llmware-ai/llmware

19.6

Adjusted Score

19.6

Raw Score

100%

Time Factor

2026-05-17

Last Push

14.8K

Stars

Python

Language

82.8K

Lines of Code

322

Files

995

Pattern Hits

2026-07-14

Scan Date

0.23

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 0HIGH 74MEDIUM 159LOW 762

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 995 distinct pattern matches across 18 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.

Cross-File Repetition73 hits · 365 pts

Severity	File	Line	Snippet	Context
HIGH	README.md	0	this 'hello world' example demonstrates how to get started using local bling models with provided context, using both py	STRING
HIGH	docs/components/rag_optimized_models.md	0	this 'hello world' example demonstrates how to get started using local bling models with provided context, using both py	STRING
HIGH	docs/getting_started/overview.md	0	this 'hello world' example demonstrates how to get started using local bling models with provided context, using both py	STRING
HIGH	tests/embeddings/test_install_embeddings.py	0	note: this setup_library method is provided to enable a self-contained example to create a test library	STRING
HIGH	solutions/embeddings/using_milvus_lite.py	0	note: this setup_library method is provided to enable a self-contained example to create a test library	STRING
HIGH	solutions/rag/example-2-build_embeddings.py	0	note: this setup_library method is provided to enable a self-contained example to create a test library	STRING
HIGH	docs/examples/embedding.md	0	note: this setup_library method is provided to enable a self-contained example to create a test library	STRING
HIGH	tests/models/test_whisper_cpp_model_load.py	0	execute a basic inference on voice-to-text model passing a file_path string	STRING
HIGH	solutions/gguf/using-whisper-cpp-sample-files.py	0	execute a basic inference on voice-to-text model passing a file_path string	STRING
HIGH	…slim_agents/agents-7-using-whisper-cpp-sample-files.py	0	execute a basic inference on voice-to-text model passing a file_path string	STRING
HIGH	docs/components/whisper_cpp.md	0	execute a basic inference on voice-to-text model passing a file_path string	STRING
HIGH	solutions/ui/integrating_pywebio_ui.py	0	simple inference loop that loads a model and runs through a series of test questions.	STRING
HIGH	solutions/gguf/bling_fast_start.py	0	simple inference loop that loads a model and runs through a series of test questions.	STRING
HIGH	solutions/models/bling_fast_start.py	0	simple inference loop that loads a model and runs through a series of test questions.	STRING
HIGH	…_agents/agents-2-llmware_model_sampler_bling_dragon.py	0	simple inference loop that loads a model and runs through a series of test questions.	STRING
HIGH	docs/examples/models.md	0	simple inference loop that loads a model and runs through a series of test questions.	STRING
HIGH	solutions/embeddings/using_milvus_lite.py	0	this method is the core example of installing an embedding on a library. -- two inputs - (1) a pre-created library objec	STRING
HIGH	solutions/rag/example-2-build_embeddings.py	0	this method is the core example of installing an embedding on a library. -- two inputs - (1) a pre-created library objec	STRING
HIGH	docs/examples/embedding.md	0	this method is the core example of installing an embedding on a library. -- two inputs - (1) a pre-created library objec	STRING
HIGH	…t_start_marimo_examples/llmware_fast_start_example2.py	0	this method is the core example of installing an embedding on a library. -- two inputs - (1) a pre-created library objec	STRING
HIGH	…lutions/embeddings/using_semantic_reranker_with_rag.py	0	executes a rag process in memory using semantic reranker model and bling-phi-3-gguf to answer the question.	STRING
HIGH	solutions/onnxruntime/using_onnx_reranker_models.py	0	executes a rag process in memory using semantic reranker model and bling-phi-3-gguf to answer the question.	STRING
HIGH	solutions/openvino/using_openvino_reranker_model.py	0	executes a rag process in memory using semantic reranker model and bling-phi-3-gguf to answer the question.	STRING
HIGH	…m_agents/agents-10-using_semantic_reranker_with_rag.py	0	executes a rag process in memory using semantic reranker model and bling-phi-3-gguf to answer the question.	STRING
HIGH	solutions/onnxruntime/using_local_foundry_models.py	0	this example shows how to use windows local foundry models. pre-reqs: 1. install local foundry, e.g., `winget install mi	STRING
HIGH	solutions/gguf/using_local_foundry_models.py	0	this example shows how to use windows local foundry models. pre-reqs: 1. install local foundry, e.g., `winget install mi	STRING
HIGH	solutions/openvino/using_local_foundry_models.py	0	this example shows how to use windows local foundry models. pre-reqs: 1. install local foundry, e.g., `winget install mi	STRING
HIGH	solutions/models/using_local_foundry_models.py	0	this example shows how to use windows local foundry models. pre-reqs: 1. install local foundry, e.g., `winget install mi	STRING
HIGH	solutions/gguf/using-whisper-cpp-sample-files.py	0	this example shows how to use llmware provided sample files for testing with whispercpp, integrated as of llmware 0.2.11	STRING
HIGH	…slim_agents/agents-7-using-whisper-cpp-sample-files.py	0	this example shows how to use llmware provided sample files for testing with whispercpp, integrated as of llmware 0.2.11	STRING
HIGH	docs/components/whisper_cpp.md	0	this example shows how to use llmware provided sample files for testing with whispercpp, integrated as of llmware 0.2.11	STRING
HIGH	solutions/gguf/using-phi-3-function-calls.py	0	this example shows how to use 7 different slim function calling models fine-tuned on top of phi-3: -- extraction - slim-	STRING
HIGH	solutions/models/using-phi-3-function-calls.py	0	this example shows how to use 7 different slim function calling models fine-tuned on top of phi-3: -- extraction - slim-	STRING
HIGH	…ons/slim_agents/agents-8-using-phi-3-function-calls.py	0	this example shows how to use 7 different slim function calling models fine-tuned on top of phi-3: -- extraction - slim-	STRING
HIGH	solutions/gguf/using_function_calls.py	0	discover a list of slim tools in the model catalog. -- slims are available in both traditional pytorch and quantized ggu	STRING
HIGH	solutions/models/using_function_calls.py	0	discover a list of slim tools in the model catalog. -- slims are available in both traditional pytorch and quantized ggu	STRING
HIGH	solutions/rag/example-7-function-calls.py	0	discover a list of slim tools in the model catalog. -- slims are available in both traditional pytorch and quantized ggu	STRING
HIGH	docs/components/slim_models.md	0	discover a list of slim tools in the model catalog. -- slims are available in both traditional pytorch and quantized ggu	STRING
HIGH	solutions/gguf/using_function_calls.py	0	slim models can be identified in the modelcatalog like any llmware model. instead of using inference method, slim models	STRING
HIGH	solutions/models/using_function_calls.py	0	slim models can be identified in the modelcatalog like any llmware model. instead of using inference method, slim models	STRING
HIGH	solutions/rag/example-7-function-calls.py	0	slim models can be identified in the modelcatalog like any llmware model. instead of using inference method, slim models	STRING
HIGH	docs/components/slim_models.md	0	slim models can be identified in the modelcatalog like any llmware model. instead of using inference method, slim models	STRING
HIGH	solutions/gguf/using_function_calls.py	0	this example shows two key elements of function calling slim models - 1. using logit information to indicate confidence	STRING
HIGH	solutions/models/using_function_calls.py	0	this example shows two key elements of function calling slim models - 1. using logit information to indicate confidence	STRING
HIGH	solutions/rag/example-7-function-calls.py	0	this example shows two key elements of function calling slim models - 1. using logit information to indicate confidence	STRING
HIGH	docs/components/slim_models.md	0	this example shows two key elements of function calling slim models - 1. using logit information to indicate confidence	STRING
HIGH	solutions/gguf/using_slim_extract.py	0	this example illustrates how to use the slim-extract model to extract custom keys from selected text. we have included a	STRING
HIGH	solutions/models/using_slim_extract.py	0	this example illustrates how to use the slim-extract model to extract custom keys from selected text. we have included a	STRING
HIGH	solutions/slim_agents/agents-3-using_slim_extract.py	0	this example illustrates how to use the slim-extract model to extract custom keys from selected text. we have included a	STRING
HIGH	solutions/gguf/bling_fast_start.py	0	this example demonstrates prompting local bling models with provided context - easy to select among different bling mode	STRING
HIGH	solutions/models/bling_fast_start.py	0	this example demonstrates prompting local bling models with provided context - easy to select among different bling mode	STRING
HIGH	docs/examples/models.md	0	this example demonstrates prompting local bling models with provided context - easy to select among different bling mode	STRING
HIGH	solutions/gguf/gguf_streaming.py	0	this example illustrates how to use the stream method for gguf models for fast streaming of inference, especially for re	STRING
HIGH	solutions/slim_agents/agents-11-gguf_streaming.py	0	this example illustrates how to use the stream method for gguf models for fast streaming of inference, especially for re	STRING
HIGH	docs/components/gguf.md	0	this example illustrates how to use the stream method for gguf models for fast streaming of inference, especially for re	STRING
HIGH	solutions/models/document_summarizer.py	0	this example shows a packaged 'document_summarizer' prompt using the slim-summary-tool. it shows a variety of techniques	STRING
HIGH	solutions/slim_agents/agents-9-document_summarizer.py	0	this example shows a packaged 'document_summarizer' prompt using the slim-summary-tool. it shows a variety of techniques	STRING
HIGH	docs/examples/prompts.md	0	this example shows a packaged 'document_summarizer' prompt using the slim-summary-tool. it shows a variety of techniques	STRING
HIGH	…ions/rag/example-9-function-calls-with-web-services.py	0	end-to-end example generating 30 output key:value pairs	STRING
HIGH	solutions/use_cases/web_services_slim_fx.py	0	end-to-end example generating 30 output key:value pairs	STRING
13 more matches not shown…

Modern AI Meta-Vocabulary110 hits · 322 pts

Severity	File	Line	Snippet	Context
MEDIUM	README.md	35	# 300+ Models in Catalog with 50+ RAG-optimized BLING, DRAGON and Industry BERT models	COMMENT
MEDIUM	README.md	82	# to install an embedding on a library - pick an embedding model and vector_db	COMMENT
MEDIUM	README.md	150	# including in batches, if needed, to fit the model context window	COMMENT
MEDIUM	README.md	413	# check out the model card on Huggingface for RAG benchmark test performance results and other useful information	COMMENT
MEDIUM	README.md	502	# using a RAG-optimized LLM running locally	COMMENT
MEDIUM	README.md	588	# use local cpu model - try the newest - RAG finetune of Phi-3 quantized and packaged in GGUF	COMMENT
MEDIUM	README.md	600	### OpenVINO Encoders - ideal for on-device, efficient RAG:	COMMENT
MEDIUM	README.md	629	### Industry-specific Embedding Models for Specialized RAG	COMMENT
MEDIUM	llmware/library.py	870	# step 2 - pass loaded embedding model to EmbeddingHandler, which will route to the appropriate resource	COMMENT
MEDIUM	llmware/models.py	1378	# main case - load embedding model from Catalog	COMMENT
MEDIUM	llmware/models.py	3290	# adjusted to the actual model context window (if available)	COMMENT
MEDIUM	llmware/models.py	6839	# Claude/Anthropic model - 8000 max token context window	COMMENT
MEDIUM	llmware/models.py	7167	# Google Gemini model - 8000 max token context window	COMMENT
MEDIUM	llmware/models.py	8218	# must have elements for embedding model	COMMENT
MEDIUM	llmware/models.py	8391	# default for HF embedding model -> will be over-ridden by model card / configs, if available	COMMENT
MEDIUM	llmware/models.py	8482	# option to set smaller size than model context window	COMMENT
MEDIUM	llmware/models.py	8588	# default for HF embedding model -> will be over-ridden by model card / configs, if available	COMMENT
MEDIUM	llmware/models.py	8679	# option to set smaller size than model context window	COMMENT
MEDIUM	llmware/models.py	10414	# stop if combined input + output at context window size	COMMENT
MEDIUM	llmware/models.py	11051	# stop if combined input + output at context window size	COMMENT
MEDIUM	llmware/models.py	14211	# default for HF embedding model -> will be over-ridden by model card / configs, if available	COMMENT
MEDIUM	llmware/models.py	14261	# option to set smaller size than model context window	COMMENT
MEDIUM	llmware/models.py	15610	# stop if combined input + output at context window size	COMMENT
MEDIUM	llmware/models.py	16080	# stop if combined input + output at context window size	COMMENT
MEDIUM	llmware/models.py	16192	# stop if combined input + output at context window size	COMMENT
MEDIUM	llmware/util.py	1948	# note: the tokenizer is used primarily for 'counting' against the context window, so if the	COMMENT
MEDIUM	llmware/util.py	1950	# relative to the context window, but there should be any other detrimental impacts	COMMENT
MEDIUM	llmware/prompts.py	439	# and 'inject' real-time, up-to-date fact set into the prompt to minimize hallucination risk	COMMENT
MEDIUM	llmware/prompts.py	1000	# note: when loading model, context window is automatically set based on model	COMMENT
MEDIUM	llmware/retrieval.py	131	# explicitly pass name of embedding model, if multiple embeddings on library	COMMENT
MEDIUM	llmware/retrieval.py	409	# check that embedding model is available, and if not, flip to text search	COMMENT
MEDIUM	llmware/retrieval.py	715	# confirm that embedding model exists, or catch and raise error	COMMENT
MEDIUM	llmware/retrieval.py	778	# confirm that embedding model exists, or catch and raise error	COMMENT
MEDIUM	llmware/retrieval.py	825	# confirm that embedding model exists, or catch and raise error	COMMENT
MEDIUM	tests/embeddings/test_install_embeddings.py	54	# select embedding model	COMMENT
MEDIUM	solutions/ui/integrating_pywebio_ui.py	396	# please note that by default, we recommend setting temperature=0.0 and sample=False for fact-based RAG	COMMENT
MEDIUM	solutions/embeddings/embeddings_fast_start.py	29	# To create vector embeddings you just need to specify the embedding model and the vector embedding DB	COMMENT
MEDIUM	solutions/embeddings/using_pinecone.py	22	# To create vector embeddings you just need to specify the embedding model and the vector embedding DB	COMMENT
MEDIUM⚡	solutions/embeddings/using_milvus_lite.py	124	# Step 2 - Select any embedding model in the LLMWare catalog	COMMENT
MEDIUM	solutions/embeddings/using_sentence_transformer.py	89	# use directly now as an embedding model	COMMENT
MEDIUM	solutions/embeddings/using_multiple_vector_db.py	92	# use directly now as an embedding model	COMMENT
MEDIUM	solutions/embeddings/using_multiple_vector_db.py	108	# 2. if embedding_model_name only passed, then looks up the first instance of that embedding model	COMMENT
MEDIUM	solutions/embeddings/using_multiple_embeddings.py	96	# use directly now as an embedding model	COMMENT
MEDIUM	solutions/embeddings/using_multiple_embeddings.py	113	# 2. if embedding_model_name only passed, then looks up the first instance of that embedding model	COMMENT
MEDIUM	solutions/embeddings/using_lance.py	23	# To create vector embeddings you just need to specify the embedding model and the vector embedding DB	COMMENT
MEDIUM	solutions/onnxruntime/adding_openvino_or_onnx_model.py	65	# or if using in conjunction with building a RAG prompt	COMMENT
MEDIUM	…lutions/gguf/dragon_rag_benchmark_tests_huggingface.py	25	# Pull a 200 question RAG benchmark test dataset from llmware HuggingFace repo	COMMENT
MEDIUM	solutions/gguf/dragon_rag_benchmark_tests_llmware.py	26	# Pull a 200 question RAG benchmark test dataset from llmware HuggingFace repo	COMMENT
MEDIUM	solutions/gguf/huggingface_integration.py	44	# *** use any HF embedding model, e.g., BERT, Roberta, etc.	COMMENT
MEDIUM	solutions/gguf/dragon_gguf_fast_start.py	27	# Pull a 200 question RAG benchmark test dataset from llmware HuggingFace repo	COMMENT
MEDIUM	solutions/gguf/using-qwen2-models.py	24	# 2 - RAG FINETUNE - DRAGON + BLING	COMMENT
MEDIUM	solutions/gguf/using-qwen2-models.py	26	print("\nExample #2 - RAG finetuned Qwen2 for fact-based question answering with context passage.")	CODE
MEDIUM	solutions/gguf/llmware_model_fast_start.py	85	# Pull a 200 question RAG benchmark test dataset from llmware HuggingFace repo	COMMENT
MEDIUM⚡	solutions/openvino/README.md	108	Explore a wide range of [examples in the llmware repository](https://llmware-ai.github.io/llmware/examples). Because Ope	CODE
MEDIUM	solutions/openvino/adding_openvino_or_onnx_model.py	65	# or if using in conjunction with building a RAG prompt	COMMENT
MEDIUM	…tions/models/dragon_rag_benchmark_tests_huggingface.py	25	# Pull a 200 question RAG benchmark test dataset from llmware HuggingFace repo	COMMENT
MEDIUM	solutions/models/dragon_rag_benchmark_tests_llmware.py	26	# Pull a 200 question RAG benchmark test dataset from llmware HuggingFace repo	COMMENT
MEDIUM	solutions/models/huggingface_integration.py	44	# *** use any HF embedding model, e.g., BERT, Roberta, etc.	COMMENT
MEDIUM	solutions/models/prompt_with_pdf_source.py	23	# 3. batch according to the model context window, and make available for any future inferences	COMMENT
MEDIUM	solutions/models/dragon_gguf_fast_start.py	27	# Pull a 200 question RAG benchmark test dataset from llmware HuggingFace repo	COMMENT
50 more matches not shown…

Hyper-Verbose Identifiers281 hits · 252 pts

Severity	File	Line	Snippet	Context
LOW	README.md	353	def bling_meets_llmware_hello_world (model_name):	CODE
LOW	README.md	510	def contract_analysis_on_laptop (model_name):	CODE
LOW	llmware/configs.py	263	def get_supported_collection_db(cls):	CODE
LOW	llmware/configs.py	434	def get_logging_level_by_module(cls, module):	CODE
LOW	llmware/configs.py	441	def set_logging_level_by_module(cls, module, level):	CODE
LOW	llmware/configs.py	799	def get_uri_string_experimental_db(cls):	CODE
LOW⚡	llmware/configs.py	1143	def get_auth_credentials_provider(cls):	CODE
LOW⚡	llmware/configs.py	1147	def get_auth_credentials_file(cls):	CODE
LOW⚡	llmware/configs.py	1155	def get_auth_token_transport_header(cls):	CODE
LOW	llmware/library.py	454	def set_incremental_docs_blocks_images(self, added_docs=0, added_blocks=0, added_images=0, added_pages=0,	CODE
LOW	llmware/library.py	627	def export_library_to_txt_file(self, output_fp=None, output_fn=None, include_text=True, include_tables=True,	CODE
LOW	llmware/library.py	684	def export_library_to_jsonl_file(self, output_fp, output_fn, include_text=True, include_tables=True,	CODE
LOW	llmware/library.py	757	def pull_files_from_cloud_bucket (self, aws_access_key=None, aws_secret_key=None, bucket_name=None):	CODE
LOW	llmware/library.py	1133	def delete_installed_embedding(self, embedding_model_name, vector_db, vector_db_api_key=None):	CODE
LOW	llmware/library.py	1210	def expand_text_result_before(self, block, window_size=400):	CODE
LOW	llmware/library.py	1424	def set_incremental_docs_blocks_images(self, added_docs=0, added_blocks=0, added_images=0, added_pages=0,	CODE
LOW⚡	llmware/models.py	2699	def get_global_inference_count(cls):	CODE
LOW⚡	llmware/models.py	2703	def increment_global_inference_count(cls):	CODE
LOW⚡	llmware/models.py	2708	def reset_global_inference_count(cls):	CODE
LOW	llmware/models.py	178	def get_tokenizer_bos_eos_lookup(cls):	CODE
LOW	llmware/models.py	202	def load_prompt_wrappers_from_file(cls, new_wrapper_registry):	CODE
LOW	llmware/models.py	214	def load_tokenizer_configs_from_file(cls, new_tokenizer_configs):	CODE
LOW	llmware/models.py	370	def create_new_foundry_manager(cls):	CODE
LOW	llmware/models.py	602	def load_prompt_wrapper_registry(self, fp=None, fn="prompt_wrappers.json"):	CODE
LOW	llmware/models.py	615	def save_prompt_wrapper_registry(self, fp=None, fn="prompt_wrappers.json"):	CODE
LOW	llmware/models.py	630	def get_tokenizer_bos_eos_configs(self):	CODE
LOW	llmware/models.py	636	def save_tokenizer_bos_eos_configs(self, fp=None, fn="tokenizer_bos_eos_configs.json"):	CODE
LOW	llmware/models.py	651	def load_tokenizer_bos_eos_configs(self, fp=None, fn="tokenizer_bos_eos_configs.json"):	CODE
LOW	llmware/models.py	664	def add_model_cards_from_file(self, fp=None, fn="custom_models_manifest.json"):	CODE
LOW	llmware/models.py	703	def register_new_finetune_wrapper(self, name, main_start="", main_stop="", llm_start="",	CODE
LOW	llmware/models.py	730	def get_list_registered_finetune_wrappers(self):	CODE
LOW	llmware/models.py	736	def register_new_hf_generative_model(self, hf_model_name, llmware_lookup_name=None, display_name=None,	CODE
LOW	llmware/models.py	778	def register_sentence_transformer_model(self, model_name, embedding_dims, context_window,	CODE
LOW	llmware/models.py	920	def setup_custom_llmware_inference_server(self, uri_string, secret_key=None):	CODE
LOW	llmware/models.py	953	def _instantiate_model_class_from_string(self, model_class, model_name, model_card, api_key=None,	CODE
LOW	llmware/models.py	1325	def load_sentence_transformer_model(self,model, model_name):	CODE
LOW	llmware/models.py	1442	def list_generative_local_models(self):	CODE
LOW	llmware/models.py	1468	def list_intel_npu_optimized_models(self):	CODE
LOW	llmware/models.py	1757	def list_function_call_models(self):	CODE
LOW	llmware/models.py	1997	def remediate_function_call_string(self,input_string, dedupe_values=True):	CODE
LOW	llmware/models.py	2444	def parse_instruction_for_user_vars(self, prompt_card, inference_dict=None):	CODE
LOW	llmware/models.py	3935	def cleanup_stream_gen_on_early_stop(self):	CODE
LOW	llmware/models.py	3942	def inference_over_api_endpoint(self, prompt, context=None, inference_dict=None, get_logits=False):	CODE
LOW	llmware/models.py	4003	def function_call_over_api_endpoint(self, context="", tool_type="", model_name="", params="", prompt="",	CODE
LOW	llmware/models.py	4422	def load_ov_external_tokenizer(self):	CODE
LOW	llmware/models.py	4480	def ov_text_to_image_pipeline(self):	CODE
LOW	llmware/models.py	4950	def inference_over_api_endpoint(self, prompt, context=None, inference_dict=None, get_logits=False):	CODE
LOW	llmware/models.py	5145	def function_call_over_api_endpoint(self, context="", tool_type="", model_name="", params="", prompt="",	CODE
LOW	llmware/models.py	5526	def load_ov_external_tokenizer(self):	CODE
LOW	llmware/models.py	5842	def prompt_engineer_completion (self, query, context, inference_dict=None):	CODE
LOW	llmware/models.py	7978	def cleanup_stream_gen_on_early_stop(self):	CODE
LOW	llmware/models.py	9705	def inference_over_api_endpoint(self, prompt, context=None, inference_dict=None, get_logits=False):	CODE
LOW	llmware/models.py	9767	def function_call_over_api_endpoint(self, context="", tool_type="", model_name="", params="", prompt="",	CODE
LOW	llmware/models.py	10177	def _load_llama_cpp_shared_library(self):	CODE
LOW	llmware/models.py	11074	def function_call_over_api_endpoint(self, context="", tool_type="", model_name="", params="", prompt="",	CODE
LOW	llmware/models.py	11162	def inference_over_api_endpoint(self, prompt, context=None, inference_dict=None, get_logits=False):	CODE
LOW	llmware/models.py	12610	def create_model_catalog_extension(self):	CODE
LOW	llmware/models.py	12749	def prepare_foundry_manager_and_model(self):	CODE
LOW	llmware/models.py	13762	def cleanup_stream_gen_on_early_stop(self):	CODE
LOW	llmware/models.py	14945	def _load_clip_model_for_inference(self, model_repo_path, model_card=None, **kwargs):	CODE
221 more matches not shown…

Structural Annotation Overuse104 hits · 215 pts

Severity	File	Line	Snippet	Context
LOW	llmware/models.py	1137	# Step 1 - resolve local path	COMMENT
LOW⚡	tests/embeddings/test_install_embeddings.py	17	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	tests/embeddings/test_install_embeddings.py	26	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	tests/embeddings/test_install_embeddings.py	32	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	solutions/embeddings/using_chromadb.py	45	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	solutions/embeddings/using_chromadb.py	50	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	solutions/embeddings/using_chromadb.py	56	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	solutions/embeddings/using_redis.py	34	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	solutions/embeddings/using_redis.py	39	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	solutions/embeddings/using_redis.py	45	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	solutions/embeddings/using_milvus_lite.py	28	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	solutions/embeddings/using_milvus_lite.py	37	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	solutions/embeddings/using_milvus_lite.py	43	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	solutions/embeddings/using_milvus_lite.py	121	# Step 1 - create library	COMMENT
LOW⚡	solutions/embeddings/using_milvus_lite.py	124	# Step 2 - Select any embedding model in the LLMWare catalog	COMMENT
LOW⚡	solutions/embeddings/using_neo4j.py	47	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	solutions/embeddings/using_neo4j.py	52	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	solutions/embeddings/using_neo4j.py	58	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	solutions/embeddings/using_sentence_transformer.py	26	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	solutions/embeddings/using_sentence_transformer.py	31	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	solutions/embeddings/using_sentence_transformer.py	37	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	solutions/embeddings/using_multiple_vector_db.py	34	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	solutions/embeddings/using_multiple_vector_db.py	39	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	solutions/embeddings/using_multiple_vector_db.py	45	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	solutions/embeddings/using_pg_vector.py	46	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	solutions/embeddings/using_pg_vector.py	51	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	solutions/embeddings/using_pg_vector.py	57	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	solutions/embeddings/using_multiple_embeddings.py	39	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	solutions/embeddings/using_multiple_embeddings.py	44	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	solutions/embeddings/using_multiple_embeddings.py	50	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	solutions/embeddings/using_qdrant.py	31	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	solutions/embeddings/using_qdrant.py	36	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	solutions/embeddings/using_qdrant.py	42	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	solutions/embeddings/docs2vecs_with_milvus-rag.py	23	# Step 0 - Configuration - we will use these in Step 4 to install the embeddings	COMMENT
LOW⚡	solutions/embeddings/docs2vecs_with_milvus-rag.py	27	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	solutions/embeddings/docs2vecs_with_milvus-rag.py	32	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	solutions/embeddings/docs2vecs_with_milvus-rag.py	39	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	solutions/embeddings/docs2vecs_with_milvus-rag.py	45	# Step 4 - Install the embeddings	COMMENT
LOW⚡	…ons/embeddings/docs2vecs_with_milvus-un_resolutions.py	21	# Step 0 - Configuration - we will use these in Step 4 to install the embeddings	COMMENT
LOW⚡	…ons/embeddings/docs2vecs_with_milvus-un_resolutions.py	25	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	…ons/embeddings/docs2vecs_with_milvus-un_resolutions.py	30	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	…ons/embeddings/docs2vecs_with_milvus-un_resolutions.py	36	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	…ons/embeddings/docs2vecs_with_milvus-un_resolutions.py	42	# Step 4 - Install the embeddings	COMMENT
LOW⚡	…ons/embeddings/docs2vecs_with_milvus-un_resolutions.py	52	# Step 5 - start using the new vector embeddings with Query	COMMENT
LOW⚡	solutions/embeddings/docs2vecs_with_milvus-contracts.py	22	# Step 0 - Configuration - we will use these in Step 4 to install the embeddings	COMMENT
LOW⚡	solutions/embeddings/docs2vecs_with_milvus-contracts.py	26	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	solutions/embeddings/docs2vecs_with_milvus-contracts.py	31	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
LOW⚡	solutions/embeddings/docs2vecs_with_milvus-contracts.py	37	# Step 3 - point ".add_files" method to the folder of documents that was just created	COMMENT
LOW⚡	solutions/embeddings/docs2vecs_with_milvus-contracts.py	43	# Step 4 - Install the embeddings	COMMENT
LOW⚡	solutions/embeddings/docs2vecs_with_milvus-contracts.py	53	# Step 5 - start using the new vector embeddings with Query	COMMENT
LOW	solutions/gguf/using-custom-gguf-model.py	16	# Step 1 - register new gguf model - we will pick the popular LLama-2-13B-chat-GGUF	COMMENT
LOW	solutions/gguf/using-custom-gguf-model.py	23	# Step 2- if the prompt_wrapper is a standard, e.g., Meta's <INST>, then no need to do anything else	COMMENT
LOW	solutions/gguf/using-ollama-models.py	8	# Step 1 - register your Ollama models in llmware ModelCatalog	COMMENT
LOW	solutions/gguf/using-ollama-models.py	22	# Step 2 - start using the Ollama model like any other model in llmware	COMMENT
LOW	solutions/gguf/using-ollama-models.py	66	# Step 3 - using the ollama discovery API - optional	COMMENT
LOW	solutions/models/using-ollama-models.py	8	# Step 1 - register your Ollama models in llmware ModelCatalog	COMMENT
LOW	solutions/models/using-ollama-models.py	22	# Step 2 - start using the Ollama model like any other model in llmware	COMMENT
LOW	solutions/models/using-ollama-models.py	66	# Step 3 - using the ollama discovery API - optional	COMMENT
LOW⚡	solutions/rag/example-2-build_embeddings.py	56	# Step 1 - Create library which is the main 'organizing construct' in llmware	COMMENT
LOW⚡	solutions/rag/example-2-build_embeddings.py	65	# Step 2 - Pull down the sample files from S3 through the .load_sample_files() command	COMMENT
44 more matches not shown…

Deep Nesting167 hits · 116 pts

Severity	File	Line	Context
LOW	llmware/configs.py	403	CODE
LOW	llmware/models.py	257	CODE
LOW	llmware/models.py	993	CODE
LOW	llmware/models.py	1119	CODE
LOW	llmware/models.py	1276	CODE
LOW	llmware/models.py	1547	CODE
LOW	llmware/models.py	1659	CODE
LOW	llmware/models.py	1770	CODE
LOW	llmware/models.py	1997	CODE
LOW	llmware/models.py	2198	CODE
LOW	llmware/models.py	2322	CODE
LOW	llmware/models.py	2444	CODE
LOW	llmware/models.py	2487	CODE
LOW	llmware/models.py	2579	CODE
LOW	llmware/models.py	2836	CODE
LOW	llmware/models.py	3076	CODE
LOW	llmware/models.py	4088	CODE
LOW	llmware/models.py	4321	CODE
LOW	llmware/models.py	5227	CODE
LOW	llmware/models.py	5455	CODE
LOW	llmware/models.py	5870	CODE
LOW	llmware/models.py	6451	CODE
LOW	llmware/models.py	6631	CODE
LOW	llmware/models.py	8769	CODE
LOW	llmware/models.py	9345	CODE
LOW	llmware/models.py	10177	CODE
LOW	llmware/models.py	10813	CODE
LOW	llmware/models.py	11343	CODE
LOW	llmware/models.py	11769	CODE
LOW	llmware/models.py	11985	CODE
LOW	llmware/models.py	12067	CODE
LOW	llmware/models.py	12127	CODE
LOW	llmware/models.py	12186	CODE
LOW	llmware/models.py	12582	CODE
LOW	llmware/models.py	12610	CODE
LOW	llmware/models.py	13304	CODE
LOW	llmware/models.py	13850	CODE
LOW	llmware/models.py	13884	CODE
LOW	llmware/models.py	13926	CODE
LOW	llmware/models.py	14071	CODE
LOW	llmware/models.py	14100	CODE
LOW	llmware/models.py	15071	CODE
LOW	llmware/models.py	15240	CODE
LOW	llmware/models.py	15407	CODE
LOW	llmware/util.py	242	CODE
LOW	llmware/util.py	578	CODE
LOW	llmware/util.py	641	CODE
LOW	llmware/util.py	689	CODE
LOW	llmware/util.py	775	CODE
LOW	llmware/util.py	851	CODE
LOW	llmware/util.py	953	CODE
LOW	llmware/util.py	999	CODE
LOW	llmware/util.py	1043	CODE
LOW	llmware/util.py	1294	CODE
LOW	llmware/util.py	1464	CODE
LOW	llmware/util.py	1508	CODE
LOW	llmware/util.py	1920	CODE
LOW	llmware/util.py	1990	CODE
LOW	llmware/web_services.py	191	CODE
LOW	llmware/web_services.py	480	CODE
107 more matches not shown…

Self-Referential Comments22 hits · 70 pts

Severity	File	Line	Snippet	Context
MEDIUM	llmware/embeddings.py	940	# Creating an index will accelerate the search process and it needs to be done once table has some vectors a	COMMENT
MEDIUM	tests/models/test_agent_llmfx_process.py	9	# Create an agent using LLMfx class	COMMENT
MEDIUM	tests/models/test_cohere_command_r_model.py	13	# Define a simple prompt for testing	COMMENT
MEDIUM	solutions/embeddings/using_mongo_atlas.py	30	# Create a library and populate it with some sample documents	COMMENT
MEDIUM	solutions/gguf/huggingface_integration.py	139	# Create a library and add some documents so we can do some vector embeddings	COMMENT
MEDIUM	solutions/gguf/huggingface_integration.py	172	# Create a library and add some documents so we can do some vector embeddings	COMMENT
MEDIUM	solutions/gguf/cohere_command_r_example.py	13	# Define a prompt for inference	COMMENT
MEDIUM	solutions/models/huggingface_integration.py	139	# Create a library and add some documents so we can do some vector embeddings	COMMENT
MEDIUM	solutions/models/huggingface_integration.py	172	# Create a library and add some documents so we can do some vector embeddings	COMMENT
MEDIUM	solutions/models/prompt_state.py	11	# Create a new prompter with state persistence	COMMENT
MEDIUM	solutions/models/prompt_state.py	20	# Define a list of prompts	COMMENT
MEDIUM	solutions/models/cohere_command_r_example.py	13	# Define a prompt for inference	COMMENT
MEDIUM⚡	solutions/sources/semantic_retrieval.py	39	# Create a Query instance	COMMENT
MEDIUM	solutions/sources/bulk_retrieval.py	28	# Create a Query instance	COMMENT
MEDIUM	solutions/sources/bulk_retrieval.py	31	# Create a list of keys of interest. This can be omitted if you want all keys	COMMENT
MEDIUM	solutions/sources/query_state.py	29	# Create a Query instance with history persistence	COMMENT
MEDIUM⚡	solutions/sources/text_retrieval.py	29	# Create a Query instance	COMMENT
MEDIUM	solutions/sources/bibliography.py	28	# Create a Query instance	COMMENT
MEDIUM⚡	solutions/sources/dual_pass_with_custom_filter.py	19	# Create a new library or load if it exists	COMMENT
MEDIUM	solutions/use_cases/lecture_tool/pages/4_Summarizer.py	65	# Create a list of only the unique points generated by the model	COMMENT
MEDIUM	solutions/slim_agents/youtube_topics_extraction.py	21	# Create a LLMfx object	COMMENT
MEDIUM	tutorials/getting_started/working_with_libraries.py	47	# Create a library	COMMENT

Excessive Try-Catch Wrapping45 hits · 46 pts

Severity	File	Line	Snippet	Context
LOW	llmware/models.py	2358	except Exception as e:	CODE
LOW	llmware/models.py	6010	except Exception as e:	CODE
LOW	llmware/models.py	6295	except Exception as e:	CODE
LOW	llmware/models.py	6610	except Exception as e:	CODE
LOW	llmware/models.py	6789	except Exception as e:	CODE
LOW	llmware/models.py	7016	except Exception as e:	CODE
LOW	llmware/models.py	7114	except Exception as e:	CODE
LOW	llmware/models.py	7338	except Exception as e:	CODE
LOW	llmware/models.py	7458	except Exception as e:	CODE
LOW	llmware/models.py	7835	except Exception as e:	CODE
LOW	llmware/models.py	10282	except Exception as e:	CODE
LOW	llmware/models.py	11436	except Exception as e:	CODE
LOW	llmware/models.py	13609	except Exception as e:	CODE
LOW	llmware/models.py	13654	except Exception as e:	CODE
LOW	llmware/models.py	13726	except Exception as e:	CODE
LOW	llmware/models.py	14384	except Exception as e:	CODE
LOW	llmware/models.py	15176	except Exception as e:	CODE
LOW	llmware/models.py	15351	except Exception as e:	CODE
LOW	llmware/web_services.py	452	except Exception as e:	CODE
LOW	llmware/web_services.py	1176	except Exception as e:	CODE
LOW	llmware/web_services.py	1205	except Exception as e:	CODE
LOW	llmware/web_services.py	1233	except Exception as e:	CODE
LOW	llmware/web_services.py	1274	except Exception as e:	CODE
LOW	llmware/web_services.py	1316	except Exception as e:	CODE
LOW	llmware/web_services.py	1351	except Exception as e:	CODE
MEDIUM	llmware/web_services.py	357	def __init__(self, url_or_fp, link="/", save_images=True, reset_img_folder=False	CODE
LOW	llmware/parsers.py	624	except Exception as e:	CODE
LOW	llmware/embeddings.py	1034	except Exception as e:	CODE
LOW	llmware/embeddings.py	2383	except Exception as err:	CODE
MEDIUM	llmware/embeddings.py	1019	def search_index(self, query_embedding_vector, sample_count=10):	CODE
LOW	tests/run-tests.py	24	except Exception as e:	CODE
LOW	tests/run-tests.py	41	except Exception as e:	CODE
LOW	tests/run-tests.py	54	except Exception as e:	CODE
LOW	tests/run-tests.py	64	except Exception as e:	CODE
LOW	tests/run-tests.py	85	except Exception as e:	CODE
LOW	tests/run-tests.py	100	except Exception as e:	CODE
LOW	tests/models/test_prompt_benchmark_test.py	46	except Exception as e:	CODE
LOW	tests/models/test_prompt_benchmark_test.py	102	except Exception as e:	CODE
LOW⚡	solutions/gguf/chat_models_gguf_fast_start.py	26	except Exception as e:	CODE
LOW⚡	solutions/gguf/chat_models_gguf_fast_start.py	36	except Exception as e:	CODE
LOW⚡	solutions/models/chat_models_gguf_fast_start.py	26	except Exception as e:	CODE
LOW⚡	solutions/models/chat_models_gguf_fast_start.py	36	except Exception as e:	CODE
MEDIUM⚡	solutions/sources/dual_pass_with_custom_filter.py	24	print(f"Error: Failed to create or load library '{library_name}'")	CODE
MEDIUM⚡	solutions/sources/dual_pass_with_custom_filter.py	30	print(f"Error: Input folder path '{input_folder_path}' does not exist.")	CODE
MEDIUM⚡	solutions/sources/dual_pass_with_custom_filter.py	40	print(f"Error: Embedding generation failed for model '{embedding_model}' with vector db '{vector_db}'")	CODE

AI Structural Patterns69 hits · 42 pts

Severity	File	Line	Context
LOW	llmware/library.py	516	CODE
LOW	llmware/library.py	783	CODE
LOW	llmware/library.py	1208	CODE
LOW	llmware/library.py	1231	CODE
LOW	llmware/library.py	1254	CODE
LOW	llmware/models.py	880	CODE
LOW	llmware/models.py	1036	CODE
LOW	llmware/models.py	1659	CODE
LOW	llmware/models.py	3076	CODE
LOW	llmware/models.py	4003	CODE
LOW	llmware/models.py	4088	CODE
LOW	llmware/models.py	5145	CODE
LOW	llmware/models.py	5227	CODE
LOW	llmware/models.py	6182	CODE
LOW	llmware/models.py	7499	CODE
LOW	llmware/models.py	8372	CODE
LOW	llmware/models.py	8569	CODE
LOW	llmware/models.py	8769	CODE
LOW	llmware/models.py	9767	CODE
LOW	llmware/models.py	9850	CODE
LOW	llmware/models.py	11074	CODE
LOW	llmware/models.py	11669	CODE
LOW	llmware/models.py	13122	CODE
LOW	llmware/models.py	13429	CODE
LOW	llmware/models.py	13696	CODE
LOW	llmware/models.py	14192	CODE
LOW	llmware/models.py	14697	CODE
LOW	llmware/models.py	16212	CODE
LOW	llmware/web_services.py	1249	CODE
LOW	llmware/parsers.py	62	CODE
LOW	llmware/parsers.py	1198	CODE
LOW	llmware/parsers.py	3059	CODE
LOW	llmware/parsers.py	3325	CODE
LOW	llmware/parsers.py	3459	CODE
LOW	llmware/parsers.py	4337	CODE
LOW	llmware/prompts.py	103	CODE
LOW	llmware/prompts.py	216	CODE
LOW	llmware/prompts.py	690	CODE
LOW	llmware/prompts.py	697	CODE
LOW	llmware/prompts.py	711	CODE
LOW	llmware/prompts.py	720	CODE
LOW	llmware/prompts.py	731	CODE
LOW	llmware/prompts.py	746	CODE
LOW	llmware/prompts.py	760	CODE
LOW	llmware/prompts.py	773	CODE
LOW	llmware/prompts.py	1245	CODE
LOW	llmware/prompts.py	1253	CODE
LOW	llmware/prompts.py	1261	CODE
LOW	llmware/prompts.py	1962	CODE
LOW	llmware/prompts.py	1971	CODE
LOW	llmware/agents.py	1370	CODE
LOW	llmware/retrieval.py	116	CODE
LOW	llmware/retrieval.py	1684	CODE
LOW	llmware/retrieval.py	1719	CODE
LOW	llmware/retrieval.py	1741	CODE
LOW	llmware/retrieval.py	1748	CODE
LOW	llmware/resources.py	808	CODE
LOW	llmware/resources.py	3559	CODE
LOW	llmware/resources.py	3659	CODE
LOW	llmware/resources.py	3704	CODE
9 more matches not shown…

Unused Imports37 hits · 36 pts

Severity	File	Line	Context
LOW	setup.py	3	CODE
LOW	setup.py	4	CODE
LOW	setup.py	6	CODE
LOW	setup.py	7	CODE
LOW	setup.py	7	CODE
LOW	llmware/models.py	18	CODE
LOW	llmware/models.py	32	CODE
LOW	llmware/util.py	31	CODE
LOW	llmware/web_services.py	364	CODE
LOW	llmware/parsers.py	48	CODE
LOW	llmware/gguf_configs.py	29	CODE
LOW	llmware/gguf_configs.py	30	CODE
LOW	llmware/gguf_configs.py	32	CODE
LOW	llmware/gguf_configs.py	32	CODE
LOW	tests/run-tests.py	48	CODE
LOW	tests/embeddings/test_all_embedding_dbs.py	6	CODE
LOW	tests/embeddings/test_all_embedding_dbs.py	14	CODE
LOW	tests/embeddings/test_all_embedding_dbs.py	15	CODE
LOW	tests/library/test_library.py	11	CODE
LOW	tests/models/test_prompt_benchmark_test.py	14	CODE
LOW	tests/models/test_hf_model_load_prompt.py	3	CODE
LOW	tests/configs/test_account_overrides.py	11	CODE
LOW	solutions/gguf/huggingface_integration.py	17	CODE
LOW	solutions/gguf/using_gguf.py	3	CODE
LOW	solutions/models/huggingface_integration.py	17	CODE
LOW	solutions/models/prompt_with_sources.py	10	CODE
LOW	solutions/rag/example-5-rag-semantic-query.py	36	CODE
LOW	solutions/sources/parse_images.py	9	CODE
LOW	solutions/sources/parse_images.py	9	CODE
LOW	solutions/sources/parse_images.py	10	CODE
LOW	solutions/sources/parse_web_sources_in_memory.py	16	CODE
LOW	solutions/use_cases/agent_with_custom_tables.py	27	CODE
LOW	solutions/use_cases/agent_with_custom_tables.py	31	CODE
LOW	…tions/slim_agents/document_unique_topics_extraction.py	8	CODE
LOW	…ns/slim_agents/agents-5-agent-llmfx-getting-started.py	12	CODE
LOW	solutions/slim_agents/agent-llmfx-getting-started.py	12	CODE
LOW	solutions/slim_agents/youtube_topics_extraction.py	8	CODE

AI Slop Vocabulary13 hits · 34 pts

Severity	File	Line	Snippet	Context
MEDIUM	llmware/models.py	9131	# explicit check and setting to facilitate debugging	COMMENT
MEDIUM	llmware/models.py	9164	# explicit check and setting to facilitate debugging, if needed	COMMENT
MEDIUM	llmware/models.py	9187	# explicit check and setting to facilitate debugging, if needed	COMMENT
MEDIUM	llmware/models.py	9471	# explicit check and setting to facilitate debugging	COMMENT
MEDIUM	llmware/models.py	9504	# explicit check and setting to facilitate debugging, if needed	COMMENT
MEDIUM	llmware/models.py	9522	# explicit check and setting to facilitate debugging, if needed	COMMENT
LOW	llmware/web_services.py	850	# this is an external link - just use the source	COMMENT
MEDIUM	llmware/prompts.py	568	# this method is intended to be used in conjunction with sources as follows:	COMMENT
MEDIUM	llmware/agents.py	1585	#TODO: build more robust type checking, e.g., float/decimal/currency	COMMENT
LOW	llmware/embeddings.py	1444	# if wait longer than 5 mins, then time out and just return	COMMENT
MEDIUM	solutions/onnxruntime/adding_openvino_or_onnx_model.py	65	# or if using in conjunction with building a RAG prompt	COMMENT
MEDIUM	solutions/openvino/adding_openvino_or_onnx_model.py	65	# or if using in conjunction with building a RAG prompt	COMMENT
LOW	solutions/slim_agents/agents-1-start_here.py	62	# Discovering other models is easy -> to invoke a model, simply use the 'model_name' and pass in .load_model()	COMMENT

Over-Commented Block29 hits · 28 pts

Severity	File	Line	Snippet	Context
LOW	llmware/models.py	11321		COMMENT
LOW	llmware/parsers.py	741	# char * input_fp	COMMENT
LOW	llmware/parsers.py	1021	# if any issue loading module, will be captured at .get_module_office_parser()	COMMENT
LOW	llmware/parsers.py	1041	# int unique_doc_num	COMMENT
LOW	llmware/parsers.py	2421	# char * write_to_filename	COMMENT
LOW	llmware/parsers.py	2601	# char * input_filename	COMMENT
LOW	llmware/parsers.py	3601	# char * input_account_name	COMMENT
LOW	llmware/parsers.py	3801	# char * input_account_name	COMMENT
LOW	tests/set-env.sh	1	# LLM API KEYS	COMMENT
LOW	tests/set-env.sh	21	#export NEO4J_PASSWORD=<an alternative Neo4j password>	COMMENT
LOW	tests/embeddings/test_all_embedding_dbs.py	81	sample_files_path = Setup().load_sample_files()	COMMENT
LOW	solutions/embeddings/using_multiple_vector_db.py	101		COMMENT
LOW	solutions/embeddings/using_multiple_embeddings.py	101	print("\nupdate: Embedding record of the Library")	COMMENT
LOW	solutions/gguf/using-llama-3.py	1		COMMENT
LOW	solutions/models/set_model_api_keys.py	21		COMMENT
LOW	solutions/models/using-llama-3.py	1		COMMENT
LOW	solutions/rag/example-2-build_embeddings.py	161	# alternatively, to use this example as self-contained, then create a new library from scratch:	COMMENT
LOW	solutions/sources/parse_jsonl_custom.py	41	# All three text databases supported (mongo, postgres, and sqlite)	COMMENT
LOW	solutions/sources/pdf_parser_new_configs.py	21	# Measured in string len characters, e.g., 400 characters as target text chunk size, with max of 600 characters	COMMENT
LOW	solutions/sources/pdf_parser_new_configs.py	41	# ENCODING	COMMENT
LOW	solutions/sources/pdf_parser_new_configs.py	61	lib.add_files(input_folder_path=fp, strip_header=True)	COMMENT
LOW	solutions/sources/parse_csv_custom.py	101	# if "doc_ID" or "block_ID" mapping provided, then will "over-write" the default doc_ID and block_ID and	COMMENT
LOW	solutions/sources/office_parser_new_configs.py	21		COMMENT
LOW	solutions/sources/office_parser_new_configs.py	61		COMMENT
LOW	solutions/use_cases/lecture_tool/pages/3_Prompts.py	41		COMMENT
LOW	solutions/slim_agents/agents-1-start_here.py	141		COMMENT
LOW	docs/components/model_catalog.md	161	# Add a LM Studio Model	COMMENT
LOW	scripts/aws/launch-llmware-ami.sh	1	#! /bin/bash	COMMENT
LOW	tutorials/getting_started/loading_sample_files.py	21		COMMENT

Decorative Section Separators6 hits · 27 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	solutions/openvino/README.md	114	# ---------------------------	COMMENT
MEDIUM⚡	solutions/openvino/README.md	116	# ---------------------------	COMMENT
MEDIUM⚡	solutions/openvino/README.md	124	# ---------------------------	COMMENT
MEDIUM⚡	solutions/openvino/README.md	126	# ---------------------------	COMMENT
MEDIUM⚡	solutions/openvino/README.md	134	# ---------------------------	COMMENT
MEDIUM⚡	solutions/openvino/README.md	136	# ---------------------------	COMMENT

Redundant / Tautological Comments14 hits · 21 pts

Severity	File	Line	Snippet	Context
LOW	llmware/models.py	14983	# Check if vision is supported	COMMENT
LOW	llmware/models.py	15224	# Check if vision is supported	COMMENT
LOW	tests/models/test_prompt_benchmark_test.py	71	# Print results	COMMENT
LOW	…lutions/gguf/dragon_rag_benchmark_tests_huggingface.py	88	# Print results	COMMENT
LOW	solutions/gguf/dragon_rag_benchmark_tests_llmware.py	54	# Print results	COMMENT
LOW	solutions/gguf/using-custom-gguf-model.py	46	# Print results	COMMENT
LOW⚡	solutions/gguf/chat_models_gguf_fast_start.py	40	# Print results	COMMENT
LOW	solutions/gguf/dragon_gguf_fast_start.py	54	# Print results	COMMENT
LOW	solutions/gguf/llmware_model_fast_start.py	148	# Print results	COMMENT
LOW	…tions/models/dragon_rag_benchmark_tests_huggingface.py	88	# Print results	COMMENT
LOW	solutions/models/dragon_rag_benchmark_tests_llmware.py	54	# Print results	COMMENT
LOW⚡	solutions/models/chat_models_gguf_fast_start.py	40	# Print results	COMMENT
LOW	solutions/models/dragon_gguf_fast_start.py	54	# Print results	COMMENT
LOW	solutions/models/llmware_model_fast_start.py	148	# Print results	COMMENT

Slop Phrases8 hits · 21 pts

Severity	File	Line	Snippet	Context
MEDIUM	solutions/gguf/adjusting_sampling_settings.py	22	# -- temperature: range between 0.0 - 1.0 (for GGUF models, you can also try setting to negative)	COMMENT
LOW	solutions/gguf/using-azure-openai.py	20	# Make sure to replace the deployment names with your deployments in the	COMMENT
MEDIUM	solutions/gguf/using-azure-openai.py	67	# reset so you can use the standard OpenAI client	COMMENT
MEDIUM	solutions/openvino/using_openvino_streamer.py	31	# here is a simple example that will stream the text to local host	COMMENT
MEDIUM	solutions/openvino/using-openvino-vision-models.py	30	# here is a simple example that will stream the text to local host	COMMENT
MEDIUM	solutions/models/adjusting_sampling_settings.py	22	# -- temperature: range between 0.0 - 1.0 (for GGUF models, you can also try setting to negative)	COMMENT
LOW	solutions/models/using-azure-openai.py	20	# Make sure to replace the deployment names with your deployments in the	COMMENT
MEDIUM	solutions/models/using-azure-openai.py	67	# reset so you can use the standard OpenAI client	COMMENT

Modern Structural Boilerplate14 hits · 12 pts

Severity	File	Line	Snippet	Context
LOW	llmware/library.py	35	logger = logging.getLogger(__name__)	CODE
LOW	llmware/models.py	60	logger = logging.getLogger(__name__)	CODE
LOW	llmware/models.py	14017	def set_request_tensor(self, request, tensor, key=None) -> None:	CODE
LOW	llmware/models.py	14031	def update_tensor(self, inputs: Any, request, key=None) -> None:	CODE
LOW	llmware/util.py	48	logger = logging.getLogger(__name__)	CODE
LOW	llmware/web_services.py	27	logger = logging.getLogger(__name__)	CODE
LOW	llmware/parsers.py	56	logger = logging.getLogger(__name__)	CODE
LOW	llmware/prompts.py	40	logger = logging.getLogger(__name__)	CODE
LOW	llmware/agents.py	39	logger = logging.getLogger(__name__)	CODE
LOW	llmware/setup.py	32	logger = logging.getLogger(__name__)	CODE
LOW	llmware/embeddings.py	73	logger = logging.getLogger(__name__)	CODE
LOW	llmware/retrieval.py	40	logger = logging.getLogger(__name__)	CODE
LOW	llmware/resources.py	60	logger = logging.getLogger(__name__)	CODE
LOW	llmware/gguf_configs.py	34	logger = logging.getLogger(__name__)	CODE

Cross-Language Confusion1 hit · 8 pts

Severity	File	Line	Snippet	Context
HIGH	llmware/retrieval.py	1516	# edge case - but return empty match if query is null	COMMENT

TODO Padding1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	llmware/resources.py	4103	# TODO: implement cursor option - see DBCursor class for more details.	COMMENT

Example Usage Blocks1 hit · 2 pts

Severity	File	Line	Snippet	Context
LOW	tests/models/test_prompt_benchmark_test.py	121	# Example usage	COMMENT

Analysis Overview

What These Metrics Mean

Score History

Severity Breakdown

Directory Score Breakdown

Pattern Findings