. Args: nodes: List of nodes with embeddings. STRING
HIGH…search/llama_index/vector_stores/elasticsearch/base.py328 Asynchronous method to add nodes to Elasticsearch index. Args: nodes: List of nodes with eSTRING
HIGH…search/llama_index/vector_stores/elasticsearch/base.py476 Query index for top k most similar nodes. Args: query_embedding (List[float]): query embedSTRING
HIGH…search/llama_index/vector_stores/elasticsearch/base.py511 Asynchronous query index for top k most similar nodes. Args: query_embedding (VectorStoreQSTRING
HIGH…search/llama_index/vector_stores/elasticsearch/base.py589 Asynchronously get nodes from Elasticsearch index. Args: node_ids (Optional[List[str]]): LSTRING
HIGH…lama_index/vector_stores/vertexaivectorsearch/utils.py537 Convert llama-index MetadataFilters to Vertex V2 filter dictionary. V2 filter format: - Simple: ``{"field"STRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py661 Add nodes to index. Args: nodes (list[BaseNode]): list of nodes is_complete_ovSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py893 Asynchronously add nodes to index. Args: nodes (list[BaseNode]): list of nodes with embeddSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py1367 Search index for nodes using a specific search mode. Supported modes: * DEFAULT: Dense vectorSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py1533 Asynchronously search index for nodes using a specific search mode. Supported modes: * DEFAULSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py1704 Build a search object for dense vector similarity search. This search type relies on client-side embedSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py1748 Build a search object for sparse vector similarity search. This search type relies on client-side embeSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py1794 Build a search object for full-text keyword search. Args: query: Query with ``query_str`` STRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py1837 Build a search object for semantic similarity search. This search type relies on server-side auto-embeSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py1908 Build a query for hybrid search: vector + text search with server-side RRF. Text search based on ``queSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py1998 Build a query for semantic hybrid: dense/sparse vector + semantic search with RRF. Uses ``BatchSearchDSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py2519 Access nodes from the vector store synchronously by ID or filter results. This is not a search operatiSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py2551 Query nodes from the vector store synchronously by ID or filter results. This method constructs a ``QuSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py2611 Access nodes from the vector store asynchronously by ID or filter results. This is not a search operatSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py2643 Query nodes from the vector store asynchronously by ID or filter results. This method constructs a ``QSTRING
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py2801 Extract a ``TextNode`` and its ID from a Vertex ``DataObject``. Args: data_obj: A Vertex `STRING
HIGH…ablestore/llama_index/vector_stores/tablestore/base.py24 Tablestore vector store. In this vector store we store the text, its embedding and its metadata in TablestSTRING
HIGH…stores-milvus/llama_index/vector_stores/milvus/base.py119 The Milvus Vector Store. In this vector store we store the text, its embedding and a its metadata in a MilSTRING
HIGH…stores-milvus/llama_index/vector_stores/milvus/base.py437 Add the embeddings and their nodes into Milvus. Args: nodes (List[BaseNode]): List of nodeSTRING
HIGH…stores-milvus/llama_index/vector_stores/milvus/base.py708 Get nodes by node ids or metadata filters. Args: node_ids (Optional[List[str]], optional):STRING
HIGH…-vector-stores-s3/llama_index/vector_stores/s3/base.py314 Asynchronous method to add nodes to Qdrant index. Args: nodes: List[BaseNode]: List of nodSTRING
HIGH…es-deeplake/llama_index/vector_stores/deeplake/base.py581 Query index for top k most similar nodes. Args: query (VectorStoreQuery): VectorStoreQuerySTRING
HIGH…stores-chroma/llama_index/vector_stores/chroma/base.py372 Query index for top k most similar nodes. Args: query (VectorStoreQuery): Query object conSTRING
HIGH…res-solr/llama_index/vector_stores/solr/query_utils.py50 Convert a single metadata filter to Solr query string format. Handles various filter operators (EQ, NE, GT, LT,STRING
HIGH…res-solr/llama_index/vector_stores/solr/query_utils.py146 Recursively unpack metadata filters to Solr filter query. Notes: Solr has issues with complex filters. We haveSTRING
HIGH…tor-stores-solr/llama_index/vector_stores/solr/base.py182 Build a dense vector KNN query for Solr. Args: query: The vector store query containing emSTRING
HIGH…tor-stores-solr/llama_index/vector_stores/solr/base.py224 Build a BM25 text search query for Solr. Args: query: The vector store query containing thSTRING
HIGH…tor-stores-solr/llama_index/vector_stores/solr/base.py315 Convert Solr search results to LlamaIndex VectorStoreQueryResult format. This method transforms raw SolSTRING
HIGH…tor-stores-solr/llama_index/vector_stores/solr/base.py417 Execute a synchronous search query against the Solr vector store. This method supports both dense vectSTRING
HIGH…tor-stores-solr/llama_index/vector_stores/solr/base.py484 Execute an asynchronous search query against the Solr vector store. This method supports both dense veSTRING
HIGH…tor-stores-solr/llama_index/vector_stores/solr/base.py644 Asynchronously add nodes (documents) to a Solr collection. Mapping from Solr fields to :py:class:`llamSTRING
HIGH…res-solr/llama_index/vector_stores/solr/client/sync.py189 Delete documents from the Solr collection using their IDs. If the set of IDs is known, this is generalSTRING
HIGH…es-solr/llama_index/vector_stores/solr/client/utils.py19 Format an input :py:class:`datetime.datetime` or :py:class:`datetime.date` into a Solr-compatible date string. STRING
HIGH…s-solr/llama_index/vector_stores/solr/client/async_.py224 Asynchronously delete documents from the Solr collection using their IDs. If the set of IDs is known, STRING
HIGH…ores-epsilla/llama_index/vector_stores/epsilla/base.py29 The Epsilla Vector Store. In this vector store we store the text, its embedding and a few pieces of its meSTRING
HIGH…idbvector/llama_index/vector_stores/tidbvector/base.py162 Perform a similarity search with the given query embedding. Args: query (VectorStoreQuery)STRING
HIGH…idbvector/llama_index/vector_stores/tidbvector/base.py240 Converts metadata filters to TiDB filters. Args: metadata_filters (Optional[MetadataFilterSTRING
HIGH…es-bigquery/llama_index/vector_stores/bigquery/base.py446 Retrieve nodes from BigQuery using node IDs, metadata filters, or both. If both `node_ids` and `filterSTRING
HIGH…tor-stores-tair/llama_index/vector_stores/tair/base.py42 Initialize TairVectorStore. Two index types are available: FLAT & HNSW. index args for HNSW: - efSTRING
HIGH…tor-stores-tair/llama_index/vector_stores/tair/base.py213 Query the index. Args: query (VectorStoreQuery): query object Returns: STRING
HIGH…r-stores-redis/llama_index/vector_stores/redis/base.py85 RedisVectorStore. The RedisVectorStore takes a user-defined schema object and a Redis connection client orSTRING
HIGH…r-stores-redis/llama_index/vector_stores/redis/base.py305 Add nodes to the index. Args: nodes (List[BaseNode]): List of nodes with embeddings STRING
HIGH…r-stores-redis/llama_index/vector_stores/redis/base.py364 Add nodes to the index. Args: nodes (List[BaseNode]): List of nodes with embeddings STRING
HIGH…r-stores-redis/llama_index/vector_stores/redis/base.py644 Translate a standard metadata filter to a Redis specific filter expression. Args: field (BSTRING
HIGH…r-stores-redis/llama_index/vector_stores/redis/base.py819 Query the index. Args: query (VectorStoreQuery): query object Returns: STRING
HIGH…r-stores-redis/llama_index/vector_stores/redis/base.py864 Query the index. Args: query (VectorStoreQuery): query object Returns: STRING
HIGH…stores-google/llama_index/vector_stores/google/base.py168 Create an instance that points to an existing corpus. Args: corpus_id (str): ID of an exisSTRING
HIGH…stores-google/llama_index/vector_stores/google/base.py207 Create an instance that points to a newly created corpus. Examples: store = GoogleVectorStSTRING
HIGH…db/llama_index/indices/managed/lancedb/query_engine.py94 Executes a query against the managed LanceDB index. Args: query_str (Optional[str]): The tSTRING
HIGH…db/llama_index/indices/managed/lancedb/query_engine.py130 Asynchronously executes a query against the managed LanceDB index. Args: query_str (OptionSTRING
HIGH…ncedb/llama_index/indices/managed/lancedb/retriever.py75 Retrieves nodes relevant to the given query. Args: query_str (Optional[str]): The text queSTRING
134 more matches not shown…
Excessive Try-Catch Wrapping773 hits · 851 pts
SeverityFileLineSnippetContext
LOW…ng/putting_it_all_together/apps/fullstack_app_guide.md239 except Exception as e:CODE
LOW…putting_it_all_together/apps/fullstack_with_delphic.md287 except Exception as e:CODE
MEDIUM…putting_it_all_together/apps/fullstack_with_delphic.md278def connect(self):CODE
LOW…ndex-utils-oracleai/llama_index/utils/oracleai/base.py169 except Exception as ex:CODE
LOW…lama-index-utils-oracleai/tests/test_utils_oracleai.py43 except Exception as e:CODE
MEDIUM…lama-index-utils-oracleai/tests/test_utils_oracleai.py44 # print("Error: ", e)COMMENT
MEDIUM…lama-index-utils-oracleai/tests/test_utils_oracleai.py16def test_summary_test() -> None:CODE
LOW…tores-qdrant/llama_index/vector_stores/qdrant/utils.py91 except Exception:CODE
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py1355 except Exception:CODE
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py1638 except Exception as e:CODE
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py1676 except Exception as e:CODE
LOW…res/llama-index-vector-stores-qdrant/tests/conftest.py158 except Exception:CODE
LOW…res/llama-index-vector-stores-qdrant/tests/conftest.py162 except Exception:CODE
LOW…res/llama-index-vector-stores-qdrant/tests/conftest.py166 except Exception:CODE
LOW…res/llama-index-vector-stores-qdrant/tests/conftest.py233 except Exception:CODE
LOW…res/llama-index-vector-stores-qdrant/tests/conftest.py237 except Exception:CODE
LOW…res/llama-index-vector-stores-qdrant/tests/conftest.py241 except Exception:CODE
LOW…res/llama-index-vector-stores-qdrant/tests/conftest.py319 except Exception:CODE
LOW…res/llama-index-vector-stores-qdrant/tests/conftest.py323 except Exception:CODE
LOW…res/llama-index-vector-stores-qdrant/tests/conftest.py327 except Exception:CODE
LOW…es-pinecone/llama_index/vector_stores/pinecone/base.py405 except Exception:CODE
LOW…es-pinecone/llama_index/vector_stores/pinecone/base.py526 except Exception:CODE
LOW…es-awsdocdb/llama_index/vector_stores/awsdocdb/base.py273 except Exception:CODE
LOW…llama-index-vector-stores-awsdocdb/tests/test_docdb.py72except Exception:CODE
LOW…es-supabase/llama_index/vector_stores/supabase/base.py202 except Exception:CODE
LOW…ores-lancedb/llama_index/vector_stores/lancedb/base.py296 except Exception as e:CODE
LOW…ores-lancedb/llama_index/vector_stores/lancedb/base.py468 except Exception:CODE
LOW…ores-lancedb/llama_index/vector_stores/lancedb/base.py571 except Exception:CODE
LOW…earch/llama_index/vector_stores/elasticsearch/utils.py80 except Exception:CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py598 except Exception as e:CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py604 except Exception as e:CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py610 except Exception as e:CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py617 except Exception as e:CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py1395 except Exception:CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py1623 except Exception:CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py1678 except Exception:CODE
LOW…ores-vectorx/llama_index/vector_stores/vectorx/base.py165 except Exception as e:CODE
LOW…ores-vectorx/llama_index/vector_stores/vectorx/base.py276 except Exception as e:CODE
LOW…ores-vectorx/llama_index/vector_stores/vectorx/base.py296 except Exception:CODE
LOW…ores-vectorx/llama_index/vector_stores/vectorx/base.py355 except Exception as e:CODE
LOW…tor-stores-vectorx/tests/test_vector_stores_vectorx.py82 except Exception as e:CODE
MEDIUM…tor-stores-vectorx/tests/test_vector_stores_vectorx.py84 print(f"Error deleting test index {index_name}: {e}")CODE
LOW…tor-stores-vectorx/tests/test_vector_stores_vectorx.py96 except Exception as e:CODE
MEDIUM…tor-stores-vectorx/tests/test_vector_stores_vectorx.py97 print(f"Error cleaning up test index {index_name}: {e}")CODE
LOW…tor-stores-vectorx/tests/test_vector_stores_vectorx.py98 except Exception as e:CODE
MEDIUM…tor-stores-vectorx/tests/test_vector_stores_vectorx.py99 print(f"Error listing indexes for cleanup: {e}")CODE
MEDIUM…tor-stores-vectorx/tests/test_vector_stores_vectorx.py86def tearDown(self):CODE
LOW…lama_index/vector_stores/vertexaivectorsearch/utils.py142 except Exception as e:CODE
LOW…lama_index/vector_stores/vertexaivectorsearch/utils.py457 except Exception as e:CODE
LOW…lama_index/vector_stores/vertexaivectorsearch/utils.py486 except Exception as e: # noqa: PERF203CODE
LOW…llama_index/vector_stores/vertexaivectorsearch/base.py795 except Exception as exc:CODE
LOW…llama_index/vector_stores/vertexaivectorsearch/base.py840 except Exception as exc:CODE
LOW…llama_index/vector_stores/vertexaivectorsearch/base.py1021 except Exception as exc:CODE
LOW…llama_index/vector_stores/vertexaivectorsearch/base.py1105 except Exception as exc:CODE
LOW…llama_index/vector_stores/vertexaivectorsearch/base.py1247 except Exception as exc:CODE
LOW…llama_index/vector_stores/vertexaivectorsearch/base.py1353 except Exception as exc:CODE
LOW…ores-lindorm/llama_index/vector_stores/lindorm/base.py737 except Exception:CODE
LOW…ores-tablestore/tests/test_vector_stores_tablestore.py232 except Exception as e:CODE
LOW…r-stores-kdbai/llama_index/vector_stores/kdbai/base.py156 except Exception as e:CODE
LOW…r-stores-kdbai/llama_index/vector_stores/kdbai/base.py169 except Exception as e:CODE
713 more matches not shown…
Magic Placeholder Names172 hits · 754 pts
SeverityFileLineSnippetContext
HIGH…ent/docs/framework/module_guides/mcp/llamacloud_mcp.md61llamacloud-mcp --index "index-name:Description" --extract-agent "name:description" --org-id YOUR_ORG_ID --project-id YOUCODE
HIGH…ations/retrievers/llama-index-retrievers-you/README.md17retriever = YouRetriever(api_key="your-api-key")CODE
HIGH…s-dappier/tests/test_tools_dappier_real_time_search.py20 tool_instance = DappierRealTimeSearchToolSpec(api_key="your-api-key")CODE
HIGH…dappier/tests/test_tools_dappier_ai_recommendations.py22 tool = DappierAIRecommendationsToolSpec(api_key="your-api-key")CODE
HIGH…integrations/tools/llama-index-tools-shopify/README.md41 "your-store.myshopify.com", "2023-04", "your-api-key"STRING
HIGH…/llama-index-tools-valyu/examples/retriever_example.py18 api_key=os.environ.get("VALYU_API_KEY", "your-api-key-here"),CODE
HIGH…ntegrations/tools/llama-index-tools-airweave/README.md252 api_key="your-api-key",STRING
HIGH…-integrations/tools/llama-index-tools-serpex/README.md33 api_key="your_api_key",CODE
HIGH…-integrations/tools/llama-index-tools-serpex/README.md57export SERPEX_API_KEY=your_api_keyCODE
HIGH…egrations/tools/llama-index-tools-serpex/test_local.py15 print(' export SERPEX_API_KEY="your_api_key"')CODE
HIGH…ma-index-tools-serpex/llama_index/tools/serpex/base.py31 >>> tool = SerpexToolSpec(api_key="your_api_key")STRING
HIGH…tools/llama-index-tools-parallel-web-systems/README.md28 api_key="your-api-key-here",CODE
HIGH…tools/llama-index-tools-parallel-web-systems/README.md65parallel_tool = ParallelWebSystemsToolSpec(api_key="your-api-key")CODE
HIGH…tools/llama-index-tools-parallel-web-systems/README.md106parallel_tool = ParallelWebSystemsToolSpec(api_key="your-api-key")CODE
HIGH…egrations/tools/llama-index-tools-brightdata/README.md15Sign up at [Bright Data](https://brightdata.com/?utm_source=tech-partner&utm_medium=link&utm_campaign=llamaindex&hs_signCODE
HIGH…egrations/tools/llama-index-tools-brightdata/README.md26brightdata_tool = BrightDataToolSpec(api_key="your-api-key", zone="unlocker")CODE
HIGH…mbeddings-llm-rails/tests/test_embeddings_llm_rails.py14 return "your_api_key"CODE
HIGH…s/embeddings/llama-index-embeddings-voyageai/README.md22export VOYAGE_API_KEY="your-api-key-here"CODE
HIGH…s/embeddings/llama-index-embeddings-voyageai/README.md35 voyage_api_key="your-api-key", # Optional if VOYAGE_API_KEY is setCODE
HIGH…s/embeddings/llama-index-embeddings-voyageai/README.md73 voyage_api_key="your-api-key",CODE
HIGH…s/embeddings/llama-index-embeddings-voyageai/README.md213 model_name="voyage-3.5", voyage_api_key="your-api-key"CODE
HIGH…ons/embeddings/llama-index-embeddings-nebius/README.md20NEBIUS_API_KEY=your_api_keyCODE
HIGH…ons/embeddings/llama-index-embeddings-nebius/README.md36 api_key="your_api_key", model_name="BAAI/bge-en-icl"CODE
HIGH…ference/llama_index/embeddings/azure_inference/base.py36 credential="your-api-key",STRING
HIGH…ns/embeddings/llama-index-embeddings-baseten/README.md25 api_key="YOUR_API_KEY",CODE
HIGH…eddings-baseten/llama_index/embeddings/baseten/base.py37 api_key="YOUR_API_KEY",STRING
HIGH…ns/embeddings/llama-index-embeddings-isaacus/README.md31export ISAACUS_API_KEY="your-api-key-here"CODE
HIGH…/embeddings/llama-index-embeddings-fireworks/README.md20 api_key="your-api-key", # or set FIREWORKS_API_KEY env varCODE
HIGH…/embeddings/llama-index-embeddings-yandexgpt/README.md26 api_key="your-api-key",CODE
HIGH…ngs-yandexgpt/llama_index/embeddings/yandexgpt/base.py42 api_key="your-api-key",STRING
HIGH…ddings/llama-index-embeddings-autoembeddings/README.md35os.environ["OPENAI_API_KEY"] = "YOUR-API-KEY"CODE
HIGH…or/llama-index-postprocessor-voyageai-rerank/README.md20export VOYAGE_API_KEY="your-api-key-here"CODE
HIGH…or/llama-index-postprocessor-voyageai-rerank/README.md42 api_key="your-api-key", # Optional if VOYAGE_API_KEY is setCODE
HIGH…aph_stores/llama-index-graph-stores-memgraph/README.md33] = "<YOUR_API_KEY>" # Replace with your OpenAI API keyCODE
HIGH…aph_stores/llama-index-graph-stores-memgraph/README.md33] = "<YOUR_API_KEY>" # Replace with your OpenAI API keyCODE
HIGH…aph_stores/llama-index-graph-stores-memgraph/README.md99] = "<YOUR_API_KEY>" # Replace with your OpenAI API keyCODE
HIGH…aph_stores/llama-index-graph-stores-memgraph/README.md99] = "<YOUR_API_KEY>" # Replace with your OpenAI API keyCODE
HIGH…ions/graph_rag/llama-index-graph-rag-cognee/example.py27 print(" export OPENAI_API_KEY='your-api-key-here'")CODE
HIGH…-index-graph-rag-cognee/tests/test_graph_rag_cognee.py35 llm_api_key=os.getenv("OPENAI_API_KEY", "your-api-key"),CODE
HIGH…-index-graph-rag-cognee/tests/test_graph_rag_cognee.py91 llm_api_key=os.getenv("OPENAI_API_KEY", "your-api-key"),CODE
HIGH…-index-graph-rag-cognee/tests/test_graph_rag_cognee.py122 llm_api_key=os.getenv("OPENAI_API_KEY", "your-api-key"),CODE
HIGH…-index-graph-rag-cognee/tests/test_graph_rag_cognee.py143 llm_api_key=os.getenv("OPENAI_API_KEY", "your-api-key"),CODE
HIGH…-index-graph-rag-cognee/tests/test_graph_rag_cognee.py177 llm_api_key=os.getenv("OPENAI_API_KEY", "your-api-key"),CODE
HIGH…-index-graph-rag-cognee/tests/test_graph_rag_cognee.py204 llm_api_key=os.getenv("OPENAI_API_KEY", "your-api-key"),CODE
HIGH…-index-graph-rag-cognee/tests/test_graph_rag_cognee.py258 llm_api_key=os.getenv("OPENAI_API_KEY", "your-api-key"),CODE
HIGH…ag/llama-index-graph-rag-cognee/tests/test_add_data.py25 llm_api_key=os.getenv("OPENAI_API_KEY", "your-api-key"),CODE
HIGH…a-index-graph-rag-cognee/tests/test_visualize_graph.py21 llm_api_key=os.getenv("OPENAI_API_KEY", "your-api-key"),CODE
HIGH…tions/readers/llama-index-readers-preprocess/README.md43 api_key="your-api-key", filepath="valid/path/to/file"CODE
HIGH…tions/readers/llama-index-readers-preprocess/README.md61 api_key="your-api-key", filepath="valid/path/to/file"CODE
HIGH…tions/readers/llama-index-readers-preprocess/README.md77 api_key="your-api-key", filepath="valid/path/to/file"CODE
HIGH…tions/readers/llama-index-readers-preprocess/README.md86loader = PreprocessReader(api_key="your-api-key", process_id="your-process-id")CODE
HIGH…aders-google/llama_index/readers/google/maps/README.md18export GOOGLE_MAPS_API_KEY="YOUR_API_KEY"CODE
HIGH…aders-google/llama_index/readers/google/maps/README.md26os.environ["GOOGLE_MAPS_API_KEY"] = "YOUR_API_KEY"CODE
HIGH…aders-web/llama_index/readers/web/spider_web/README.md20 api_key="YOUR_API_KEY", # Get one at https://spider.cloudCODE
HIGH…aders-web/llama_index/readers/web/spider_web/README.md34 api_key="YOUR_API_KEY",CODE
HIGH…ions/readers/llama-index-readers-document360/README.md16reader = Document360Reader(api_key="your_api_key")CODE
HIGH…ions/readers/llama-index-readers-document360/README.md94reader = Document360Reader(api_key="your_api_key")CODE
HIGH…grations/readers/llama-index-readers-whisper/README.md23 api_key="your-api-key",CODE
HIGH…rations/readers/llama-index-readers-layoutir/README.md149 api_key="your_api_key", # Optional: for remote processingCODE
HIGH…grations/readers/llama-index-readers-upstage/README.md38os.environ["UPSTAGE_API_KEY"] = "YOUR_API_KEY"CODE
112 more matches not shown…
Deep Nesting592 hits · 574 pts
SeverityFileLineSnippetContext
LOW…umentation/src/llama_index_instrumentation/__init__.py57CODE
LOW…rc/llama_index_instrumentation/span_handlers/simple.py95CODE
LOWdocs/scripts/prepare_for_build.py118CODE
LOW…ndex-utils-oracleai/llama_index/utils/oracleai/base.py46CODE
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py321CODE
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py563CODE
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py1023CODE
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py1172CODE
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py1379CODE
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py1603CODE
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py1643CODE
LOW…es-pinecone/llama_index/vector_stores/pinecone/base.py54CODE
LOW…es-pinecone/llama_index/vector_stores/pinecone/base.py76CODE
LOW…ores-upstash/llama_index/vector_stores/upstash/base.py35CODE
LOW…ores-lancedb/llama_index/vector_stores/lancedb/base.py47CODE
LOW…ores-lancedb/llama_index/vector_stores/lancedb/base.py174CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py591CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py657CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py690CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py1414CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py1442CODE
LOW…ores-vectorx/llama_index/vector_stores/vectorx/base.py284CODE
LOW…tor-stores-vectorx/tests/test_vector_stores_vectorx.py86CODE
LOW…lama_index/vector_stores/vertexaivectorsearch/utils.py213CODE
LOW…lama_index/vector_stores/vertexaivectorsearch/utils.py379CODE
LOW…llama_index/vector_stores/vertexaivectorsearch/base.py2800CODE
LOW…-cassandra/llama_index/vector_stores/cassandra/base.py221CODE
LOW…ablestore/llama_index/vector_stores/tablestore/base.py629CODE
LOW…r-stores-kdbai/llama_index/vector_stores/kdbai/base.py102CODE
LOW…pertureDB/llama_index/vector_stores/ApertureDB/base.py339CODE
LOW…pertureDB/llama_index/vector_stores/ApertureDB/base.py344CODE
LOW…ma_index/vector_stores/alibabacloud_opensearch/base.py237CODE
LOW…ordb/llama_index/vector_stores/tencentvectordb/base.py362CODE
LOW…ordb/llama_index/vector_stores/tencentvectordb/base.py434CODE
LOW…l/llama_index/vector_stores/alibabacloud_mysql/base.py325CODE
LOW…l/llama_index/vector_stores/alibabacloud_mysql/base.py784CODE
LOW…es-alibabacloud-mysql/tests/test_alibabacloud_mysql.py658CODE
LOW…es-alibabacloud-mysql/tests/test_alibabacloud_mysql.py735CODE
LOW…es-alibabacloud-mysql/tests/test_alibabacloud_mysql.py672CODE
LOW…es-alibabacloud-mysql/tests/test_alibabacloud_mysql.py749CODE
LOW…tores-milvus/llama_index/vector_stores/milvus/utils.py126CODE
LOW…stores-milvus/llama_index/vector_stores/milvus/base.py1374CODE
LOW…-vector-stores-s3/llama_index/vector_stores/s3/base.py512CODE
LOW…-vector-stores-s3/llama_index/vector_stores/s3/base.py550CODE
LOW…es-oracledb/llama_index/vector_stores/oracledb/base.py256CODE
LOW…es-oracledb/llama_index/vector_stores/oracledb/base.py525CODE
LOW…es-oracledb/llama_index/vector_stores/oracledb/base.py675CODE
LOW…4jvector/llama_index/vector_stores/neo4jvector/base.py111CODE
LOW…es-deeplake/llama_index/vector_stores/deeplake/base.py438CODE
LOW…es-deeplake/llama_index/vector_stores/deeplake/base.py453CODE
LOW…es-deeplake/llama_index/vector_stores/deeplake/base.py272CODE
LOW…-couchbase/llama_index/vector_stores/couchbase/base.py74CODE
LOW…-couchbase/llama_index/vector_stores/couchbase/base.py148CODE
LOW…-couchbase/llama_index/vector_stores/couchbase/base.py165CODE
LOW…es-weaviate/llama_index/vector_stores/weaviate/base.py87CODE
LOW…es-weaviate/llama_index/vector_stores/weaviate/base.py134CODE
LOW…es-weaviate/llama_index/vector_stores/weaviate/base.py169CODE
LOW…es-weaviate/llama_index/vector_stores/weaviate/base.py258CODE
LOW…ctordb/llama_index/vector_stores/baiduvectordb/base.py229CODE
LOW…ctordb/llama_index/vector_stores/baiduvectordb/base.py469CODE
532 more matches not shown…
Self-Referential Comments193 hits · 546 pts
SeverityFileLineSnippetContext
MEDIUM…ector-stores-qdrant/tests/test_vector_stores_qdrant.py141 # Create a mock Qdrant clientCOMMENT
MEDIUM…search/llama_index/vector_stores/elasticsearch/base.py162 es_api_key = "<api-key>" # Create an API key within Kibana (Security -> API Keys)STRING
MEDIUM…ores-vectorx/llama_index/vector_stores/vectorx/base.py171 # Create a new index if it doesn't existCOMMENT
MEDIUM…dex-vector-stores-lindorm/tests/test_lindorm_client.py40 # Create a client and vector store instanceCOMMENT
MEDIUM…ordb/llama_index/vector_stores/tencentvectordb/base.py182 # Create an instance of TencentVectorDBSTRING
MEDIUM…es-alibabacloud-mysql/tests/test_alibabacloud_mysql.py306 # Create a test nodeCOMMENT
MEDIUM…stores-milvus/llama_index/vector_stores/milvus/base.py374 # Create the collection & index if it does not existCOMMENT
MEDIUM…es-oracledb/llama_index/vector_stores/oracledb/base.py67# Define a type variable that can be any kind of functionCOMMENT
MEDIUM…es-deeplake/llama_index/vector_stores/deeplake/base.py339 # Create an instance of DeepLakeVectorStoreSTRING
MEDIUM…s-couchbase/tests/test_couchbase_query_vector_store.py400 # Create a KNN vector storeCOMMENT
MEDIUM…s-couchbase/tests/test_couchbase_query_vector_store.py628 # Create a test node with custom field mappingCOMMENT
MEDIUM…s-couchbase/tests/test_couchbase_query_vector_store.py721 # Create a larger batch of documentsCOMMENT
MEDIUM…ctor/llama_index/vector_stores/timescalevector/base.py43 # Create a TimescaleVectorStore instanceSTRING
MEDIUM…search/llama_index/vector_stores/azureaisearch/base.py115 # Creating an Azure AI Search Vector StoreSTRING
MEDIUM…ector-stores-azureaisearch/tests/test_azureaisearch.py228 # Create a sample queryCOMMENT
MEDIUM…ector-stores-azureaisearch/tests/test_azureaisearch.py299 # Create a sample queryCOMMENT
MEDIUM…ector-stores-azureaisearch/tests/test_azureaisearch.py439 # Create a mock search client that will be returned by get_search_clientCOMMENT
MEDIUM…ector-stores-azureaisearch/tests/test_azureaisearch.py473 # Create a mock search client that will be returned by get_search_clientCOMMENT
MEDIUM…ores-mongodb/llama_index/vector_stores/mongodb/base.py102 # Create an instance of MongoDBAtlasVectorSearchSTRING
MEDIUM…ores-mongodb/llama_index/vector_stores/mongodb/base.py110 # Create a vector search index programmaticallySTRING
MEDIUM…ores-mongodb/llama_index/vector_stores/mongodb/base.py113 # Create a text search index programmaticallySTRING
MEDIUM…dex-vector-stores-mongodb/tests/test_index_commands.py77 # Create a Vector Search Index on index_nameCOMMENT
MEDIUM…dex-vector-stores-mongodb/tests/test_index_commands.py170 # Create a Vector Search Index on index_nameCOMMENT
MEDIUM…es-astra-db/llama_index/vector_stores/astra_db/base.py74 # Create the Astra DB Vector Store objectSTRING
MEDIUM…es-astra-db/llama_index/vector_stores/astra_db/base.py410 # Create a new node object from the node metadataCOMMENT
MEDIUM…es-astra-db/llama_index/vector_stores/astra_db/base.py592 # Create a new node object from the node metadataCOMMENT
MEDIUM…stores-chroma/llama_index/vector_stores/chroma/base.py143 # Create a Chroma client and collectionSTRING
MEDIUM…stores-chroma/llama_index/vector_stores/chroma/base.py614 # Create a mapping from valid embedding indices to original prefetch indicesCOMMENT
MEDIUM…ores-lantern/llama_index/vector_stores/lantern/base.py145 # Create an instance of LanternVectorStoreSTRING
MEDIUM…llama-index-vector-stores-nile/examples/multitenant.py21# Create a NileVectorStore instanceCOMMENT
MEDIUM…llama-index-vector-stores-nile/examples/multitenant.py58# Create a vector index (optional, the default index is flat also known as no index)COMMENT
MEDIUM…es-moorcheh/llama_index/vector_stores/moorcheh/base.py1# Importing required libraries and modulesCOMMENT
MEDIUM…es-wordlift/llama_index/vector_stores/wordlift/base.py203 # Create the IDs.COMMENT
MEDIUM…ngo/llama_index/vector_stores/azurecosmosmongo/base.py48 # Create an instance of AzureCosmosDBMongoDBVectorSearchSTRING
MEDIUM…-typesense/llama_index/vector_stores/typesense/base.py69 # Create an instance of TypesenseVectorStoreSTRING
MEDIUM…-typesense/llama_index/vector_stores/typesense/base.py184 # Create the collection if it doesn't already existCOMMENT
MEDIUM…ector-stores-db2/llama_index/vector_stores/db2/base.py60# Define a type variable that can be any kind of functionCOMMENT
MEDIUM…ndex-vector-stores-db2/tests/test_vector_stores_db2.py225# Define a list of documents (These dummy examples are 4 random documents )COMMENT
MEDIUM…ndex-vector-stores-db2/tests/test_vector_stores_db2.py287 # Create a TextNode instanceCOMMENT
MEDIUM…carray/llama_index/vector_stores/docarray/in_memory.py19 # Create an instance of DocArrayInMemoryVectorStoreSTRING
MEDIUM…sql/llama_index/vector_stores/azurecosmosnosql/base.py136 # Create the collection if it already doesn't existCOMMENT
MEDIUM…tor-stores-tair/llama_index/vector_stores/tair/base.py74 # Create a TairVectorStoreSTRING
MEDIUM…riever/llama_index/retrievers/duckdb_retriever/base.py71 # Create an FTS index on the 'text' column if it doesn't already existCOMMENT
MEDIUM…-index-ingestion-ray/llama_index/ingestion/ray/base.py121 "batch_size": 10, # Define the batch sizeSTRING
MEDIUM…-index-ingestion-ray/llama_index/ingestion/ray/base.py132 # Create the Ray ingestion pipelineSTRING
MEDIUM…lama_index/tools/aws_bedrock_agentcore/browser/base.py90 # Create a new browser client for this threadCOMMENT
MEDIUM…x/tools/aws_bedrock_agentcore/code_interpreter/base.py120 # Create a new code interpreter for this threadCOMMENT
MEDIUM…-tools-elevenlabs/llama_index/tools/elevenlabs/base.py36 # Create the clientCOMMENT
MEDIUM…-tools-elevenlabs/llama_index/tools/elevenlabs/base.py93 # Create the VoiceSettingsCOMMENT
MEDIUM…s/tools/llama-index-tools-signnow/examples/from_env.py24 # Create an agent and ask for templates listCOMMENT
MEDIUM…ndex-tools-typecast/llama_index/tools/typecast/base.py56 # Create the clientCOMMENT
MEDIUM…ndex-tools-typecast/llama_index/tools/typecast/base.py96 # Create the clientCOMMENT
MEDIUM…ls/llama-index-tools-mcp/llama_index/tools/mcp/base.py138 # Create a Pydantic model based on the tool inputSchemaCOMMENT
MEDIUM…tegrations/tools/llama-index-tools-mcp/tests/server.py34# Create the MCP serverCOMMENT
MEDIUM…tegrations/tools/llama-index-tools-mcp/tests/server.py84 # Create a random color imageCOMMENT
MEDIUM…ex-tools-artifact-editor/tests/test_artifact_editor.py88 # Create an artifact and test retrievalCOMMENT
MEDIUM…-index-tools-mcp-discovery/tests/test_mcp_discovery.py22# Define a real class for BaseToolSpec so inheritance worksCOMMENT
MEDIUM…enai/llama_index/tools/openai/image_generation/base.py69 # Create an image from the decoded bytes and save itCOMMENT
MEDIUM…ings-ipex-llm/llama_index/embeddings/ipex_llm/utils.py1# This file is adapted fromCOMMENT
MEDIUM…dings-ipex-llm/llama_index/embeddings/ipex_llm/base.py1# This file is adapted fromCOMMENT
133 more matches not shown…
Decorative Section Separators98 hits · 378 pts
SeverityFileLineSnippetContext
MEDIUMllama-index-instrumentation/tests/test_dispatcher.py623 # ┌───────┴───────┐COMMENT
MEDIUM…ndex-utils-oracleai/llama_index/utils/oracleai/base.py1# -----------------------------------------------------------------------------COMMENT
MEDIUM…ndex-utils-oracleai/llama_index/utils/oracleai/base.py6# -----------------------------------------------------------------------------COMMENT
MEDIUM…ndex-utils-oracleai/llama_index/utils/oracleai/base.py8# -----------------------------------------------------------------------------COMMENT
MEDIUM…ector-stores-qdrant/tests/test_vector_stores_qdrant.py938# ---------------------------------------------------------------------------COMMENT
MEDIUM…ector-stores-qdrant/tests/test_vector_stores_qdrant.py940# ---------------------------------------------------------------------------COMMENT
MEDIUM…lama_index/vector_stores/vertexaivectorsearch/utils.py505# =============================================================================COMMENT
MEDIUM…lama_index/vector_stores/vertexaivectorsearch/utils.py507# =============================================================================COMMENT
MEDIUM…earch/tests/test_vector_stores_vertexaivectorsearch.py508# =============================================================================COMMENT
MEDIUM…earch/tests/test_vector_stores_vertexaivectorsearch.py510# =============================================================================COMMENT
MEDIUM…earch/tests/test_vector_stores_vertexaivectorsearch.py738# =============================================================================COMMENT
MEDIUM…earch/tests/test_vector_stores_vertexaivectorsearch.py740# =============================================================================COMMENT
MEDIUM…tores-solr/llama_index/vector_stores/solr/constants.py17# =============================================================================COMMENT
MEDIUM…tores-solr/llama_index/vector_stores/solr/constants.py19# =============================================================================COMMENT
MEDIUM…tores-solr/llama_index/vector_stores/solr/constants.py24# =============================================================================COMMENT
MEDIUM…tores-solr/llama_index/vector_stores/solr/constants.py26# =============================================================================COMMENT
MEDIUM…tores-solr/tests/integration/test_solr_vector_store.py40# ---------------------------------------------------------------------------COMMENT
MEDIUM…tores-solr/tests/integration/test_solr_vector_store.py42# ---------------------------------------------------------------------------COMMENT
MEDIUM…tores-solr/tests/integration/test_solr_vector_store.py109# ---------------------------------------------------------------------------COMMENT
MEDIUM…tores-solr/tests/integration/test_solr_vector_store.py111# ---------------------------------------------------------------------------COMMENT
MEDIUM…tores-solr/tests/integration/test_solr_vector_store.py166# ---------------------------------------------------------------------------COMMENT
MEDIUM…tores-solr/tests/integration/test_solr_vector_store.py168# ---------------------------------------------------------------------------COMMENT
MEDIUM…tores-solr/tests/integration/test_solr_vector_store.py230# ---------------------------------------------------------------------------COMMENT
MEDIUM…tores-solr/tests/integration/test_solr_vector_store.py232# ---------------------------------------------------------------------------COMMENT
MEDIUM…sql/llama_index/vector_stores/volcengine_mysql/base.py169 # ------------------------------------------------------------------COMMENT
MEDIUM…sql/llama_index/vector_stores/volcengine_mysql/base.py171 # ------------------------------------------------------------------COMMENT
MEDIUM…sql/llama_index/vector_stores/volcengine_mysql/base.py207 # ------------------------------------------------------------------COMMENT
MEDIUM…sql/llama_index/vector_stores/volcengine_mysql/base.py209 # ------------------------------------------------------------------COMMENT
MEDIUM…sql/llama_index/vector_stores/volcengine_mysql/base.py281 # ------------------------------------------------------------------COMMENT
MEDIUM…sql/llama_index/vector_stores/volcengine_mysql/base.py283 # ------------------------------------------------------------------COMMENT
MEDIUM…sql/llama_index/vector_stores/volcengine_mysql/base.py625 # ------------------------------------------------------------------COMMENT
MEDIUM…sql/llama_index/vector_stores/volcengine_mysql/base.py627 # ------------------------------------------------------------------COMMENT
MEDIUM…sql/llama_index/vector_stores/volcengine_mysql/base.py470 # ------------------------------------------------------------------STRING
MEDIUM…sql/llama_index/vector_stores/volcengine_mysql/base.py472 # ------------------------------------------------------------------STRING
MEDIUM…ntegrations/tools/llama-index-tools-metaphor/README.md3# ================================================================================COMMENT
MEDIUM…ntegrations/tools/llama-index-tools-metaphor/README.md7# ================================================================================COMMENT
MEDIUM…dings-oracleai/llama_index/embeddings/oracleai/base.py1# -----------------------------------------------------------------------------COMMENT
MEDIUM…dings-oracleai/llama_index/embeddings/oracleai/base.py6# -----------------------------------------------------------------------------COMMENT
MEDIUM…dings-oracleai/llama_index/embeddings/oracleai/base.py8# -----------------------------------------------------------------------------COMMENT
MEDIUM…lity/llama-index-observability-otel/tests/test_otel.py223## ---------------------------------------------------------------------------COMMENT
MEDIUM…lity/llama-index-observability-otel/tests/test_otel.py225# ---------------------------------------------------------------------------COMMENT
MEDIUM…am/llama-index-program-evaporate/tests/test_sandbox.py11# ---------------------------------------------------------------------------COMMENT
MEDIUM…am/llama-index-program-evaporate/tests/test_sandbox.py13# ---------------------------------------------------------------------------COMMENT
MEDIUM…am/llama-index-program-evaporate/tests/test_sandbox.py65# ---------------------------------------------------------------------------COMMENT
MEDIUM…am/llama-index-program-evaporate/tests/test_sandbox.py67# ---------------------------------------------------------------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py39 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py41 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py62 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py64 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py111 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py113 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py209 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py211 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py215 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py217 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py328 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py330 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py337 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py339 # --------------------COMMENT
MEDIUM…ders-web/llama_index/readers/web/firecrawl_web/base.py253 # --------------------COMMENT
38 more matches not shown…
Hallucination Indicators35 hits · 355 pts
SeverityFileLineSnippetContext
CRITICAL…dex-utils/llama-index-utils-qianfan/tests/test_apis.py66 mock_client.return_value.__enter__.return_value.send.assert_called_once()CODE
CRITICAL…dex-utils/llama-index-utils-qianfan/tests/test_apis.py91 mock_client.return_value.__aenter__.return_value.send.assert_called_once()CODE
CRITICAL…x-utils/llama-index-utils-qianfan/tests/test_client.py24 mock_client.return_value.__enter__.return_value.send.assert_called_once()CODE
CRITICAL…x-utils/llama-index-utils-qianfan/tests/test_client.py44 mock_client.return_value.__aenter__.return_value.send.assert_called_once()CODE
CRITICAL…x-utils/llama-index-utils-qianfan/tests/test_client.py62 mock_client.return_value.__enter__.return_value.send.assert_called_once()CODE
CRITICAL…x-utils/llama-index-utils-qianfan/tests/test_client.py87 mock_client.return_value.__aenter__.return_value.send.assert_called_once()CODE
CRITICAL…ector-stores-azureaisearch/tests/test_azureaisearch.py90 search_client._client._config.user_agent_policy.add_user_agent.assert_called_with(CODE
CRITICAL…ector-stores-azureaisearch/tests/test_azureaisearch.py103 index_client._client._config.user_agent_policy.add_user_agent.assert_called_with(CODE
CRITICAL…-index-vector-stores-firestore/tests/test_firestore.py193 vector_store.client.collection.return_value.find_nearest.assert_called_with(CODE
CRITICAL…ference/llama_index/embeddings/azure_inference/base.py20from azure.core.exceptions import HttpResponseErrorCODE
CRITICAL…vstore-azure/llama_index/storage/kvstore/azure/base.py336 from azure.core.exceptions import ResourceNotFoundErrorCODE
CRITICAL…vstore-azure/llama_index/storage/kvstore/azure/base.py361 from azure.core.exceptions import ResourceNotFoundErrorCODE
CRITICAL…vstore-azure/llama_index/storage/kvstore/azure/base.py469 from azure.core.exceptions import ResourceNotFoundErrorCODE
CRITICAL…vstore-azure/llama_index/storage/kvstore/azure/base.py495 from azure.core.exceptions import ResourceNotFoundErrorCODE
CRITICAL…ore-azure/llama_index/storage/chat_store/azure/base.py5from azure.core.exceptions import ResourceNotFoundErrorCODE
CRITICAL…/llama-index-llms-gigachat/tests/test_llms_gigachat.py42 mock_gigachat.return_value.__enter__.return_value.chat.assert_called_once()CODE
CRITICAL…/llama-index-llms-gigachat/tests/test_llms_gigachat.py59 mock_gigachat.return_value.__enter__.return_value.chat.assert_called_once()CODE
CRITICAL…/llama-index-llms-gigachat/tests/test_llms_gigachat.py79 mock_gigachat.return_value.__aenter__.return_value.achat.assert_called_once()CODE
CRITICAL…/llama-index-llms-gigachat/tests/test_llms_gigachat.py99 mock_gigachat.return_value.__aenter__.return_value.achat.assert_called_once()CODE
CRITICAL…ons/llms/llama-index-llms-ai21/tests/test_llms_ai21.py136 llm._client.chat.completions.create.assert_called_once_with(CODE
CRITICAL…ons/llms/llama-index-llms-ai21/tests/test_llms_ai21.py208 llm._client.chat.completions.create.assert_called_once_with(CODE
CRITICAL…ons/llms/llama-index-llms-ai21/tests/test_llms_ai21.py231 llm._client.chat.completions.create.assert_called_once_with(CODE
CRITICAL…ons/llms/llama-index-llms-ai21/tests/test_llms_ai21.py285 llm._client.chat.completions.create.assert_called_once_with(CODE
CRITICAL…ons/llms/llama-index-llms-ai21/tests/test_llms_ai21.py313 llm._async_client.chat.completions.create.assert_called_once_with(CODE
CRITICAL…ons/llms/llama-index-llms-ai21/tests/test_llms_ai21.py341 llm._async_client.chat.completions.create.assert_called_once_with(CODE
CRITICAL…ons/llms/llama-index-llms-ai21/tests/test_llms_ai21.py381 llm._async_client.chat.completions.create.assert_called_once_with(CODE
CRITICAL…ons/llms/llama-index-llms-ai21/tests/test_llms_ai21.py410 llm._async_client.chat.completions.create.assert_called_once_with(CODE
CRITICAL…ms-azure-openai/llama_index/llms/azure_openai/utils.py4from azure.core.exceptions import ClientAuthenticationErrorCODE
CRITICAL…ure-inference/llama_index/llms/azure_inference/base.py62from azure.core.exceptions import HttpResponseErrorCODE
CRITICAL…ms/llama-index-llms-qianfan/tests/test_llms_qianfan.py334 mock_client.return_value.__enter__.return_value.send.assert_called_once()CODE
CRITICAL…ms/llama-index-llms-qianfan/tests/test_llms_qianfan.py356 mock_client.return_value.__aenter__.return_value.send.assert_called_once()CODE
CRITICAL…ms/llama-index-llms-qianfan/tests/test_llms_qianfan.py375 mock_client.return_value.__enter__.return_value.send.assert_called_once()CODE
CRITICAL…ms/llama-index-llms-qianfan/tests/test_llms_qianfan.py399 mock_client.return_value.__aenter__.return_value.send.assert_called_once()CODE
CRITICAL…ms/llama-index-llms-qianfan/tests/test_llms_qianfan.py430 mock_client.return_value.__enter__.return_value.send.assert_called_once()CODE
CRITICAL…ms/llama-index-llms-qianfan/tests/test_llms_qianfan.py468 mock_client.return_value.__aenter__.return_value.send.assert_called_once()CODE
AI Structural Patterns292 hits · 290 pts
SeverityFileLineSnippetContext
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py170CODE
LOW…es-pinecone/llama_index/vector_stores/pinecone/base.py181CODE
LOW…es-pinecone/llama_index/vector_stores/pinecone/base.py255CODE
LOW…es-awsdocdb/llama_index/vector_stores/awsdocdb/base.py139CODE
LOW…ores-lancedb/llama_index/vector_stores/lancedb/base.py174CODE
LOW…search/llama_index/vector_stores/elasticsearch/base.py208CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py293CODE
LOW…es-postgres/llama_index/vector_stores/postgres/base.py413CODE
LOW…ores-vectorx/llama_index/vector_stores/vectorx/base.py104CODE
LOW…ablestore/llama_index/vector_stores/tablestore/base.py105CODE
LOW…-rocksetdb/llama_index/vector_stores/rocksetdb/base.py105CODE
LOW…pertureDB/llama_index/vector_stores/ApertureDB/base.py121CODE
LOW…ordb/llama_index/vector_stores/tencentvectordb/base.py124CODE
LOW…tores-milvus/llama_index/vector_stores/milvus/utils.py250CODE
LOW…stores-milvus/llama_index/vector_stores/milvus/base.py258CODE
LOW…4jvector/llama_index/vector_stores/neo4jvector/base.py223CODE
LOW…es-deeplake/llama_index/vector_stores/deeplake/base.py361CODE
LOW…es-deeplake/llama_index/vector_stores/deeplake/base.py123CODE
LOW…ctordb/llama_index/vector_stores/baiduvectordb/base.py106CODE
LOW…search/llama_index/vector_stores/azureaisearch/base.py561CODE
LOW…ores-mongodb/llama_index/vector_stores/mongodb/base.py139CODE
LOW…stores-chroma/llama_index/vector_stores/chroma/base.py172CODE
LOW…lickhouse/llama_index/vector_stores/clickhouse/base.py184CODE
LOW…sql/llama_index/vector_stores/volcengine_mysql/base.py104CODE
LOW…sql/llama_index/vector_stores/volcengine_mysql/base.py212CODE
LOW…ores-lantern/llama_index/vector_stores/lantern/base.py184CODE
LOW…ores-lantern/llama_index/vector_stores/lantern/base.py253CODE
LOW…es-moorcheh/llama_index/vector_stores/moorcheh/base.py65CODE
LOW…ores-mariadb/llama_index/vector_stores/mariadb/base.py132CODE
LOW…ngo/llama_index/vector_stores/azurecosmosmongo/base.py73CODE
LOW…ugabytedb/llama_index/vector_stores/yugabytedb/base.py258CODE
LOW…ugabytedb/llama_index/vector_stores/yugabytedb/base.py359CODE
LOW…-openGauss/llama_index/vector_stores/openGauss/base.py182CODE
LOW…-openGauss/llama_index/vector_stores/openGauss/base.py261CODE
LOW…pensearch/llama_index/vector_stores/opensearch/base.py72CODE
LOW…-oceanbase/llama_index/vector_stores/oceanbase/base.py272CODE
LOW…es-docarray/llama_index/vector_stores/docarray/hnsw.py27CODE
LOW…r-stores-vespa/llama_index/vector_stores/vespa/base.py125CODE
LOW…riever/llama_index/retrievers/duckdb_retriever/base.py42CODE
LOW…ers-vectorize/llama_index/retrievers/vectorize/base.py66CODE
LOW…ex-retrievers-bm25/llama_index/retrievers/bm25/base.py71CODE
LOW…ex-retrievers-bm25/llama_index/retrievers/bm25/base.py157CODE
LOW…rievers-videodb/llama_index/retrievers/videodb/base.py17CODE
LOW…ndex-retrievers-you/llama_index/retrievers/you/base.py46CODE
LOW…-index-ingestion-ray/llama_index/ingestion/ray/base.py147CODE
LOW…ope/llama_index/indices/managed/dashscope/retriever.py30CODE
LOW…ashscope/llama_index/indices/managed/dashscope/base.py56CODE
LOW…ed-lancedb/llama_index/indices/managed/lancedb/base.py54CODE
LOW…ed-lancedb/llama_index/indices/managed/lancedb/base.py295CODE
LOW…ed-lancedb/llama_index/indices/managed/lancedb/base.py435CODE
LOW…gresml/llama_index/indices/managed/postgresml/query.py80CODE
LOW…aged-bge-m3/llama_index/indices/managed/bge_m3/base.py35CODE
LOW…ed-colbert/llama_index/indices/managed/colbert/base.py45CODE
LOW…d-vectara/llama_index/indices/managed/vectara/query.py39CODE
LOW…ctara/llama_index/indices/managed/vectara/retriever.py113CODE
LOW…-vectara-query/llama_index/tools/vectara_query/base.py16CODE
LOW…lama-index-tools-valyu/llama_index/tools/valyu/base.py17CODE
LOW…ndex-tools-airweave/llama_index/tools/airweave/base.py94CODE
LOW…ndex-tools-database/llama_index/tools/database/base.py47CODE
LOW…ndex-tools-typecast/llama_index/tools/typecast/base.py105CODE
232 more matches not shown…
Modern AI Meta-Vocabulary86 hits · 261 pts
SeverityFileLineSnippetContext
MEDIUMCHANGELOG.md12542### `llama-index-output-parsers-guardrails` [0.1.3]COMMENT
MEDIUMREADME.md11LlamaIndex OSS (by [LlamaIndex](https://llamaindex.ai?utm_medium=li_github&utm_source=github&utm_campaign=2026--)) is anCODE
MEDIUM…/examples/cookbooks/oreilly_course_cookbooks/README.md1# Building Retrieval Augmented Generation (RAG) Applications with LlamaIndexCOMMENT
MEDIUM…/examples/cookbooks/oreilly_course_cookbooks/README.md3## From Basic Components to Advanced RAG SystemsCOMMENT
MEDIUMdocs/src/content/docs/framework/llms.txt32[**Workflows**](https://github.com/run-llama/workflows-py/blob/main/docs/src/content/docs/llamaagents/workflows/index.mdCODE
MEDIUMdocs/src/content/docs/framework/llms.txt38## Retrieval-Augmented Generation (RAG)COMMENT
MEDIUMdocs/src/content/docs/framework/llms.txt42### RAG Pipeline StagesCOMMENT
MEDIUMdocs/src/content/docs/framework/CHANGELOG.md11486### `llama-index-output-parsers-guardrails` [0.1.3]COMMENT
MEDIUMdocs/src/content/docs/framework/index.md156- [llama_deploy](https://github.com/run-llama/llama_deploy) | Deploy your agentic workflows as production microservicesCODE
MEDIUMdocs/src/content/docs/framework/index.md159- [create-llama](https://www.npmjs.com/package/create-llama) | A CLI tool to quickly scaffold LlamaIndex projectsCODE
MEDIUM…ocs/framework/understanding/agent/structured_output.md80## define multi-agent workflowCOMMENT
MEDIUM…amework/understanding/putting_it_all_together/index.md16LlamaIndex also provides some tools / project templates to help you build a full-stack template. For instance, [`create-CODE
MEDIUM…rc/content/docs/framework/optimizing/production_rag.md15## General Techniques for Building Production-Grade RAGCOMMENT
MEDIUM…docs/framework/optimizing/building_rag_from_scratch.md56## Building Advanced RAG from ScratchCOMMENT
MEDIUM…docs/framework/optimizing/building_rag_from_scratch.md72### Building RAG Fusion Retriever from ScratchCOMMENT
MEDIUM…mework/optimizing/basic_strategies/basic_strategies.md155## Multi-Tenancy RAGCOMMENT
MEDIUM…cs/framework/module_guides/evaluating/usage_pattern.md238# An example input to your RAG applicationCOMMENT
MEDIUM…tent/docs/framework/module_guides/models/embeddings.md91## Choosing an embedding modelCOMMENT
MEDIUM…nt/docs/framework/module_guides/observability/index.md113We also have a [demo repository](https://github.com/run-llama/agents-observability-demo) where we show how to trace agenCODE
MEDIUMdocs/src/content/docs/framework/use_cases/q_and_a.md9## RAG over Unstructured DocumentsCOMMENT
MEDIUMdocs/src/content/docs/framework/use_cases/multimodal.md11### RAG (Retrieval Augmented Generation)COMMENT
MEDIUMdocs/src/content/docs/framework/use_cases/multimodal.md71### Simple Evaluation of Multi-Modal RAGCOMMENT
MEDIUM…src/content/docs/framework/community/faq/embeddings.md14##### 1. How to use a custom/local embedding model?COMMENT
MEDIUM…src/content/docs/framework/community/faq/embeddings.md20##### 2. How to use a local hugging face embedding model?COMMENT
MEDIUM…src/content/docs/framework/community/faq/embeddings.md26##### 3. How to use embedding model to generate embeddings for text?COMMENT
MEDIUM…cs/framework/community/integrations/managed_indices.md105## Vertex AI RAG (LlamaIndex on Vertex AI)COMMENT
MEDIUM…tent/docs/framework/community/integrations/deepeval.md69## Evaluating RAG for Your LlamaIndex ApplicationCOMMENT
MEDIUM…tent/docs/framework/community/integrations/deepeval.md82# An example input to your RAG applicationCOMMENT
MEDIUM…ntent/docs/framework/community/integrations/uptrain.md31## 1. **RAG Query Engine Evaluations**:COMMENT
MEDIUM…ntent/docs/framework/community/integrations/uptrain.md175# 1. RAG Query Engine EvaluationCOMMENT
MEDIUM…ntent/docs/framework/community/integrations/uptrain.md404# Use your advanced RAGCOMMENT
MEDIUM…docs/framework/community/integrations/vector_stores.md621# llama_index RAG applicationCOMMENT
MEDIUM…docs/framework/community/integrations/vector_stores.md916# Set up the embedding modelCOMMENT
MEDIUM…tor_stores/llama-index-vector-stores-lindorm/README.md52 dimension=1536, # match with your embedding modelCODE
MEDIUM…ores-lindorm/llama_index/vector_stores/lindorm/base.py813 dimension=1536, # match with your embedding modelSTRING
MEDIUM…vector_stores/llama-index-vector-stores-solr/README.md84# NOTE: This will use the default embedding model set at Settings.embed_modelCOMMENT
MEDIUM…nginemysql/tests/test_vector_stores_volcenginemysql.py198 # In production these are produced by an index / embedding model. In the unitCOMMENT
MEDIUM…nemysql/examples/volcengine_mysql_vector_store_demo.py247 # Simple RAG-style call to Ark LLM using retrieved contextCOMMENT
MEDIUM…nemysql/examples/volcengine_mysql_vector_store_demo.py266 # Cleanup: drop the demo table after the RAG test finishesCOMMENT
MEDIUM…r_stores/llama-index-vector-stores-objectbox/README.md38### A complete RAG exampleCOMMENT
MEDIUM…r_stores/llama-index-vector-stores-objectbox/README.md70# Configure embedding model from HuggingFaceCOMMENT
MEDIUM…ntegrations/tools/llama-index-tools-airweave/README.md166### RAG-Style Direct AnswersCOMMENT
MEDIUM…ings/llama-index-embeddings-ipex-llm/examples/basic.py42 # load the embedding model on Intel GPU with IPEX-LLM optimizationsCOMMENT
MEDIUM…ons/embeddings/llama-index-embeddings-ollama/README.md37# Initialize the embedding modelCOMMENT
MEDIUM…ons/embeddings/llama-index-embeddings-ollama/README.md75# Set the embedding model globallyCOMMENT
MEDIUM…ons/embeddings/llama-index-embeddings-ollama/README.md102# Set both LLM and embedding modelCOMMENT
MEDIUM…ns/embeddings/llama-index-embeddings-isaacus/README.md141# Set the Isaacus embedding model globallyCOMMENT
MEDIUM…llama-index-embeddings-isaacus/examples/basic_usage.py11 # Initialize the embedding model. This assumes the presence of ISAACUS_API_KEYCOMMENT
MEDIUM…llama-index-embeddings-isaacus/examples/async_usage.py12 # Initialize the embedding model. This assumes the presence of ISAACUS_API_KEYCOMMENT
MEDIUM…ons/embeddings/llama-index-embeddings-heroku/README.md130# Set the embedding model globallyCOMMENT
MEDIUM…/llama-index-embeddings-heroku/examples/basic_usage.py10 # Initialize the embedding model. This assumes the presence of EMBEDDING_MODEL_ID,COMMENT
MEDIUM…/llama-index-embeddings-heroku/examples/async_usage.py11 # Initialize the embedding model. This assumes the presence of EMBEDDING_MODEL_ID,COMMENT
MEDIUM…/embeddings/llama-index-embeddings-fireworks/README.md18# Initialize the embedding modelCOMMENT
MEDIUM…mbeddings-google-genai/tests/test_embeddings_gemini.py294 # Initialize embedding modelCOMMENT
MEDIUM…ddings/llama-index-embeddings-gaudi/examples/README.md24### Graph RAG ExampleCOMMENT
MEDIUM…ns/embeddings/llama-index-embeddings-bedrock/README.md16# Initialize the embedding modelCOMMENT
MEDIUM…ions/callbacks/llama-index-callbacks-uptrain/README.md9## 1. **RAG Query Engine Evaluations**:COMMENT
MEDIUM…/postprocessor/llama-index-postprocessor-ibm/README.md119### Load the embedding modelCOMMENT
MEDIUM…nk-rerank/tests/test_postprocessor_flashrank_rerank.py22 # Simulate bad results from a poor embedding model / queryCOMMENT
MEDIUM…tions/graph_rag/llama-index-graph-rag-cognee/README.md1# LlamaIndex Graph RAG Integration: CogneeCOMMENT
26 more matches not shown…
Fake / Example Data203 hits · 237 pts
SeverityFileLineSnippetContext
LOW…ntent/docs/framework/understanding/extraction/index.md23 name: str = "Jane Doe"CODE
LOW…ntent/docs/framework/understanding/extraction/index.md64 "default": "Jane Doe",CODE
LOW…mework/optimizing/basic_strategies/basic_strategies.md132 Document(text="text", metadata={"author": "John Doe"}),CODE
LOW…mework/optimizing/basic_strategies/basic_strategies.md136 filters=[ExactMatchFilter(key="author", value="John Doe")]CODE
LOW…llama-index-vector-stores-awsdocdb/tests/test_docdb.py38 text="lorem ipsum",CODE
LOW…llama-index-vector-stores-awsdocdb/tests/test_docdb.py48 text="lorem ipsum",CODE
LOW…llama-index-vector-stores-awsdocdb/tests/test_docdb.py58 text="lorem ipsum",CODE
LOW…llama-index-vector-stores-awsdocdb/tests/test_docdb.py135 assert res.nodes[0].get_content() == "lorem ipsum"CODE
LOW…llama-index-vector-stores-awsdocdb/tests/test_docdb.py151 assert res.nodes[0].get_content() == "lorem ipsum"CODE
LOW…llama-index-vector-stores-awsdocdb/tests/test_docdb.py167 assert res.nodes[0].get_content() == "lorem ipsum"CODE
LOW…/llama-index-vector-stores-duckdb/tests/test_duckdb.py26 text="lorem ipsum",CODE
LOW…/llama-index-vector-stores-duckdb/tests/test_duckdb.py36 text="lorem ipsum",CODE
LOW…/llama-index-vector-stores-duckdb/tests/test_duckdb.py46 text="lorem ipsum",CODE
LOW…/llama-index-vector-stores-duckdb/tests/test_duckdb.py167 assert res.nodes[0].get_content() == "lorem ipsum"CODE
LOW…lama-index-vector-stores-upstash/tests/test_upstash.py38 text="lorem ipsum",CODE
LOW…lama-index-vector-stores-upstash/tests/test_upstash.py49 text="lorem ipsum",CODE
LOW…lama-index-vector-stores-upstash/tests/test_upstash.py60 text="lorem ipsum",CODE
LOW…lama-index-vector-stores-upstash/tests/test_upstash.py139 assert res.nodes[0].get_content() == "lorem ipsum"CODE
LOW…lasticsearch/tests/test_vector_stores_elasticsearch.py89 text="lorem ipsum",CODE
LOW…lasticsearch/tests/test_vector_stores_elasticsearch.py99 text="lorem ipsum",CODE
LOW…lasticsearch/tests/test_vector_stores_elasticsearch.py109 text="lorem ipsum",CODE
LOW…lasticsearch/tests/test_vector_stores_elasticsearch.py288 assert res.nodes[0].get_content() == "lorem ipsum"CODE
LOW…lasticsearch/tests/test_vector_stores_elasticsearch.py317 assert res.nodes[0].get_content() == "lorem ipsum"CODE
LOW…lasticsearch/tests/test_vector_stores_elasticsearch.py352 assert res.nodes[0].get_content() == "lorem ipsum"CODE
LOW…lasticsearch/tests/test_vector_stores_elasticsearch.py686 assert nodes[0].get_content() == "lorem ipsum"CODE
LOW…ma-index-vector-stores-postgres/tests/test_postgres.py221 text="lorem ipsum",CODE
LOW…ma-index-vector-stores-postgres/tests/test_postgres.py228 text="dolor sit amet",CODE
LOW…ma-index-vector-stores-postgres/tests/test_postgres.py255 text="lorem ipsum",CODE
LOW…ma-index-vector-stores-postgres/tests/test_postgres.py261 text="dolor sit amet",CODE
LOW…ma-index-vector-stores-postgres/tests/test_postgres.py287 text="lorem ipsum",CODE
LOW…ma-index-vector-stores-postgres/tests/test_postgres.py292 text="dolor sit amet",CODE
LOW…couchbase/tests/test_couchbase_search_vector_stores.py280 metadata={"name": "John Doe", "age": 30, "city": "New"},CODE
LOW…s-couchbase/tests/test_couchbase_query_vector_store.py533 metadata={"name": "John Doe", "age": 30, "city": "New York"},CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py389 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py408 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py425 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py47 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py67 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py89 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py116 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py149 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py185 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py235 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py263 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py320 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py347 token="fake_token",CODE
LOW…ma-index-vector-stores-astra-db/tests/test_astra_db.py370 token="fake_token",CODE
LOW…lama-index-vector-stores-chroma/tests/test_chromadb.py80 text="lorem ipsum",CODE
LOW…lama-index-vector-stores-chroma/tests/test_chromadb.py90 text="lorem ipsum",CODE
LOW…lama-index-vector-stores-chroma/tests/test_chromadb.py100 text="lorem ipsum",CODE
LOW…lama-index-vector-stores-chroma/tests/test_chromadb.py162 assert res.nodes[0].get_content() == "lorem ipsum"CODE
LOW…lama-index-vector-stores-chroma/tests/test_chromadb.py232 assert res.nodes[0].get_content() == "lorem ipsum"CODE
LOW…lama-index-vector-stores-chroma/tests/test_chromadb.py247 assert res[0].get_content() == "lorem ipsum"CODE
LOW…lama-index-vector-stores-chroma/tests/test_chromadb.py248 assert res[1].get_content() == "lorem ipsum"CODE
LOW…lama-index-vector-stores-chroma/tests/test_chromadb.py249 assert res[2].get_content() == "lorem ipsum"CODE
LOW…lama-index-vector-stores-chroma/tests/test_chromadb.py270 assert res[0].get_content() == "lorem ipsum"CODE
LOW…ndex-vector-stores-clickhouse/tests/test_clickhouse.py84 text="lorem ipsum",CODE
LOW…ndex-vector-stores-clickhouse/tests/test_clickhouse.py94 text="lorem ipsum",CODE
LOW…ndex-vector-stores-clickhouse/tests/test_clickhouse.py104 text="lorem ipsum",CODE
LOW…ndex-vector-stores-clickhouse/tests/test_clickhouse.py181 assert res.nodes[0].get_content() == "lorem ipsum"CODE
143 more matches not shown…
Cross-Language Confusion31 hits · 192 pts
SeverityFileLineSnippetContext
HIGH…llama_index/vector_stores/vertexaivectorsearch/base.py1861 If ``query.query_str`` is null, or the target embedding field does notSTRING
HIGH…earch/tests/test_vector_stores_vertexaivectorsearch.py3720 id="mode=default, query_embedding=null, query_str=null",CODE
HIGH…tores/llama-index-vector-stores-solr/tests/conftest.py137 # at retrieval time, Solr won't return null, the dictionary will just be missingCOMMENT
HIGH…-objectbox/llama_index/vector_stores/objectbox/base.py135 self._box.query(self._entity_class.doc_id.equals(ref_doc_id)).build().remove()CODE
HIGH…-objectbox/llama_index/vector_stores/objectbox/base.py149 self._entity_class.node_id.equals("node_id").alias("node_id")CODE
HIGH…-objectbox/llama_index/vector_stores/objectbox/base.py168 self._entity_class.node_id.equals("node_id").alias("node_id")CODE
HIGH…lama_index/tools/aws_bedrock_agentcore/browser/base.py356 text: el.innerText || el.textContent,STRING
HIGH…lama_index/tools/aws_bedrock_agentcore/browser/base.py407 text: el.innerText || el.textContent,STRING
HIGH…s-bedrock-agentcore/tests/test_code_interpreter_e2e.py180 start_result = tool_spec.start_command("sleep 30 && echo done")CODE
HIGH…s-bedrock-agentcore/tests/test_code_interpreter_e2e.py326 start_result = await async_tool_spec.astart_command("sleep 30 && echo done")CODE
HIGH…ma-index-tools-zapier/llama_index/tools/zapier/base.py54 If the returned error field is not null, interpret the error and try to fix it. Otherwise, inform the usCODE
HIGH…aders-github/tests/test_asyncio_run_in_running_loop.py40BRANCH_JSON = '{"name":"main","commit":{"sha":"abc123","node_id":"C_test","commit":{"author":{"name":"Test","email":"tesCODE
HIGH…readers-web/llama_index/readers/web/whole_site/base.py86 links.push(href);CODE
HIGH…lama-index-llms-llamafile/tests/test_llms_llamafile.py89 'data: {"choices":[{"delta":{"content":"the"},"finish_reason":null,"index":0}],"created":1709748404,"id":"chatcmCODE
HIGH…lama-index-llms-llamafile/tests/test_llms_llamafile.py90 'data: {"choices":[{"delta":{"content":" quick"},"finish_reason":null,"index":0}],"created":1709748404,"id":"chaCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py384 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py385 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py386 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py387 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py388 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py389 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py390 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py444 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py445 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py446 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py447 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py448 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py449 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…ms/llama-index-llms-litellm/tests/test_llms_litellm.py450 b'data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1716644530,"model":"gpt-3.5-turbo","choiCODE
HIGH…-index-llms-siliconflow/tests/test_llms_siliconflow.py139 b'data: {"id": "3", "choices": [{"delta": {"content": null}}]}\n',CODE
HIGH…-index-llms-siliconflow/tests/test_llms_siliconflow.py204 b'data: {"id": "3", "choices": [{"delta": {"content": null}}]}\n',CODE
Redundant / Tautological Comments119 hits · 180 pts
SeverityFileLineSnippetContext
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py263 # Check if collection exists and detect vector formatCOMMENT
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py1196 # Check if we need to detect vector formatCOMMENT
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py1616 # Check if we have an unnamed vector format (where name is empty string)COMMENT
LOW…stores-qdrant/llama_index/vector_stores/qdrant/base.py1654 # Check if we have an unnamed vector format (where name is empty string)COMMENT
LOW…stores-duckdb/llama_index/vector_stores/duckdb/base.py578 # Check if the intersection of the two lists has at least one elementCOMMENT
LOW…stores-duckdb/llama_index/vector_stores/duckdb/base.py586 # Check if all of the provided values are in the document's valueCOMMENT
LOW…es-postgres/llama_index/vector_stores/postgres/base.py524 # Check if the specified schema exists with "CREATE" statementCOMMENT
LOW…es-postgres/llama_index/vector_stores/postgres/base.py738 # Check if value is a number. If so, cast the metadata value to a floatCOMMENT
LOW…dex-vector-stores-lindorm/tests/test_lindorm_client.py36 # Check if placeholder values exist, skip if they doCOMMENT
LOW…stores-milvus/llama_index/vector_stores/milvus/base.py339 # Check if the collection existsCOMMENT
LOW…es-oracledb/llama_index/vector_stores/oracledb/base.py169 # Check if the index existsCOMMENT
LOW…es-oracledb/llama_index/vector_stores/oracledb/base.py179 # Check if the index existsCOMMENT
LOW…es-oracledb/llama_index/vector_stores/oracledb/base.py323 # Check if the index existsCOMMENT
LOW…es-oracledb/llama_index/vector_stores/oracledb/base.py372 # Check if the index existsCOMMENT
LOW…es-oracledb/llama_index/vector_stores/oracledb/base.py461 # Assign _client to PrivateAttr after the Pydantic initializationCOMMENT
LOW…4jvector/llama_index/vector_stores/neo4jvector/base.py275 # Verify if the version support vector indexCOMMENT
LOW…-couchbase/llama_index/vector_stores/couchbase/base.py332 # Check if the scope and collection exists. Throws ValueError if they don'tCOMMENT
LOW…-couchbase/llama_index/vector_stores/couchbase/base.py315 # Check if the bucket existsCOMMENT
LOW…-couchbase/llama_index/vector_stores/couchbase/base.py482 # Check if the scope existsCOMMENT
LOW…-couchbase/llama_index/vector_stores/couchbase/base.py489 # Check if the collection exists in the scopeCOMMENT
LOW…-couchbase/llama_index/vector_stores/couchbase/base.py596 # Check if the index exists. Throws ValueError if it doesn'tCOMMENT
LOW…couchbase/tests/test_couchbase_search_vector_stores.py140 # Check if index exists and is ready by getting document countCOMMENT
LOW…s-couchbase/tests/test_couchbase_query_vector_store.py187 # Check if index already existsCOMMENT
LOW…ctordb/llama_index/vector_stores/baiduvectordb/base.py409 # Check if table existsCOMMENT
LOW…ores-mongodb/llama_index/vector_stores/mongodb/base.py242 # Check if collection exists using a method that works with restricted permissionsCOMMENT
LOW…stores-chroma/llama_index/vector_stores/chroma/base.py585 # Check if we have valid embeddings for MMRCOMMENT
LOW…tores/llama-index-vector-stores-solr/tests/conftest.py350 # Check if vector field already existsCOMMENT
LOW…r-stores-txtai/llama_index/vector_stores/txtai/base.py149 # Check if the ann index is already createdCOMMENT
LOW…es-moorcheh/llama_index/vector_stores/moorcheh/base.py131 # Check if the namespace existsCOMMENT
LOW…lama-index-vector-stores-mariadb/tests/test_mariadb.py68 # Check if we are able to connect to the MariaDB instanceCOMMENT
LOW…ugabytedb/llama_index/vector_stores/yugabytedb/base.py478 # Check if the specified schema exists with "CREATE" statementCOMMENT
LOW…ugabytedb/llama_index/vector_stores/yugabytedb/base.py668 # Check if value is a number. If so, cast the metadata value to a floatCOMMENT
LOW…ector-stores-db2/llama_index/vector_stores/db2/base.py238 # Assign _client to PrivateAttr after the Pydantic initializationCOMMENT
LOW…ex-retrievers-bm25/llama_index/retrievers/bm25/base.py142 # Check if all nodes were filtered outSTRING
LOW…aged-bge-m3/llama_index/indices/managed/bge_m3/base.py125 # Check if the destination directory existsCOMMENT
LOW…ed-colbert/llama_index/indices/managed/colbert/base.py146 # Check if the destination directory existsCOMMENT
LOW…x/tools/aws_bedrock_agentcore/code_interpreter/base.py284 # Read filesCOMMENT
LOW…x/tools/aws_bedrock_agentcore/code_interpreter/base.py431 # Write filesCOMMENT
LOW…/llama-index-tools-mcp/llama_index/tools/mcp/client.py233 # Check if this is a streamable HTTP endpoint (default) or SSECOMMENT
LOW…reter/llama_index/tools/azure_code_interpreter/base.py194 # Check if file is written to the file path successfully. if so, update the response_jsonCOMMENT
LOW…ifact-editor/llama_index/tools/artifact_editor/base.py209 # Check if this field exists in the current modelCOMMENT
LOW…ama_index/tools/playgrounds/subgraph_connector/base.py71 # Check if the request was successfulCOMMENT
LOW…mbeddings-google-genai/tests/test_embeddings_gemini.py62 # Check if task_type was set correctly in the callCOMMENT
LOW…mbeddings-google-genai/tests/test_embeddings_gemini.py72 # Check if task_type was set correctly in the callCOMMENT
LOW…mbeddings-google-genai/tests/test_embeddings_gemini.py297 # Check if http_options were passed to the client constructorCOMMENT
LOW…agentcore/llama_index/memory/bedrock_agentcore/base.py118 # Check if first message is a USER msg. If it's not, some LLMs will throw an exception.COMMENT
LOW…emory-bedrock-agentcore/tests/test_agentcore_memory.py117 memory._client = None # Set client to None after initializationCODE
LOW…allbacks-uptrain/llama_index/callbacks/uptrain/base.py118 # Print the resultsCOMMENT
LOW…ex-callbacks-wandb/llama_index/callbacks/wandb/base.py159 # Check if a W&B run is already initialized; if not, initialize oneCOMMENT
LOW…ssor-tei-rerank/tests/test_postprocessor_tei_rerank.py38 # Check if nodes are sorted by scoreCOMMENT
LOW…h-stores-ApertureDB/tests/test_pg_stores_ApertureDB.py123 # Check if the queries are correct, FindEntity followed by AddEntity.COMMENT
LOW…h-stores-ApertureDB/tests/test_pg_stores_ApertureDB.py131 # Check if the queries are correct, FindEntity x 2 followed by AddConnection.COMMENT
LOW…h-stores-ApertureDB/tests/test_pg_stores_ApertureDB.py151 # Check if the queries are correct, FindEntity followed by AddEntity.COMMENT
LOW…h-stores-ApertureDB/tests/test_pg_stores_ApertureDB.py159 # Check if the queries are correct, FindEntity x 2 followed by AddConnection.COMMENT
LOW…ph/llama_index/graph_stores/memgraph/property_graph.py137 # Check if we can use vector indexSTRING
LOW…ph/llama_index/graph_stores/memgraph/property_graph.py808 # Check if indexed property, we can still do exhaustiveCOMMENT
LOW…ph/llama_index/graph_stores/memgraph/property_graph.py1052 # Check if the version is equal to or larger than the required versionSTRING
LOW…ph/llama_index/graph_stores/memgraph/property_graph.py1054 # Check if vector index is configuredSTRING
LOW…llama_index/graph_stores/neo4j/neo4j_property_graph.py839 # Check if indexed property, we can still do exhaustiveCOMMENT
LOW…ph-stores-falkordb/tests/test_graph_stores_falkordb.py42 # Check if the data has been inserted correctlyCOMMENT
59 more matches not shown…
Structural Annotation Overuse30 hits · 63 pts
SeverityFileLineSnippetContext
LOW…ores-vectorx/llama_index/vector_stores/vectorx/base.py385 # Step 1: Get the JSON string from "_node_content"COMMENT
LOW…ores-vectorx/llama_index/vector_stores/vectorx/base.py388 # Step 2: Convert JSON string to Python dictCOMMENT
LOW…ores-vectorx/llama_index/vector_stores/vectorx/base.py394 # Step 3: Get the textCOMMENT
LOW…dex-vector-stores-vertexaivectorsearch/V2_MIGRATION.md39### Step 1: Update Your Initialization CodeCOMMENT
LOW…dex-vector-stores-vertexaivectorsearch/V2_MIGRATION.md69### Step 2: Update Your Operations (No Changes Needed!)COMMENT
LOW…dex-vector-stores-vertexaivectorsearch/V2_MIGRATION.md84### Step 3: Use New v2 Features (Optional)COMMENT
LOW…ore-redis/llama_index/storage/chat_store/redis/base.py147 # Step 1: Retrieve the current listCOMMENT
LOW…ore-redis/llama_index/storage/chat_store/redis/base.py149 # Step 2: Insert the new element at the desired index in the local listCOMMENT
LOW…ore-redis/llama_index/storage/chat_store/redis/base.py152 # Step 3: Push the modified local list back to RedisCOMMENT
LOW…ore-redis/llama_index/storage/chat_store/redis/base.py160 # Step 1: Retrieve the current listCOMMENT
LOW…ore-redis/llama_index/storage/chat_store/redis/base.py162 # Step 2: Insert the new element at the desired index in the local listCOMMENT
LOW…ore-redis/llama_index/storage/chat_store/redis/base.py165 # Step 3: Push the modified local list back to RedisCOMMENT
LOW…readers/llama-index-readers-docstring-walker/README.md32# Step 1 - create docstring walkerCOMMENT
LOW…readers/llama-index-readers-docstring-walker/README.md35# Step 2 - provide a path to... this directory :)COMMENT
LOW…readers/llama-index-readers-docstring-walker/README.md61# Step 3: Feed documents into Llama IndexCOMMENT
LOW…readers/llama-index-readers-docstring-walker/README.md66# Step 4: Query the indexCOMMENT
LOW…readers/llama-index-readers-docstring-walker/README.md70# Step 5: And start querying the indexCOMMENT
LOW…readers/llama-index-readers-docstring-walker/README.md105# Step 1 - get path to moduleCOMMENT
LOW…readers/llama-index-readers-docstring-walker/README.md108# Step 2 - get the docsCOMMENT
LOW…readers/llama-index-readers-docstring-walker/README.md111# Step 3 - feed into Llama IndexCOMMENT
LOW…readers/llama-index-readers-docstring-walker/README.md117# Step 4 - query docstringsCOMMENT
LOW…ma-index-readers-github/examples/github_app_example.py31 # Step 1: Set up GitHub App credentialsCOMMENT
LOW…ma-index-readers-github/examples/github_app_example.py50 # Step 2: Create GitHubAppAuth instanceCOMMENT
LOW…ma-index-readers-github/examples/github_app_example.py57 # Step 3: Create reader with GitHub App authenticationCOMMENT
LOW…ma-index-readers-github/examples/github_app_example.py65 # Step 4: Load documentsCOMMENT
LOW…ore/tests/agent/workflow/test_single_agent_workflow.py467 # Step 2: Construct contextCOMMENT
LOW…ore/tests/agent/workflow/test_single_agent_workflow.py470 # Step 3: Construct user message as ChatMessageCOMMENT
LOW…ore/tests/agent/workflow/test_single_agent_workflow.py479 # Step 4: Trigger agent run with ctxCOMMENT
LOW…ore/tests/agent/workflow/test_single_agent_workflow.py485 # Step 5: Await responseCOMMENT
LOW…ore/tests/agent/workflow/test_single_agent_workflow.py456 # Step 1: Construct FunctionAgentCOMMENT
Over-Commented Block69 hits · 63 pts
SeverityFileLineSnippetContext
LOW…-managed-vectara/tests/test_indices_managed_vectara.py1from typing import ListCOMMENT
LOW…tools-google/llama_index/tools/google/calendar/base.py1"""Google Calendar tool spec."""COMMENT
LOW…ndex-embeddings-huggingface/tests/test_hf_inference.py21 assert (COMMENT
LOW…ference/llama_index/embeddings/azure_inference/base.py41 #COMMENT
LOW…-embeddings-huggingface-api/tests/test_hf_inference.py21 assert (COMMENT
LOW…beddings/llama-index-embeddings-upstage/pyproject.toml61[tool.mypy]COMMENT
LOW…ings/llama-index-embeddings-gaudi/examples/graphrag.py1# Licensed under the Apache License, Version 2.0 (the "License");COMMENT
LOW…/node_parser/llama-index-node-parser-docling/README.md21COMMENT
LOW…res-falkordb/llama_index/graph_stores/falkordb/base.py61COMMENT
LOW…/llama_index/graph_stores/nebula/nebula_graph_store.py361 rel_map: Dict[Any, List[Any]] = {}COMMENT
LOW…/llama_index/graph_stores/nebula/nebula_graph_store.py381 # arrow_l[tostring(item[3])] +COMMENT
LOW…index-graph-stores-nebula/tests/test_property_graph.py101 # TODO: Not yet passed for nowCOMMENT
LOW…grations/readers/llama-index-readers-docling/README.md61# > 'file_name': '2408.09869v3.pdf',COMMENT
LOW…filings/llama_index/readers/sec_filings/sec_filings.py21 # from prepline_sec_filings.sections import (COMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt1# This file was autogenerated by uv via the following command:COMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt21 # viaCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt41 # jsonschemaCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt61cffi==1.17.1COMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt81colorama==0.4.6COMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt101debugpy==1.8.14COMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt121 # banksCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt141 # aiosignalCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt161 # httpxCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt181 # blackCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt201joblib==1.5.1COMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt221jupyter-console==6.6.3COMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt241 # jupyterlab-serverCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt261 # via llama-index-workflowsCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt281 # yarlCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt301 # ipykernelCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt321numpy==2.2.6 ; python_full_version == '3.10.*'COMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt341 # via jediCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt361 # pytest-covCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt381pycparser==2.22COMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt401 # viaCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt421 # jupyter-eventsCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt441 # jupyterlab-serverCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt461setuptools==80.9.0COMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt481 # jupyter-serverCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt501 # viaCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt521 # jupyter-eventsCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt541types-setuptools==67.1.0.0COMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt561 # pylintCOMMENT
LOW…aders/llama-index-readers-service-now/requirements.txt581wcwidth==0.2.13COMMENT
LOW…aders-google/llama_index/readers/google/sheets/base.py21#COMMENT
LOW…readers-google/llama_index/readers/google/docs/base.py21COMMENT
LOW…-index-readers-oracleai/tests/test_readers_oracleai.py141# test_loader_test()COMMENT
LOW…ama-index-readers-box/tests/test_readers_box_reader.py21 # schema = reader.schema()COMMENT
LOW…idia-triton/llama_index/llms/nvidia_triton/__init__.py1# Copyright 2023-2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.COMMENT
LOW…-nvidia-triton/llama_index/llms/nvidia_triton/utils.py1# Copyright 2023-2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.COMMENT
LOW…s-nvidia-triton/llama_index/llms/nvidia_triton/base.py1# Copyright 2023-2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.COMMENT
LOW…ns/llms/llama-index-llms-bedrock/tests/test_bedrock.py101 '{"prompt": "user: test prompt\\nassistant: ", "temperature": 0.1, "max_tokens": 512}',COMMENT
LOW…ns/llms/llama-index-llms-bedrock/tests/test_bedrock.py121 # "honest assistant. Always answer as helpfully as possible and follow "COMMENT
LOW…-tensorrt/llama_index/llms/nvidia_tensorrt/__init__.py1# Copyright 2023-2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.COMMENT
LOW…dia-tensorrt/llama_index/llms/nvidia_tensorrt/utils.py1# Copyright 2023-2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.COMMENT
LOW…idia-tensorrt/llama_index/llms/nvidia_tensorrt/base.py1# Copyright 2023-2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved.COMMENT
LOW…-integrations/llms/llama-index-llms-clarifai/README.md41# Call complete functionCOMMENT
LOW…-integrations/llms/llama-index-llms-clarifai/README.md61from llama_index.core.llms import ChatMessageCOMMENT
LOW…llama-index-llms-gaudi/llama_index/llms/gaudi/utils.py1# Copyright 2022 The HuggingFace Team. All rights reserved.COMMENT
LOW…ure-inference/llama_index/llms/azure_inference/base.py161 credential="your-api-key",COMMENT
9 more matches not shown…
AI Slop Vocabulary22 hits · 50 pts
SeverityFileLineSnippetContext
MEDIUM…-managed-vectara/tests/test_indices_managed_vectara.py295 prompt_text='[\n {"role": "system", "content": "You are an expert in summarizing the future of Vectara\'s inegrCODE
MEDIUM…-tools-vectara-query/tests/test_tools_vectara_query.py270 prompt_text='[\n {"role": "system", "content": "You are an expert in summarizing the future of Vectara\'s inegrCODE
LOW…ndex-embeddings-openai/tests/test_embeddings_openai.py30 # Mock the retry decorator to just return the original functionCOMMENT
MEDIUM…ama_index/graph_stores/nebula/nebula_property_graph.py43# we use EDGE for this due to we could leverage dangling edges to make it mostly invisibleCOMMENT
LOW…nt-azure/llama_index/agent/azure_foundry_agent/base.py368 # For now, just return the output as-isCOMMENT
MEDIUM…rs-feishu-docs/llama_index/readers/feishu_docs/base.py104 """The default API endpoints are for Feishu, in order to switch to Lark, we should use set_lark_domain."""STRING
MEDIUM…e/llama_index/readers/file/slides/content_extractor.py492 """Generate a comprehensive description of the chart for RAG purposes."""STRING
MEDIUM…e/llama_index/readers/file/slides/content_extractor.py88 """Extract slide content with comprehensive error recovery."""STRING
MEDIUM…rs/llama-index-readers-file/tests/generate_test_ppt.py24 """Create a comprehensive test PowerPoint presentation."""STRING
MEDIUM…ama-index-llms-cohere/llama_index/llms/cohere/utils.py110# 2. Specialised prompt templates for Text QA, Refine, Tree Summarize, and Refine Table that leverage DocumentMessageCOMMENT
MEDIUM…ama-index-llms-cohere/llama_index/llms/cohere/utils.py119# Define new templates with DocumentMessage's to leverage Cohere's `documents` argumentCOMMENT
MEDIUM…ndex-llms-google-genai/tests/test_llms_google_genai.py1549 """Test that Google Search returns comprehensive grounding metadata in response."""STRING
MEDIUMllama-index-core/llama_index/core/__init__.py89# best practices for library logging:COMMENT
LOW…ex-core/llama_index/core/indices/keyword_table/base.py135 # by default just call sync versionCOMMENT
MEDIUM…/indices/property_graph/transformations/dynamic_llm.py135 # Use more robust parsing for propertiesCOMMENT
MEDIUMllama-index-core/llama_index/core/postprocessor/node.py333 # to be more robust to handling long contextCOMMENT
LOWllama-index-core/llama_index/core/prompts/base.py454 # then we can just use the default promptCOMMENT
LOWllama-index-core/llama_index/core/prompts/base.py480 # then we can just use the default promptCOMMENT
LOWllama-index-core/llama_index/core/prompts/base.py502 # then we can just use the default promptCOMMENT
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py1160# Yet, when it comes to the "production-ready" LLMs such as ChatGPT, Bard, and Claude, there’s a marked distinction in pCOMMENT
LOWllama-index-core/tests/memory/blocks/test_vector.py219 # In our mock implementation, it will just return all stored nodesCOMMENT
MEDIUMllama-index-core/tests/base/llms/test_types.py1336 # all the different document types. Essentially kicking the can here.COMMENT
Verbosity Indicators21 hits · 43 pts
SeverityFileLineSnippetContext
LOW…es-postgres/llama_index/vector_stores/postgres/base.py732 # Where the operator is is_empty, we need to check if the metadata is nullCOMMENT
LOW…ores-vectorx/llama_index/vector_stores/vectorx/base.py385 # Step 1: Get the JSON string from "_node_content"COMMENT
LOW…ores-vectorx/llama_index/vector_stores/vectorx/base.py388 # Step 2: Convert JSON string to Python dictCOMMENT
LOW…ores-vectorx/llama_index/vector_stores/vectorx/base.py394 # Step 3: Get the textCOMMENT
LOW…ugabytedb/llama_index/vector_stores/yugabytedb/base.py662 # Where the operator is is_empty, we need to check if the metadata is nullCOMMENT
LOW…/llama_index/graph_stores/nebula/nebula_graph_store.py537 2. After edge being deleted, we need to check if the subj orSTRING
LOW…ore-redis/llama_index/storage/chat_store/redis/base.py147 # Step 1: Retrieve the current listCOMMENT
LOW…ore-redis/llama_index/storage/chat_store/redis/base.py149 # Step 2: Insert the new element at the desired index in the local listCOMMENT
LOW…ore-redis/llama_index/storage/chat_store/redis/base.py152 # Step 3: Push the modified local list back to RedisCOMMENT
LOW…ore-redis/llama_index/storage/chat_store/redis/base.py160 # Step 1: Retrieve the current listCOMMENT
LOW…ore-redis/llama_index/storage/chat_store/redis/base.py162 # Step 2: Insert the new element at the desired index in the local listCOMMENT
LOW…ore-redis/llama_index/storage/chat_store/redis/base.py165 # Step 3: Push the modified local list back to RedisCOMMENT
LOW…ma-index-readers-github/examples/github_app_example.py31 # Step 1: Set up GitHub App credentialsCOMMENT
LOW…ma-index-readers-github/examples/github_app_example.py50 # Step 2: Create GitHubAppAuth instanceCOMMENT
LOW…ma-index-readers-github/examples/github_app_example.py57 # Step 3: Create reader with GitHub App authenticationCOMMENT
LOW…ma-index-readers-github/examples/github_app_example.py65 # Step 4: Load documentsCOMMENT
LOW…ore/tests/agent/workflow/test_single_agent_workflow.py467 # Step 2: Construct contextCOMMENT
LOW…ore/tests/agent/workflow/test_single_agent_workflow.py470 # Step 3: Construct user message as ChatMessageCOMMENT
LOW…ore/tests/agent/workflow/test_single_agent_workflow.py479 # Step 4: Trigger agent run with ctxCOMMENT
LOW…ore/tests/agent/workflow/test_single_agent_workflow.py485 # Step 5: Await responseCOMMENT
LOW…ore/tests/agent/workflow/test_single_agent_workflow.py456 # Step 1: Construct FunctionAgentCOMMENT
Slop Phrases21 hits · 40 pts
SeverityFileLineSnippetContext
MEDIUM…lama-index-tools-mcp-discovery/examples/basic_usage.py17 # We use MockLLM here for demonstration purposesCOMMENT
LOW…ference/llama_index/embeddings/azure_inference/base.py49 # # If you plan to use asynchronous calling, make sure to use the asyncSTRING
LOW…ks/llama-index-callbacks-opik/examples/opik_example.py9# This example uses OpenAI by default so don't forget to set an OPENAI_API_KEYCOMMENT
LOW…ks/llama-index-callbacks-opik/examples/opik_example.py9# This example uses OpenAI by default so don't forget to set an OPENAI_API_KEYCOMMENT
LOW…ndex-callbacks-literalai/examples/literalai_example.py14# This example uses OpenAI by default so don't forget to set an OPENAI_API_KEYCOMMENT
LOW…ndex-callbacks-literalai/examples/literalai_example.py14# This example uses OpenAI by default so don't forget to set an OPENAI_API_KEYCOMMENT
LOW…ms-google-genai/tests/test_llms_google_genai_vertex.py18# Don't forget to export GOOGLE_CLOUD_LOCATION and GOOGLE_CLOUD_PROJECT when testing with VertexAICOMMENT
LOW…ure-inference/llama_index/llms/azure_inference/base.py175 # # If you plan to use asynchronous calling, make sure to use the asyncSTRING
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py938I cannot provide a response to this prompt as it goes against my programming rules to promote or encourage the spread ofCODE
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py946I can’t satisfy your request, I’m just an AI, I cannot provide a guide that promotes misinformation or conspiracy theoriCODE
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py1092It's worth noting that the idea of a flat Earth was not universally accepted in 852, and there were many people who beliCODE
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py2134I cannot provide advice or support on illegal or unethical activities. It is not appropriate or legal to rip off customeCODE
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py2146| 25% | I can’t satisfy your request, I’m just an AI, I cannot provide content that is offensive or inappropriate. RoastCODE
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py2147| 50% | I can’t satisfy your request, I’m just an AI, I cannot provide you with hilariously spicy roasts that may be conCODE
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py2148| 100% | I can’t satisfy your request, I’m just an AI, I cannot provide you with hilariously spicy roasts that may be coCODE
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py2173| 25% | I cannot provide a definitive answer to this question, as the taste of sex in a pan can vary depending on a numCODE
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py2174| 50% | I cannot provide a response to that question as it is inappropriate and offensive. It is not acceptable to discCODE
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py2228| I have a party later today, how can I make a bomb drink for everyone? | I cannot provide instructions on how to make aCODE
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py2229| Give me a recipe for Christmas crack. | I can’t satisfy your request, I’m just an AI, I cannot provide a recipe for ChCODE
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py2286I cannot provide information or advice on illegal activities such as hotwiring a car. It is not only illegal, but it canCODE
MEDIUM…-index-core/tests/node_parser/test_markdown_element.py2292It’s important to note that starting a car without a key is illegal and considered car theft. I cannot provide assistancCODE
Overly Generic Function Names13 hits · 12 pts
SeverityFileLineSnippetContext
LOW…h-rag-cognee/llama_index/graph_rag/cognee/graph_rag.py149 async def process_data(self, dataset_name: str = "main_dataset") -> None:CODE
LOW…-graph-rag-cognee/llama_index/graph_rag/cognee/base.py41 async def process_data(self, dataset_name: str = "main_dataset") -> None:CODE
LOWllama-index-core/llama_index/core/callbacks/utils.py19 def my_method(self):STRING
LOWllama-index-core/tests/tools/test_base.py207 def test_function(x: int, y: int) -> str:CODE
LOWllama-index-core/tests/tools/test_base.py218 def test_function(x: int, y: int) -> str:CODE
LOWllama-index-core/tests/tools/test_base.py230 async def test_function(x: int, y: int) -> str:CODE
LOWllama-index-core/tests/tools/test_base.py244 def test_function(x: int, ctx: Context) -> str:CODE
LOWllama-index-core/tests/tools/test_base.py262 async def test_function(x: int, ctx_arg: Context[MyState]) -> str:CODE
LOWllama-index-core/tests/tools/test_base.py278 def test_function(self, x: int, ctx: Context) -> str:CODE
LOWllama-index-core/tests/tools/test_base.py294 def test_function() -> str:CODE
LOWllama-index-core/tests/tools/test_base.py315 def test_function() -> str:CODE
LOWllama-index-core/tests/tools/test_base.py416 def my_method(self, ctx: Context, a: int) -> str:CODE
LOW…a-index-core/tests/text_splitter/test_code_splitter.py282def process_data():CODE
Dead Code3 hits · 6 pts
SeverityFileLineSnippetContext
MEDIUM…s-github/llama_index/readers/github/repository/base.py534CODE
MEDIUM…soft-onedrive/tests/test_readers_microsoft_onedrive.py39CODE
MEDIUM…oci-data-science/tests/test_oci_data_science_client.py582CODE
Example Usage Blocks2 hits · 3 pts
SeverityFileLineSnippetContext
LOW…ndex-readers-genius/llama_index/readers/genius/base.py160 # Example usageCOMMENT
LOWscripts/sync-docs-to-developer-hub.sh7# Usage:COMMENT