Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server.
This report summarizes scanner evidence for zylon-ai/private-gpt, a Python project with 57,565 GitHub stars. SynthScan examined 200,046 lines of code across 941 source files, recording 3658 pattern matches distributed across 20 syntactic categories. The legacy adjusted pattern signal is 23.6 (Elevated pattern signal); it is not an authorship estimate.
Use the findings to ask whether maintainers can explain intent, verify dependencies, simplify unnecessary scaffolding, and focus review effort. Risk Payload v1 adds ownership, supply-chain, over-engineering, and review-effort vectors when available. These are prompts for human verification, not probabilities, security findings, or measured maintenance costs.
Use each vector to guide manual verification of the underlying findings.
Can maintainers explain intent, assumptions, and trade-offs? 2338 finding(s).
Are imports declared and package/API names verified? 480 finding(s).
Are wrappers, guards, and repeated structures necessary? 2881 finding(s).
Which changes need focused human review? 3658 finding(s).
This chart tracks the legacy adjusted pattern score across scan runs. Changes can reflect source changes, scan coverage, or detector/scoring versions; they do not measure AI adoption or prove that a team refactored code. Compare runs only when their scoring versions are compatible. The dashed line tracks the raw pattern-hit count.
Groups findings by configured severity weight. Severity is not a confidence estimate, security rating, or proof that a package is missing. Verify imports against the project's manifests and inspect each finding in its local design context.
This horizontal bar chart shows where configured pattern scores accumulate across directories. Treat the bars as locations to inspect, not as evidence of authorship or code quality. Use the file-level findings to decide whether a directory needs a focused ownership, dependency, complexity, or review check.
The scanner identified 3658 distinct pattern matches across 20 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. 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 configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | ui/index.html | 4367 | function appearanceBriefHasContent(prefix) { | CODE |
| LOW | ui/index.html | 4806 | function setAppearanceGeneratorStatus(prefix, message = "") { | CODE |
| LOW | ui/index.html | 4816 | function appearanceGeneratorPrompt(brief) { | CODE |
| LOW | ui/index.html | 4863 | function normalizeAppearanceSuggestion(candidate, fallbackBrief = "") { | CODE |
| LOW | ui/index.html | 4940 | function onboardingErrorToastMessage(check, fallback) { | CODE |
| LOW | ui/index.html | 5313 | function normalizeDocumentBackedSettings(chat) { | CODE |
| LOW | ui/index.html | 5333 | function normalizeChatContextSelections() { | CODE |
| LOW | ui/index.html | 5784 | function normalizeCodeExecToolName(name) { | CODE |
| LOW | ui/index.html | 6204 | function collectToolResultCitationSources(content, context) { | CODE |
| LOW | ui/index.html | 6253 | function renderMarkdownWithCitations(text, citationContext, explicitCitations = []) { | CODE |
| LOW | ui/index.html | 6439 | function parseMarkdownTableAlignments(line) { | CODE |
| LOW | ui/index.html | 7610 | function openProductionNoticeModal() { | CODE |
| LOW | ui/index.html | 7689 | function readSettingsConnectionForm() { | CODE |
| LOW | ui/index.html | 7704 | function readOnboardingConnectionForm() { | CODE |
| LOW | ui/index.html | 7735 | function saveAppearanceSettingsFrom(prefix) { | CODE |
| LOW | ui/index.html | 7811 | async function generateAppearanceFromBrief(prefix) { | CODE |
| LOW | private_gpt/initialize.py | 22 | def download_nltk_package_if_not_present( | CODE |
| LOW | private_gpt/initialize.py | 49 | def unzip_download_nltk_package_if_not_present( | CODE |
| LOW | private_gpt/initialize.py | 118 | def _initialize_arize_phoenix(settings: "Settings") -> None: | CODE |
| LOW | private_gpt/di.py | 32 | def create_application_injector() -> Injector: | CODE |
| LOW | private_gpt/di.py | 48 | def discard_inherited_injectors(loop: AbstractEventLoop | None = None) -> None: | CODE |
| LOW | private_gpt/global_handler.py | 53 | async def request_validation_exception_handler( | CODE |
| LOW | private_gpt/global_handler.py | 67 | async def request_validation_exception_adapter( | CODE |
| LOW | private_gpt/launcher.py | 172 | async def inject_injector_middleware(request: Request, call_next: Any) -> Any: | CODE |
| LOW | private_gpt/settings/settings_loader.py | 49 | def load_settings_from_profile(profile: str) -> dict[str, Any]: | CODE |
| LOW | private_gpt/settings/settings_loader.py | 81 | def discover_models_from_environment( | CODE |
| LOW | private_gpt/settings/settings.py | 1256 | def url_with_default_database(self) -> str: | CODE |
| LOW | private_gpt/settings/settings.py | 1273 | def empty_redis_database_is_none(cls, value: Any) -> Any: | CODE |
| LOW | private_gpt/settings/settings.py | 2009 | def split_comma_separated_lists(cls, value: object) -> object: | CODE |
| LOW | private_gpt/settings/settings.py | 2191 | def validate_chat_scheduler_configuration(self) -> "Settings": | CODE |
| LOW | private_gpt/chat/input_models.py | 380 | def convert_from_llama_index_messages( | CODE |
| LOW | private_gpt/chat/input_models.py | 458 | def _standalone_server_tool_messages( | CODE |
| LOW | private_gpt/chat/input_models.py | 920 | def _convert_into_llama_index_messages( | CODE |
| LOW | private_gpt/chat/input_models.py | 1009 | def _convert_assistant_message( | CODE |
| LOW | private_gpt/chat/input_models.py | 1272 | def __get_pydantic_json_schema__(cls, core_schema: Any, handler: Any) -> Any: | CODE |
| LOW | private_gpt/chat/schema_models.py | 52 | def _handle_leading_underscores(field_name: str) -> str: | CODE |
| LOW | private_gpt/chat/schema_models.py | 68 | def _handle_reserved_basemodel_attributes(field_name: str) -> str: | CODE |
| LOW | private_gpt/chat/schema_models.py | 84 | def _validate_json_schema_item(schema: dict[str, Any], strict: bool = True) -> None: | CODE |
| LOW | private_gpt/chat/schema_models.py | 160 | def _resolve_field_name_collisions(field_name: str, used_names: set[str]) -> str: | CODE |
| LOW | private_gpt/chat/schema_models.py | 377 | def create_model_from_json_schema( | CODE |
| LOW | private_gpt/artifact_index/base_artifact_index.py | 587 | async def _aget_node_with_embedding( | CODE |
| LOW | private_gpt/artifact_index/base_artifact_index.py | 650 | async def _aget_node_with_embedding( | CODE |
| LOW | private_gpt/server/tools/tool_service.py | 55 | async def build_semantic_search_tool( | CODE |
| LOW | private_gpt/server/tools/tool_service.py | 67 | async def build_tabular_data_analysis_tool( | CODE |
| LOW | private_gpt/server/tools/tool_service.py | 75 | async def build_database_query_tool( | CODE |
| LOW | private_gpt/server/tools/tool_service.py | 129 | async def tabular_data_analysis_tool( | CODE |
| LOW | private_gpt/server/chat/chat_models.py | 260 | def __get_pydantic_json_schema__(cls, core_schema: Any, handler: Any) -> Any: | CODE |
| LOW | private_gpt/server/chat/chat_facade.py | 27 | async def create_chat_event_generator( | CODE |
| LOW | private_gpt/server/chat/chat_request_mapper.py | 98 | async def _configure_output_cls_from_json_schema( | CODE |
| LOW | …server/chat/interceptors/loop_detection_interceptor.py | 92 | def _messages_since_last_user(messages: list[ChatMessage]) -> list[ChatMessage]: | CODE |
| LOW | …gpt/server/chat/interceptors/multimodal_interceptor.py | 117 | def resolve_multimodal_models( | CODE |
| LOW | …t/server/chat/interceptors/condensation_interceptor.py | 201 | async def _consume_and_emit_with_min_duration( | CODE |
| LOW⚡ | …r/chat/interceptors/platform_guidelines_interceptor.py | 109 | def _inject_tool_instructions( | CODE |
| LOW⚡ | …r/chat/interceptors/platform_guidelines_interceptor.py | 216 | def _has_skill_management_tool(tools: list[ToolSpec]) -> bool: | CODE |
| LOW⚡ | …r/chat/interceptors/platform_guidelines_interceptor.py | 233 | def _get_citation_guidelines_content( | CODE |
| LOW | …pt/server/chat/interceptors/skills_loop_interceptor.py | 47 | def _parse_tool_result_content(content: str | None) -> dict[str, Any] | None: | CODE |
| LOW | …pt/server/chat/interceptors/skills_loop_interceptor.py | 200 | def _resolve_active_skill_names( | CODE |
| LOW | private_gpt/server/chat/interceptors/mcp_interceptor.py | 63 | def _extract_original_exception(exc: BaseException) -> BaseException: | CODE |
| LOW | private_gpt/server/chat/interceptors/mcp_interceptor.py | 83 | def _pop_token_refresh_payload( | CODE |
| LOW | private_gpt/server/chat/interceptors/mcp_interceptor.py | 192 | def _extract_token_refresh_payloads( | CODE |
| 1951 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM⚡ | pyproject.toml | 57 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 59 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 69 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 71 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 82 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 84 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 94 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 96 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 164 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 166 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 176 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 178 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 220 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 222 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 231 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 233 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 294 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 296 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 301 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | pyproject.toml | 303 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | pyproject.toml | 32 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | pyproject.toml | 34 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | pyproject.toml | 134 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | pyproject.toml | 136 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | pyproject.toml | 148 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | pyproject.toml | 150 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | pyproject.toml | 206 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | pyproject.toml | 208 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | pyproject.toml | 250 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | pyproject.toml | 252 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | pyproject.toml | 278 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | pyproject.toml | 280 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM⚡ | …r/chat/interceptors/platform_guidelines_interceptor.py | 105 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | …r/chat/interceptors/platform_guidelines_interceptor.py | 107 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | …r/chat/interceptors/platform_guidelines_interceptor.py | 226 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | …r/chat/interceptors/platform_guidelines_interceptor.py | 228 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/server/files/file_service.py | 403 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/server/files/file_service.py | 405 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | private_gpt/components/ingestion/ingestion_scheduler.py | 120 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | private_gpt/components/ingestion/ingestion_scheduler.py | 122 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | private_gpt/components/ingestion/ingestion_scheduler.py | 131 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM⚡ | private_gpt/components/ingestion/ingestion_scheduler.py | 133 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 75 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 77 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 89 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 91 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 103 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 105 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 147 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 149 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 270 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 272 | # --------------------------------------------------------------------------- | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 290 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 292 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 352 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 354 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 417 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 419 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 566 | # ------------------------------------------------------------------ | COMMENT |
| MEDIUM | private_gpt/components/ingestion/ingestion_scheduler.py | 568 | # ------------------------------------------------------------------ | COMMENT |
| 270 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | private_gpt/global_handler.py | 39 | except Exception as exc: | CODE |
| LOW | private_gpt/chat/input_models.py | 194 | except Exception as e: | CODE |
| LOW | private_gpt/chat/input_models.py | 211 | except Exception as e: | CODE |
| LOW | private_gpt/chat/input_models.py | 1212 | except Exception as e: | CODE |
| LOW | private_gpt/server/tools/tool_service.py | 122 | except Exception as e: | CODE |
| LOW | private_gpt/server/tools/tool_service.py | 158 | except Exception as e: | CODE |
| LOW | private_gpt/server/tools/tool_service.py | 190 | except Exception as e: | CODE |
| LOW | private_gpt/server/tools/tool_service.py | 212 | except Exception as e: | CODE |
| LOW | private_gpt/server/tools/tool_service.py | 233 | except Exception as e: | CODE |
| LOW | private_gpt/server/chat/chat_service.py | 271 | except Exception as e: | CODE |
| LOW | private_gpt/server/chat/chat_service.py | 282 | except Exception as e: | CODE |
| LOW | …server/chat/interceptors/loop_detection_interceptor.py | 133 | except Exception: | CODE |
| LOW | …/server/chat/interceptors/document_file_interceptor.py | 93 | except Exception as exc: | CODE |
| LOW | …gpt/server/chat/interceptors/multimodal_interceptor.py | 106 | except Exception as exc: | CODE |
| LOW | …t/server/chat/interceptors/condensation_interceptor.py | 120 | except Exception as e: | CODE |
| LOW | …t/server/chat/interceptors/condensation_interceptor.py | 189 | except Exception as e: | CODE |
| LOW | …t/server/chat/interceptors/condensation_interceptor.py | 315 | except Exception as e: | CODE |
| LOW | …pt/server/chat/interceptors/skills_loop_interceptor.py | 344 | except Exception as exc: | CODE |
| LOW | private_gpt/server/chat/interceptors/mcp_interceptor.py | 284 | except Exception as e: | CODE |
| LOW | private_gpt/server/chat/interceptors/mcp_interceptor.py | 348 | except Exception as e: | CODE |
| LOW | …/chat/interceptors/schema_coercing_tool_interceptor.py | 419 | except Exception as e: | CODE |
| LOW | …ver/chat/interceptors/skills_validation_interceptor.py | 56 | except Exception: | CODE |
| LOW | private_gpt/server/ingest/convert_service.py | 113 | except Exception as e: | CODE |
| LOW | private_gpt/server/ingest/ingest_service.py | 148 | except Exception as e: | CODE |
| LOW | private_gpt/server/ingest/ingest_service.py | 220 | except Exception as e: | CODE |
| LOW | private_gpt/server/ingest/uri_loader.py | 87 | except Exception: | CODE |
| LOW | private_gpt/server/chat_async/chat_async_facade.py | 95 | except Exception as cleanup_error: | CODE |
| LOW | private_gpt/server/utils/artifact_input.py | 30 | except Exception: | CODE |
| LOW | private_gpt/server/utils/artifact_input.py | 39 | except Exception: | CODE |
| LOW | private_gpt/server/utils/artifact_input.py | 99 | except Exception: | CODE |
| LOW | private_gpt/server/mcp/_runtime.py | 289 | except Exception: | CODE |
| LOW | private_gpt/server/mcp/_runtime.py | 336 | except Exception as e: | CODE |
| LOW | private_gpt/server/mcp/_runtime.py | 352 | except Exception as e: | CODE |
| LOW | private_gpt/server/mcp/_runtime.py | 381 | except Exception as e: | CODE |
| LOW | private_gpt/server/mcp/_runtime.py | 392 | except Exception as e: | CODE |
| MEDIUM | private_gpt/server/mcp/_runtime.py | 377 | def health_check(self) -> bool: | CODE |
| LOW | private_gpt/server/files/file_service.py | 43 | except Exception: | CODE |
| LOW | private_gpt/server/files/file_service.py | 59 | except Exception as e: | CODE |
| LOW | private_gpt/server/skills/skills_files.py | 177 | except Exception as exc: | CODE |
| LOW | private_gpt/utils/async_utils.py | 67 | except Exception as e: | CODE |
| LOW | private_gpt/utils/async_utils.py | 86 | except Exception as e: | CODE |
| LOW | private_gpt/utils/async_utils.py | 93 | except Exception as e: | CODE |
| LOW | private_gpt/utils/pool.py | 55 | except Exception: | CODE |
| LOW | private_gpt/utils/pool.py | 104 | except Exception as e: | CODE |
| LOW | private_gpt/utils/pool.py | 153 | except Exception: | CODE |
| LOW | private_gpt/utils/pool.py | 202 | except Exception as e: | CODE |
| LOW | private_gpt/cli/commands/run.py | 40 | except Exception: | CODE |
| LOW | private_gpt/cli/commands/run.py | 114 | except Exception: | CODE |
| LOW | private_gpt/components/database/procedure_inspector.py | 118 | except Exception: | STRING |
| LOW | private_gpt/components/database/procedure_inspector.py | 206 | except Exception: | STRING |
| LOW | private_gpt/components/database/procedure_inspector.py | 288 | except Exception: | STRING |
| LOW | private_gpt/components/database/table_like_inspector.py | 96 | except Exception: | CODE |
| LOW | private_gpt/components/database/table_like_inspector.py | 109 | except Exception: | CODE |
| LOW | private_gpt/components/database/table_like_inspector.py | 132 | except Exception: | CODE |
| LOW | private_gpt/components/database/table_like_inspector.py | 142 | except Exception: | CODE |
| LOW | private_gpt/components/database/function_inspector.py | 119 | except Exception: | STRING |
| LOW | private_gpt/components/database/function_inspector.py | 206 | except Exception: | STRING |
| LOW | private_gpt/components/database/function_inspector.py | 297 | except Exception: | STRING |
| LOW | private_gpt/components/ingestion/ingestion_scheduler.py | 643 | except Exception: | CODE |
| LOW | private_gpt/components/tools/binary_block_decorators.py | 68 | except Exception as e: | CODE |
| 203 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | private_gpt/context/__init__.py | 1 | CODE | |
| LOW | private_gpt/context/__init__.py | 1 | CODE | |
| LOW | private_gpt/context/__init__.py | 1 | CODE | |
| LOW | private_gpt/context/__init__.py | 1 | CODE | |
| LOW | private_gpt/context/__init__.py | 1 | CODE | |
| LOW | private_gpt/context/__init__.py | 1 | CODE | |
| LOW | private_gpt/context/context_propagation.py | 28 | CODE | |
| LOW | private_gpt/server/principal.py | 1 | CODE | |
| LOW | …rver/chat/interceptors/null_tool_values_interceptor.py | 1 | CODE | |
| LOW | …at/interceptors/server_tool_result_text_interceptor.py | 1 | CODE | |
| LOW | …/chat/interceptors/required_tool_params_interceptor.py | 1 | CODE | |
| LOW | …/chat/interceptors/schema_coercing_tool_interceptor.py | 1 | CODE | |
| LOW | …t/server/chat/interceptors/preprocessing_tool_calls.py | 11 | CODE | |
| LOW | …t/server/chat/interceptors/preprocessing_tool_calls.py | 39 | CODE | |
| LOW | private_gpt/server/mcp/mcp_service.py | 19 | CODE | |
| LOW | private_gpt/server/mcp/_runtime.py | 17 | CODE | |
| LOW | private_gpt/server/mcp/_runtime.py | 17 | CODE | |
| LOW | private_gpt/server/mcp/_runtime.py | 17 | CODE | |
| LOW | private_gpt/server/mcp/_runtime.py | 39 | CODE | |
| LOW | private_gpt/server/mcp/_runtime.py | 39 | CODE | |
| LOW | private_gpt/server/mcp/_runtime.py | 39 | CODE | |
| LOW | private_gpt/server/files/file_service.py | 1 | CODE | |
| LOW | private_gpt/server/files/file_models.py | 1 | CODE | |
| LOW | private_gpt/utils/mime.py | 3 | CODE | |
| LOW | private_gpt/utils/runner.py | 1 | CODE | |
| LOW | private_gpt/cli/main.py | 10 | CODE | |
| LOW | private_gpt/components/container_registry.py | 1 | CODE | |
| LOW | private_gpt/components/ingestion/ingestion_scheduler.py | 1 | CODE | |
| LOW | private_gpt/components/tools/tool_execution_context.py | 19 | CODE | |
| LOW | private_gpt/components/tools/tool_scheduler.py | 1 | CODE | |
| LOW | private_gpt/components/tools/remote_execution.py | 1 | CODE | |
| LOW | …ls/builders/text_editor_code_execution_tool_builder.py | 1 | CODE | |
| LOW | …ate_gpt/components/tools/builders/bash_tool_builder.py | 1 | CODE | |
| LOW | …mponents/tools/builders/present_server_tool_builder.py | 1 | CODE | |
| LOW | …/components/tools/builders/text_editor_tool_builder.py | 1 | CODE | |
| LOW | …omponents/tools/builders/present_files_tool_builder.py | 1 | CODE | |
| LOW | private_gpt/components/tools/events/registry.py | 1 | CODE | |
| LOW | private_gpt/components/tools/events/__init__.py | 1 | CODE | |
| LOW | private_gpt/components/tools/events/__init__.py | 2 | CODE | |
| LOW | private_gpt/components/tools/events/__init__.py | 2 | CODE | |
| LOW | private_gpt/components/tools/events/adapters.py | 1 | CODE | |
| LOW | private_gpt/components/llm/discovery.py | 1 | CODE | |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 16 | CODE | |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 21 | CODE | |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 21 | CODE | |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 21 | CODE | |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 21 | CODE | |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 21 | CODE | |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 21 | CODE | |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 21 | CODE | |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 30 | CODE | |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 35 | CODE | |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 40 | CODE | |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 40 | CODE | |
| LOW | …t/components/llm/tokenizers/models/model_downloader.py | 1 | CODE | |
| LOW | …pt/components/llm/tokenizers/models/model_discovery.py | 1 | CODE | |
| LOW | …te_gpt/components/llm/text_parsers/text_parser_base.py | 1 | CODE | |
| LOW | …gpt/components/llm/text_parsers/harmony_text_parser.py | 1 | CODE | |
| LOW | private_gpt/components/llm/custom/sagemaker.py | 2 | CODE | |
| LOW | private_gpt/components/context/services/__init__.py | 3 | CODE | |
| 177 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | private_gpt/eager_loading.py | 28 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/initialize.py | 19 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/di.py | 26 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/di.py | 105 | def set_injector(injector: Injector) -> None: | CODE |
| LOW | private_gpt/di.py | 151 | def set_global_injector(injector: Injector) -> None: | CODE |
| LOW | private_gpt/docs.py | 42 | def update_refs(obj: Any) -> None: | CODE |
| LOW | private_gpt/global_handler.py | 13 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/launcher.py | 53 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/settings/settings_loader.py | 15 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/context/__init__.py | 10 | __all__ = [ | CODE |
| LOW | private_gpt/artifact_index/vector_artifact_index.py | 29 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/artifact_index/base_artifact_index.py | 35 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/server/tools/tool_service.py | 23 | logger = logging.getLogger(__name__) | CODE |
| LOW | …server/chat/interceptors/loop_detection_interceptor.py | 23 | logger = logging.getLogger(__name__) | CODE |
| LOW | …/server/chat/interceptors/document_file_interceptor.py | 25 | logger = logging.getLogger(__name__) | CODE |
| LOW | …gpt/server/chat/interceptors/multimodal_interceptor.py | 33 | logger = logging.getLogger(__name__) | CODE |
| LOW | …t/server/chat/interceptors/condensation_interceptor.py | 35 | logger = logging.getLogger(__name__) | CODE |
| LOW | …r/chat/interceptors/platform_guidelines_interceptor.py | 32 | logger = logging.getLogger(__name__) | CODE |
| LOW | …server/chat/interceptors/default_values_interceptor.py | 17 | logger = logging.getLogger(__name__) | CODE |
| LOW | …pt/server/chat/interceptors/skills_loop_interceptor.py | 42 | logger = logging.getLogger(__name__) | CODE |
| LOW | …/chat/interceptors/schema_coercing_tool_interceptor.py | 28 | logger = logging.getLogger(__name__) | CODE |
| LOW | …t/server/chat/interceptors/preprocessing_tool_calls.py | 45 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/server/ingest/convert_service.py | 18 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/server/ingest/ingest_router.py | 29 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/server/ingest/ingest_service.py | 27 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/server/chat_async/chat_async_facade.py | 16 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/server/utils/auth.py | 37 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/server/mcp/_runtime.py | 47 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/server/mcp/_runtime.py | 50 | __all__ = [ | CODE |
| LOW | private_gpt/server/mcp/_runtime.py | 106 | async def set_tokens(self, tokens: OAuthToken) -> None: | CODE |
| LOW | private_gpt/server/mcp/_runtime.py | 121 | async def set_client_info(self, client_info: OAuthClientInformationFull) -> None: | CODE |
| LOW | private_gpt/utils/time.py | 13 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/utils/concurrency.py | 7 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/utils/eta.py | 8 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/cli/commands/serve.py | 12 | logger = logging.getLogger(__name__) | CODE |
| LOW | …vate_gpt/components/node_store/node_store_component.py | 25 | logger = logging.getLogger(__name__) | CODE |
| LOW | …gpt/components/node_store/patched_postgres_kv_store.py | 10 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/components/ingestion/ingestion_scheduler.py | 28 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/components/tools/binary_block_decorators.py | 18 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/components/tools/tool_scheduler.py | 35 | logger = logging.getLogger(__name__) | CODE |
| LOW⚡ | private_gpt/components/tools/remote_execution.py | 120 | def set_tool_kwargs(self, tool_kwargs: dict[str, Any]) -> None: | CODE |
| LOW⚡ | private_gpt/components/tools/remote_execution.py | 123 | def set_response(self, response: ToolExecutionResponse) -> None: | CODE |
| LOW | …pt/components/tools/builders/database_query_builder.py | 42 | logger = logging.getLogger(__name__) | CODE |
| LOW | …/components/tools/processors/tabular_data_processor.py | 19 | logger = logging.getLogger(__name__) | CODE |
| LOW | …ols/processors/anthropic_tool_translation_processor.py | 20 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/components/tools/events/__init__.py | 7 | __all__ = [ | CODE |
| LOW | private_gpt/components/llm/llm_component.py | 26 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/components/llm/discovery.py | 31 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/components/llm/prompt_helper.py | 8 | logger = logging.getLogger(__name__) | CODE |
| LOW | private_gpt/components/llm/tokenizers/mistral.py | 48 | logger = logging.getLogger(__name__) | CODE |
| LOW | …ivate_gpt/components/llm/tokenizers/models/__init__.py | 45 | __all__ = [ | CODE |
| LOW | …t/components/llm/tokenizers/models/model_downloader.py | 12 | logger = logging.getLogger(__name__) | CODE |
| LOW | …pt/components/llm/tokenizers/models/model_discovery.py | 30 | logger = logging.getLogger(__name__) | CODE |
| LOW | …gpt/components/llm/tokenizers/models/auto_discovery.py | 10 | logger = logging.getLogger(__name__) | CODE |
| LOW⚡ | …te_gpt/components/llm/tokenizers/models/model_cache.py | 12 | logger = logging.getLogger(__name__) | CODE |
| LOW⚡ | …te_gpt/components/llm/tokenizers/models/model_cache.py | 261 | def set_model_permissions(path: Path) -> None: | CODE |
| LOW | private_gpt/components/llm/prompt_styles/__init__.py | 1 | __all__ = [ | CODE |
| LOW | …onents/llm/prompt_styles/chat_template_prompt_style.py | 24 | logger = logging.getLogger(__name__) | CODE |
| LOW | …_gpt/components/llm/prompt_styles/prompt_style_base.py | 16 | logger = logging.getLogger(__name__) | CODE |
| LOW | …gpt/components/llm/text_parsers/harmony_text_parser.py | 33 | logger = logging.getLogger(__name__) | CODE |
| 157 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | private_gpt/settings/settings.py | 1327 | image_mode: Literal["embedded", "placeholder"] = Field( | CODE |
| LOW | private_gpt/settings/settings.py | 1328 | "placeholder", | CODE |
| LOW | private_gpt/server/ingest/convert_router.py | 34 | {"file_name": "document.docx", "author": "John Doe"}, | CODE |
| LOW | private_gpt/server/ingest/ingest_router.py | 113 | "author": "John Doe", | CODE |
| LOW | private_gpt/components/chunk/models.py | 85 | "author": "John Doe", | CODE |
| LOW⚡ | tests/server/chat/test_schema_models.py | 1123 | instance = model.model_validate({"name": "John Doe"}) | CODE |
| LOW⚡ | tests/server/chat/test_schema_models.py | 1124 | assert instance.name == "John Doe" | CODE |
| LOW | tests/server/chat/test_schema_models.py | 228 | "name": "John Doe", | CODE |
| LOW | tests/server/chat/test_schema_models.py | 1583 | "street": "123 Main St", | CODE |
| LOW⚡ | tests/server/chat/test_chat_routes.py | 62 | tool_kwargs={"query": "Lorem ipsum dolor sit amet"}, | CODE |
| LOW⚡ | tests/server/chat/test_chat_routes.py | 62 | tool_kwargs={"query": "Lorem ipsum dolor sit amet"}, | CODE |
| LOW⚡ | tests/server/chat/test_chat_routes.py | 66 | "Lorem ipsum dolor sit amet", | CODE |
| LOW⚡ | tests/server/chat/test_chat_routes.py | 66 | "Lorem ipsum dolor sit amet", | CODE |
| LOW⚡ | tests/server/chat/test_chat_routes.py | 1790 | tool_kwargs={"_query": "Lorem ipsum dolor sit amet"}, | CODE |
| LOW⚡ | tests/server/chat/test_chat_routes.py | 1790 | tool_kwargs={"_query": "Lorem ipsum dolor sit amet"}, | CODE |
| LOW⚡ | tests/server/chat/test_chat_routes.py | 2569 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW⚡ | tests/server/chat/test_chat_routes.py | 2569 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW⚡ | tests/server/chat/test_chat_routes.py | 2579 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 167 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 167 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 181 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 228 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 254 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 298 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 335 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 335 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 349 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 397 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 451 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 451 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 467 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 467 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 486 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 556 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 556 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 573 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 573 | "value": "Lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 593 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 642 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 682 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 2354 | tool_kwargs={"_query": "Lorem ipsum dolor sit amet"}, | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 2354 | tool_kwargs={"_query": "Lorem ipsum dolor sit amet"}, | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 2395 | tool_kwargs={"query": "Lorem ipsum dolor sit amet"}, | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 2395 | tool_kwargs={"query": "Lorem ipsum dolor sit amet"}, | CODE |
| LOW | tests/server/chat/test_chat_routes.py | 2530 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 688 | "input": {"type": "text", "value": "Lorem ipsum dolor sit amet"}, | CODE |
| LOW⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 688 | "input": {"type": "text", "value": "Lorem ipsum dolor sit amet"}, | CODE |
| LOW⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 696 | messages=[MessageInput(content="Lorem ipsum", role="user")], | CODE |
| LOW⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 722 | assert "Lorem ipsum dolor sit amet" not in capture.system_prompts[0] | CODE |
| LOW⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 722 | assert "Lorem ipsum dolor sit amet" not in capture.system_prompts[0] | CODE |
| LOW⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 723 | assert capture.system_prompts[1].count("Lorem ipsum dolor sit amet") == 1 | CODE |
| LOW⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 723 | assert capture.system_prompts[1].count("Lorem ipsum dolor sit amet") == 1 | CODE |
| LOW⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 917 | "WORKERDOC lorem ipsum dolor sit amet" not in capture.system_prompts[0] | CODE |
| LOW⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 917 | "WORKERDOC lorem ipsum dolor sit amet" not in capture.system_prompts[0] | CODE |
| LOW⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 920 | capture.system_prompts[1].count("WORKERDOC lorem ipsum dolor sit amet") | CODE |
| LOW⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 920 | capture.system_prompts[1].count("WORKERDOC lorem ipsum dolor sit amet") | CODE |
| LOW⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 942 | mock_llm = get_mock_function_calling_llm(["placeholder"]) | CODE |
| LOW | tests/server/chat/test_chat_lifecycle_e2e.py | 749 | mock_llm = get_mock_function_calling_llm(["placeholder"]) | CODE |
| LOW | tests/server/chat/test_chat_lifecycle_e2e.py | 887 | "value": "WORKERDOC lorem ipsum dolor sit amet", | CODE |
| LOW | tests/server/chat/test_chat_lifecycle_e2e.py | 887 | "value": "WORKERDOC lorem ipsum dolor sit amet", | CODE |
| 173 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | private_gpt/di.py | 61 | CODE | |
| LOW | private_gpt/di.py | 121 | CODE | |
| LOW | private_gpt/docs.py | 12 | CODE | |
| LOW | private_gpt/docs.py | 16 | CODE | |
| LOW | private_gpt/docs.py | 61 | CODE | |
| LOW | private_gpt/docs.py | 42 | CODE | |
| LOW | private_gpt/chat/input_models.py | 165 | CODE | |
| LOW | private_gpt/chat/input_models.py | 406 | CODE | |
| LOW | private_gpt/chat/input_models.py | 458 | CODE | |
| LOW | private_gpt/chat/input_models.py | 500 | CODE | |
| LOW | private_gpt/chat/input_models.py | 553 | CODE | |
| LOW | private_gpt/chat/input_models.py | 651 | CODE | |
| LOW | private_gpt/chat/input_models.py | 671 | CODE | |
| LOW | private_gpt/chat/input_models.py | 718 | CODE | |
| LOW | private_gpt/chat/input_models.py | 935 | CODE | |
| LOW | private_gpt/chat/input_models.py | 1009 | CODE | |
| LOW | private_gpt/chat/input_models.py | 1286 | CODE | |
| LOW | private_gpt/chat/input_models.py | 1334 | CODE | |
| LOW | private_gpt/artifact_index/base_artifact_index.py | 288 | CODE | |
| LOW | private_gpt/server/chat/chat_models.py | 287 | CODE | |
| LOW | …/server/chat/interceptors/document_file_interceptor.py | 42 | CODE | |
| LOW | …gpt/server/chat/interceptors/multimodal_interceptor.py | 48 | CODE | |
| LOW | …t/server/chat/interceptors/condensation_interceptor.py | 50 | CODE | |
| LOW | …at/interceptors/server_tool_result_text_interceptor.py | 49 | CODE | |
| LOW | …pt/server/chat/interceptors/skills_loop_interceptor.py | 138 | CODE | |
| LOW | private_gpt/server/chat/interceptors/mcp_interceptor.py | 225 | CODE | |
| LOW | …/chat/interceptors/schema_coercing_tool_interceptor.py | 88 | CODE | |
| LOW | …/chat/interceptors/schema_coercing_tool_interceptor.py | 240 | CODE | |
| LOW | …/chat/interceptors/schema_coercing_tool_interceptor.py | 300 | CODE | |
| LOW | …/chat/interceptors/schema_coercing_tool_interceptor.py | 365 | CODE | |
| LOW | …rver/chat/interceptors/extract_citation_interceptor.py | 71 | CODE | |
| LOW | private_gpt/server/ingest/convert_service.py | 100 | CODE | |
| LOW | private_gpt/server/ingest/ingest_service.py | 127 | CODE | |
| LOW | private_gpt/server/content/content_service.py | 168 | CODE | |
| LOW | private_gpt/server/mcp/_runtime.py | 237 | CODE | |
| LOW | private_gpt/utils/async_utils.py | 25 | CODE | |
| LOW | private_gpt/utils/tokens.py | 67 | CODE | |
| LOW | private_gpt/utils/tokens.py | 94 | CODE | |
| LOW | private_gpt/utils/tokens.py | 105 | CODE | |
| LOW | private_gpt/utils/batches.py | 17 | CODE | |
| LOW | private_gpt/utils/batches.py | 58 | CODE | |
| LOW | private_gpt/components/database/procedure_inspector.py | 33 | CODE | |
| LOW | private_gpt/components/database/procedure_inspector.py | 122 | CODE | |
| LOW | private_gpt/components/database/procedure_inspector.py | 210 | CODE | |
| LOW | private_gpt/components/database/function_inspector.py | 34 | CODE | |
| LOW | private_gpt/components/database/function_inspector.py | 123 | CODE | |
| LOW | private_gpt/components/database/function_inspector.py | 210 | CODE | |
| LOW | …t/components/tools/builders/semantic_search_builder.py | 216 | CODE | |
| LOW | …t/components/tools/builders/semantic_search_builder.py | 238 | CODE | |
| LOW | …ls/builders/text_editor_code_execution_tool_builder.py | 48 | CODE | |
| LOW | …ls/builders/text_editor_code_execution_tool_builder.py | 67 | CODE | |
| LOW | …pt/components/tools/builders/database_query_builder.py | 241 | CODE | |
| LOW | …pt/components/tools/builders/database_query_builder.py | 299 | CODE | |
| LOW | …_gpt/components/tools/builders/tabular_data_builder.py | 250 | CODE | |
| LOW | …_gpt/components/tools/builders/tabular_data_builder.py | 269 | CODE | |
| LOW | …t/components/tools/processors/text_editor_processor.py | 43 | CODE | |
| LOW | …ponents/tools/processors/skill_management_processor.py | 57 | CODE | |
| LOW | private_gpt/components/llm/llm_component.py | 184 | CODE | |
| LOW | private_gpt/components/llm/tokenizers/mistral.py | 68 | CODE | |
| LOW | private_gpt/components/llm/tokenizers/mistral.py | 109 | CODE | |
| 103 more matches not shown… | ||||
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | private_gpt/chat/schema_models.py | 450 | # Create the base dynamic model | COMMENT |
| MEDIUM | private_gpt/server/utils/auth.py | 53 | # Define a dummy authentication method that always returns True. | COMMENT |
| MEDIUM | private_gpt/utils/dataframe.py | 19 | # Create the header row and separator row | COMMENT |
| MEDIUM | private_gpt/utils/dataframe.py | 23 | # Create the data rows | COMMENT |
| MEDIUM⚡ | private_gpt/utils/random.py | 7 | # Create a namespace UUID (using namespace_dns as a random choice) | COMMENT |
| MEDIUM⚡ | private_gpt/utils/random.py | 10 | # Create a UUID using the input string within the namespace | COMMENT |
| MEDIUM | …expansion/tree_expansion_replacement_post_processor.py | 195 | # Create a linear range from min to max | COMMENT |
| MEDIUM | private_gpt/components/readers/nodes/tree_node.py | 501 | # Create a lookup dictionary for all nodes | COMMENT |
| MEDIUM | private_gpt/components/readers/nodes/tree_node.py | 538 | # Create a list of root nodes | COMMENT |
| MEDIUM | …e_gpt/components/readers/docling/docling_transforms.py | 43 | # Create a representation of images in text (if apply) | COMMENT |
| MEDIUM | …te_gpt/components/readers/pptx2md/slides_transforms.py | 69 | # Create a representation of images in text (if apply) | COMMENT |
| MEDIUM | tests/server/chat/anthropic/test_langchain_anthropic.py | 302 | # Create the Anthropic client with the mock HTTP client | COMMENT |
| MEDIUM | tests/components/web_search/test_brave_provider.py | 23 | # Create a minimal Settings object with web_search configuration | COMMENT |
| MEDIUM | tests/components/web_search/test_web_search_service.py | 24 | # Create a minimal Settings object with web_search configuration | COMMENT |
| MEDIUM | …s/components/llm/tokenizers/models/test_concurrency.py | 90 | # Create a cached model | COMMENT |
| MEDIUM | tests/components/llm/tokenizers/models/conftest.py | 108 | # Create the model in cache | COMMENT |
| MEDIUM | …components/postprocessor/test_prev_next_replacement.py | 41 | # Create a PrevNextReplacementPostProcessor instance | COMMENT |
| MEDIUM | …components/postprocessor/test_prev_next_replacement.py | 58 | # Create a set of 10 nodes with prev and next relations. | COMMENT |
| MEDIUM | …components/postprocessor/test_prev_next_replacement.py | 94 | # Create a PrevNextReplacementPostProcessor instance | COMMENT |
| MEDIUM | …sts/components/transforms/test_sentence_node_parser.py | 54 | # Create a root DocumentRoot node and a child TextNode. | COMMENT |
| MEDIUM⚡ | …sts/components/transforms/test_sentence_node_parser.py | 158 | # Create a long sentence that will exceed the 20-character chunk size. | STRING |
| MEDIUM⚡ | …sts/components/transforms/test_sentence_node_parser.py | 167 | # Create a DocumentRoot with a TextNode. | STRING |
| MEDIUM | tests/components/readers/nodes/test_node_structure.py | 28 | # Create a document tree with multiple node types | COMMENT |
| MEDIUM | tests/components/readers/nodes/test_node_structure.py | 39 | # Create a table | COMMENT |
| MEDIUM | tests/components/readers/nodes/test_node_structure.py | 70 | # Create a sample document tree | COMMENT |
| MEDIUM⚡ | tests/components/readers/nodes/test_node_structure.py | 96 | # Create a sample document tree | COMMENT |
| MEDIUM⚡ | tests/components/readers/nodes/test_node_structure.py | 99 | # Create a section | COMMENT |
| MEDIUM⚡ | tests/components/readers/nodes/test_node_structure.py | 106 | # Create a table | COMMENT |
| MEDIUM | tests/components/readers/nodes/test_node_structure.py | 137 | # Create a sample document tree | COMMENT |
| MEDIUM⚡ | tests/components/readers/nodes/test_node_structure.py | 179 | # Create a sample document tree | COMMENT |
| MEDIUM⚡ | tests/components/readers/nodes/test_node_structure.py | 182 | # Create a section | COMMENT |
| MEDIUM⚡ | tests/components/readers/nodes/test_node_structure.py | 189 | # Create a table | COMMENT |
| MEDIUM | tests/components/readers/nodes/test_node_structure.py | 263 | # Create a nested document tree | COMMENT |
| MEDIUM | tests/components/multimodality/test_describe_image.py | 42 | # Initialize parent class with only its expected parameters | COMMENT |
| MEDIUM | tests/components/multimodality/test_describe_image.py | 64 | # Create a minimal base64 encoded image (1x1 PNG) | COMMENT |
| MEDIUM | tests/components/multimodality/test_multimodality.py | 46 | # Initialize parent class with only its expected parameters | COMMENT |
| MEDIUM⚡ | tests/components/filesystems/test_path_resolver.py | 95 | # Create a symlink inside the namespace root pointing outside it | COMMENT |
| MEDIUM | tests/celery/test_base_task.py | 86 | # Create a mock request object | COMMENT |
| MEDIUM | tests/celery/test_notify.py | 50 | # Create a status class for testing | COMMENT |
| MEDIUM | tests/celery/test_notify.py | 81 | # Create a status class for testing | COMMENT |
| MEDIUM | tests/celery/test_notify.py | 170 | # Create a status class for testing | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | private_gpt/di.py | 141 | except RuntimeError: | CODE |
| HIGH | private_gpt/artifact_index/base_artifact_index.py | 129 | except ValueError: | CODE |
| HIGH | private_gpt/server/files/file_service.py | 253 | except ValueError: | CODE |
| HIGH | private_gpt/server/files/file_service.py | 261 | except ValueError: | CODE |
| HIGH | private_gpt/cli/commands/serve.py | 43 | except ProcessLookupError: | CODE |
| HIGH | private_gpt/components/database/table_like_inspector.py | 132 | except Exception: | CODE |
| HIGH | private_gpt/components/llm/tokenizers/registry.py | 70 | except (ImportError, Exception): | CODE |
| HIGH | private_gpt/components/llm/tokenizers/registry.py | 76 | except (ImportError, ValueError, Exception): | CODE |
| HIGH | private_gpt/components/llm/tokenizers/tiktoken.py | 47 | except (KeyError, ValueError): | CODE |
| HIGH | private_gpt/components/llm/tokenizers/tiktoken.py | 54 | except (KeyError, ValueError): | CODE |
| HIGH | private_gpt/components/model_discovery/client.py | 107 | except ValueError: | CODE |
| HIGH | private_gpt/components/ingest/ingest_helper.py | 75 | except (ValueError, TypeError): | CODE |
| HIGH | …onents/streaming/providers/in_memory_stream_service.py | 182 | except TimeoutError: | CODE |
| HIGH | …ivate_gpt/components/streaming/stream/stream_reader.py | 98 | except TimeoutError: | CODE |
| HIGH | …te_gpt/components/streaming/stream/stream_processor.py | 119 | except Exception: | CODE |
| HIGH | private_gpt/components/readers/nodes/node_print.py | 84 | except AttributeError: | CODE |
| HIGH | private_gpt/components/readers/nodes/table_node.py | 68 | except ValueError: | CODE |
| HIGH | …components/readers/pptx2md/convert_slide_into_image.py | 380 | except AttributeError: | CODE |
| HIGH | …components/readers/pptx2md/convert_slide_into_image.py | 386 | except AttributeError: | CODE |
| HIGH | …components/readers/pptx2md/convert_slide_into_image.py | 392 | except AttributeError: | CODE |
| HIGH | …components/readers/pptx2md/convert_slide_into_image.py | 398 | except AttributeError: | CODE |
| HIGH | private_gpt/components/code_execution/bash_executor.py | 105 | except ProcessLookupError: | CODE |
| HIGH | tests/sse/test_sse_manager.py | 89 | except ValueError: | CODE |
| HIGH | tests/components/environment/test_distributed.py | 57 | except TimeoutError: | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | private_gpt/chat/schema_models.py | 414 | # If the field already has None in its type (from anyOf with null), respect that | COMMENT |
| HIGH | …te_gpt/components/ingest/processors/df_preprocessor.py | 157 | if not with_first.equals(without_first): | CODE |
| HIGH | …ivate_gpt/components/streaming/stream/stream_reader.py | 479 | state.broadcast.push(events) | CODE |
| HIGH⚡ | …/interceptors/test_schema_coercing_tool_interceptor.py | 1258 | "anyOf [object, null] WITHOUT string: JSON string is parsed to dict", | CODE |
| HIGH⚡ | …/interceptors/test_schema_coercing_tool_interceptor.py | 1264 | "anyOf [string, null]: 'null' string -> null (null coercion still takes priority)", | CODE |
| HIGH⚡ | …/interceptors/test_schema_coercing_tool_interceptor.py | 1270 | "anyOf [string, null]: empty string -> null for nullable", | CODE |
| HIGH | …/interceptors/test_schema_coercing_tool_interceptor.py | 1448 | "parameters": '[42, "active", true, null]', | CODE |
| HIGH⚡ | tests/components/readers/nodes/test_table_nodes.py | 71 | assert deserialized.df.equals(valid_dataframe) | CODE |
| HIGH | tests/components/readers/nodes/test_table_nodes.py | 54 | assert node.df.equals(valid_dataframe) | CODE |
| HIGH | tests/components/readers/nodes/test_node_structure.py | 252 | assert table_obj.df.equals(table.df) | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | private_gpt/settings/settings.py | 358 | # Set max_workers to None if it is less than or equal to 0 | COMMENT |
| LOW | private_gpt/settings/settings.py | 1204 | # Check if visibility timeout is set when broker or backend is redis | COMMENT |
| LOW | private_gpt/chat/input_models.py | 804 | # Check if this TLDR group contains left-side TLDRs. | COMMENT |
| LOW | private_gpt/server/ingest/ingest_service.py | 81 | # Check if the vector index is initialized | COMMENT |
| LOW | private_gpt/server/ingest/ingest_service.py | 159 | # Check if the artifact index is initialized | COMMENT |
| LOW | private_gpt/server/ingest/ingest_service.py | 215 | # Check if the vector index is initialized | COMMENT |
| LOW⚡ | private_gpt/utils/random.py | 11 | # Set version to 4 for "random" UUID | COMMENT |
| LOW | private_gpt/components/llm/registry.py | 46 | # Check if any name is already registered | COMMENT |
| LOW | …vate_gpt/components/llm/decorators/reasoning_budget.py | 149 | # Check if reasoning_effort budget is enabled for this model | COMMENT |
| LOW | …vate_gpt/components/llm/decorators/reasoning_budget.py | 205 | # Check if reasoning_effort budget is enabled for this model | COMMENT |
| LOW | …vate_gpt/components/llm/decorators/reasoning_budget.py | 276 | # Check if reasoning_effort budget is enabled for this model | COMMENT |
| LOW | …vate_gpt/components/llm/decorators/reasoning_budget.py | 333 | # Check if reasoning_effort budget is enabled for this model | COMMENT |
| LOW | private_gpt/components/memory/trimming_memory.py | 212 | # Check if we need to preserve system message | COMMENT |
| LOW | …ents/chat/processors/chat_history/memory/tldr_utils.py | 90 | # Check if there's a next message and it's not a TLDR | COMMENT |
| LOW⚡ | private_gpt/components/ingest/utils.py | 261 | # Open the file and calculate the hash | COMMENT |
| LOW | private_gpt/components/ingest/ingest_helper.py | 30 | # Check if the file info has size | COMMENT |
| LOW | private_gpt/components/ingest/ingest_helper.py | 34 | # Check if the file info has a supported extension | COMMENT |
| LOW⚡ | private_gpt/components/ingest/ingest_helper.py | 59 | # Check if the file is too large | COMMENT |
| LOW⚡ | private_gpt/components/ingest/ingest_helper.py | 66 | # Check if there is any error | COMMENT |
| LOW⚡ | private_gpt/components/ingest/ingest_helper.py | 70 | # Check if the file has too many pages | COMMENT |
| LOW⚡ | private_gpt/components/ingest/ingest_helper.py | 78 | # Check if the file is special | COMMENT |
| LOW⚡ | private_gpt/components/ingest/ingest_helper.py | 88 | # Check if the file is encrypted. | COMMENT |
| LOW | …ransformations/make_continuation_markdown_transform.py | 98 | # Check if the current lines have an odd number of code block markers | COMMENT |
| LOW | …te_gpt/components/ingest/processors/df_preprocessor.py | 55 | # Check if enough values can be converted to numeric | COMMENT |
| LOW | …te_gpt/components/ingest/processors/df_preprocessor.py | 112 | # Check if conversion was successful for most values | COMMENT |
| LOW | …ents/postprocessor/tree_expansion/document_expander.py | 241 | # Check if node has been processed in all directions | COMMENT |
| LOW | …ents/postprocessor/tree_expansion/document_expander.py | 315 | # Check if adding this child would exceed token limit | COMMENT |
| LOW | private_gpt/components/embedding/registry.py | 35 | # Check if any name is already registered | COMMENT |
| LOW | private_gpt/components/engines/citations/format.py | 178 | # Check if adding this doc (and possibly its header) | COMMENT |
| LOW | private_gpt/components/engines/citations/utils.py | 243 | # Add citation to the list | COMMENT |
| LOW | private_gpt/components/readers/nodes/table_node.py | 59 | # Check if it's a number with decimal point | COMMENT |
| LOW⚡ | …components/readers/pptx2md/convert_slide_into_image.py | 881 | # Check if there are non-general zones (zone_id != 0) | COMMENT |
| LOW | private_gpt/celery/model.py | 96 | # Check if task is in progress, completed or failed | COMMENT |
| LOW | tests/server/ingest/test_ingest_routes.py | 185 | # Check if broker was called with the callback — the event type must use | COMMENT |
| LOW | tests/server/ingest/test_ingest_routes.py | 370 | # Check if broker was called with the callback | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | private_gpt/settings/settings_loader.py | 84 | Discover model configurations from environment variables. This function parses environment variables with the patte | STRING |
| HIGH | private_gpt/utils/async_utils.py | 31 | Convert a synchronous iterator to an async iterator with optional transformation. Args: iterator: The synch | STRING |
| HIGH | …ssors/chat_history/multimodality/image_preprocessor.py | 37 | Preprocess a message by extracting insights from images only. Args: main_llm: The primary LLM that will pro | STRING |
| HIGH | …ssors/chat_history/multimodality/audio_preprocessor.py | 37 | Preprocess a message by extracting insights from audio only. Args: main_llm: The primary LLM that will proc | STRING |
| HIGH | …ate_gpt/components/engines/citations/term_extractor.py | 46 | Detect the language of the input text. Args: text: Text to detect language for Returns: | STRING |
| HIGH | private_gpt/components/readers/docling/utils.py | 83 | Convert language code to EasyOCR format. Args: lang: Language code in format like 'en-US', 'es-ES' Ret | STRING |
| HIGH | private_gpt/components/readers/docling/utils.py | 101 | Convert language code to Tesseract format. Args: lang: Language code in format like 'en-US', 'es-ES' R | STRING |
| HIGH | private_gpt/components/readers/docling/utils.py | 119 | Convert language code to RapidOCR format. Args: lang: Language code in format like 'en-US', 'es-ES' Re | STRING |
| HIGH | private_gpt/components/readers/docling/utils.py | 137 | Convert language code to OCRMac format. Args: lang: Language code in format like 'en-US', 'es-ES' Retu | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | private_gpt/chat/schema_models.py | 253 | CODE | |
| LOW | private_gpt/chat/schema_models.py | 293 | CODE | |
| LOW | private_gpt/server/content/content_service.py | 406 | CODE | |
| LOW | private_gpt/server/mcp/_runtime.py | 173 | CODE | |
| LOW | private_gpt/server/primitives/primitives_router.py | 368 | CODE | |
| LOW | private_gpt/utils/retry.py | 17 | CODE | |
| LOW | …pt/components/tools/builders/database_query_builder.py | 241 | CODE | |
| LOW | …_gpt/components/tools/builders/tabular_data_builder.py | 250 | CODE | |
| LOW | private_gpt/components/llm/custom/sagemaker.py | 149 | CODE | |
| LOW | private_gpt/components/memory/trimming_memory.py | 107 | CODE | |
| LOW | …ivate_gpt/components/chat/models/chat_config_models.py | 294 | CODE | |
| LOW | …ents/postprocessor/tree_expansion/document_expander.py | 451 | CODE | |
| LOW | private_gpt/components/tabular/pandasai_service.py | 60 | CODE | |
| LOW | …ate_gpt/components/tabular/database_query_generator.py | 276 | CODE | |
| LOW | …ponents/workflows/others/tree_summarize_synthesizer.py | 43 | CODE | |
| LOW | …pt/components/workflows/others/summary_query_engine.py | 77 | CODE | |
| LOW | …_gpt/components/workflows/retrieval/semantic_search.py | 89 | CODE | |
| LOW | …te_gpt/components/vector_store/patched_qdrant_store.py | 111 | CODE | |
| LOW | …te_gpt/components/vector_store/patched_qdrant_store.py | 505 | CODE | |
| LOW | …te_gpt/components/vector_store/patched_qdrant_store.py | 554 | CODE | |
| LOW | …components/streaming/providers/redis_stream_service.py | 188 | CODE | |
| LOW | …components/streaming/providers/redis_stream_service.py | 185 | CODE | |
| LOW | private_gpt/components/prompts/prompt_builder.py | 268 | CODE | |
| LOW | private_gpt/components/prompts/prompt_builder.py | 348 | CODE | |
| LOW | private_gpt/components/prompts/prompt_builder.py | 436 | CODE | |
| LOW | private_gpt/components/readers/docling/api_clients.py | 130 | CODE | |
| LOW | private_gpt/components/multimodality/image_handler.py | 122 | CODE | |
| LOW | private_gpt/components/multimodality/audio_handler.py | 994 | CODE | |
| LOW | private_gpt/components/multimodality/audio_handler.py | 509 | CODE | |
| LOW | …s/components/database/test_dabatase_query_generator.py | 95 | CODE |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | …ents/postprocessor/tree_expansion/document_expander.py | 195 | # Step 2: Expand the node in the specified direction | COMMENT |
| LOW⚡ | …ents/postprocessor/tree_expansion/document_expander.py | 198 | # Step 1: Mark the node as processed in the specified direction | COMMENT |
| LOW⚡ | …ents/postprocessor/tree_expansion/document_expander.py | 205 | # Step 3: Process the result | COMMENT |
| LOW⚡ | …ponents/postprocessor/tree_expansion/split_subtrees.py | 132 | # Step 1: Rebuild the tree structure from the flat list of nodes | COMMENT |
| LOW⚡ | …ponents/postprocessor/tree_expansion/split_subtrees.py | 135 | # Step 2: Create a new root node and add the subtrees as children | COMMENT |
| LOW | …ponents/postprocessor/tree_expansion/split_subtrees.py | 149 | # Step 3: Remove any nodes that are not within the subtree | COMMENT |
| LOW | …ponents/postprocessor/tree_expansion/split_subtrees.py | 173 | # Step 4: Prune the tree to remove any empty nodes | COMMENT |
| LOW⚡ | …components/readers/pptx2md/convert_slide_into_image.py | 861 | # Step 1: Apply basic filtering | COMMENT |
| LOW⚡ | …components/readers/pptx2md/convert_slide_into_image.py | 864 | # Step 2: Expand zones | COMMENT |
| LOW⚡ | …components/readers/pptx2md/convert_slide_into_image.py | 870 | # Step 3: Group zones by slide for processing | COMMENT |
| LOW⚡ | …components/readers/pptx2md/convert_slide_into_image.py | 879 | # Step 4: Process each slide separately | COMMENT |
| LOW | …components/readers/pptx2md/convert_slide_into_image.py | 895 | # Step 5: Remove high-overlap duplicates | COMMENT |
| LOW | …s/components/llm/tokenizers/models/test_concurrency.py | 434 | # Step 1: Initial tokenizer-only download | COMMENT |
| LOW | …s/components/llm/tokenizers/models/test_concurrency.py | 460 | # Step 2: Later, full model downloaded | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW⚡ | …ents/postprocessor/tree_expansion/document_expander.py | 195 | # Step 2: Expand the node in the specified direction | COMMENT |
| LOW⚡ | …ents/postprocessor/tree_expansion/document_expander.py | 198 | # Step 1: Mark the node as processed in the specified direction | COMMENT |
| LOW⚡ | …ents/postprocessor/tree_expansion/document_expander.py | 205 | # Step 3: Process the result | COMMENT |
| LOW⚡ | …ponents/postprocessor/tree_expansion/split_subtrees.py | 132 | # Step 1: Rebuild the tree structure from the flat list of nodes | COMMENT |
| LOW⚡ | …ponents/postprocessor/tree_expansion/split_subtrees.py | 135 | # Step 2: Create a new root node and add the subtrees as children | COMMENT |
| LOW | …ponents/postprocessor/tree_expansion/split_subtrees.py | 149 | # Step 3: Remove any nodes that are not within the subtree | COMMENT |
| LOW | …ponents/postprocessor/tree_expansion/split_subtrees.py | 173 | # Step 4: Prune the tree to remove any empty nodes | COMMENT |
| LOW⚡ | …components/readers/pptx2md/convert_slide_into_image.py | 861 | # Step 1: Apply basic filtering | COMMENT |
| LOW⚡ | …components/readers/pptx2md/convert_slide_into_image.py | 864 | # Step 2: Expand zones | COMMENT |
| LOW⚡ | …components/readers/pptx2md/convert_slide_into_image.py | 870 | # Step 3: Group zones by slide for processing | COMMENT |
| LOW⚡ | …components/readers/pptx2md/convert_slide_into_image.py | 879 | # Step 4: Process each slide separately | COMMENT |
| LOW | …components/readers/pptx2md/convert_slide_into_image.py | 895 | # Step 5: Remove high-overlap duplicates | COMMENT |
| LOW | …s/components/llm/tokenizers/models/test_concurrency.py | 434 | # Step 1: Initial tokenizer-only download | COMMENT |
| LOW | …s/components/llm/tokenizers/models/test_concurrency.py | 460 | # Step 2: Later, full model downloaded | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | README.md | 137 | | **[Claude Code](https://docs.privategpt.dev/integrations/claude-code)** | Use your local models as the backend for age | CODE |
| MEDIUM | private_gpt/initialize.py | 61 | # Set global embedding model to Mock to prevent LlamaIndex to default to use OpenAI | COMMENT |
| MEDIUM | private_gpt/launcher.py | 273 | # Set global embedding model to Mock to prevent LlamaIndex to default to use OpenAI | COMMENT |
| MEDIUM | private_gpt/components/llm/custom/openai.py | 182 | # Extract reasoning_content for chain-of-thought streaming. | COMMENT |
| MEDIUM | private_gpt/components/ingest/ingest_component.py | 260 | max_truncate_length=max_context_window * 10, # 10x context window | CODE |
| MEDIUM | …ts/ingest/transformations/sentence_tree_node_parser.py | 159 | # 1. Chunk size should be half of the context window size to | COMMENT |
| MEDIUM | …ponents/workflows/others/tree_summarize_synthesizer.py | 84 | # repack text_chunks so that each chunk fills the context window | COMMENT |
| MEDIUM | …ponents/workflows/others/tree_summarize_synthesizer.py | 165 | # repack text_chunks so that each chunk fills the context window | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| HIGH | private_gpt/components/llm/llm_component.py | 0 | filter embedding components based on a predicate function. :param predicate: a function that takes an embedding and retu | STRING |
| HIGH | private_gpt/components/llm/registry.py | 0 | filter embedding components based on a predicate function. :param predicate: a function that takes an embedding and retu | STRING |
| HIGH | private_gpt/components/embedding/registry.py | 0 | filter embedding components based on a predicate function. :param predicate: a function that takes an embedding and retu | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | private_gpt/server/ingest/ingest_router.py | 867 | """Retrieves a comprehensive list of all documents ingested. | STRING |
| LOW | …ivate_gpt/components/chat/models/chat_config_models.py | 385 | # just return the function call | COMMENT |
| LOW | …ponents/postprocessor/tree_expansion/paper_distance.py | 46 | # not much to do here so just return empty set, | COMMENT |
| MEDIUM⚡ | tests/server/chat/test_chat_lifecycle_e2e.py | 144 | # Capture harness — hooks the *real* chain's LLM call boundary. Everything | COMMENT |
| MEDIUM⚡ | tests/server/mcp/test_mcp_service.py | 220 | # Name normalization (mirrors the deepseek-harness mcp-client contract) | COMMENT |
| MEDIUM⚡ | tests/components/processors/test_df_preprocessor.py | 221 | """Test robust type inference with edge cases.""" | STRING |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| LOW | …ponents/postprocessor/tree_expansion/paper_distance.py | 41 | COMMENT | |
| LOW | …ate_gpt/components/tabular/database_query_generator.py | 661 | fixed_result = self._execute_db2_procedure(original_sql) | COMMENT |
| LOW | …te_gpt/components/readers/pptx2md/slides_transforms.py | 101 | # Create text chunks from the tree nodes | COMMENT |
| LOW | tests/server/ingest/test_file_validation.py | 121 | # | COMMENT |
| LOW | tests/server/ingest/test_file_validation.py | 181 | # """Test file validation when the PDF contains forms.""" | COMMENT |
| LOW | tests/models/anthropic/test_openapi_schema.py | 201 | COMMENT | |
| LOW | tests/components/multimodality/test_describe_image.py | 341 | # async def test_error_handling_in_strategy_inference( | COMMENT |
| Severity | File | Line | Snippet | Context |
|---|---|---|---|---|
| MEDIUM | …r/chat/interceptors/test_preprocessing_interceptors.py | 256 | CODE | |
| MEDIUM | …r/chat/interceptors/test_preprocessing_interceptors.py | 284 | CODE | |
| MEDIUM | tests/components/multimodality/test_multimodality.py | 874 | CODE |