Repository Analysis

PromtEngineer/localGPT

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

23.6 Moderate AI signal View on GitHub

Analysis Overview

This report presents the forensic synthetic code analysis of PromtEngineer/localGPT, a Python project with 22,205 GitHub stars. SynthScan v2.0 examined 33,236 lines of code across 126 source files, recording 473 pattern matches distributed across 17 syntactic categories. The overall adjusted score of 23.6 places this repository in the Moderate AI signal band.

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

23.6
Adjusted Score
23.6
Raw Score
100%
Time Factor
2026-07-18
Last Push
22.2K
Stars
Python
Language
33.2K
Lines of Code
126
Files
473
Pattern Hits
2026-08-02
Scan Date
0.02
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

Longitudinal tracking requires multiple scan runs. Once this repository is re-scanned after new commits land, this chart will visualise how the synthetic code signal evolves over time — enabling you to detect whether AI authorship is growing, stabilising, or being actively corrected by human engineers.

No multi-scan history yet — run the scanner again to build trend data.

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 3MEDIUM 158LOW 312

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 473 distinct pattern matches across 17 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.

Modern AI Meta-Vocabulary82 hits · 241 pts
SeverityFileLineSnippetContext
MEDIUMsimple_create_index.sh3# Simple Index Creation Script for LocalGPT RAG SystemCOMMENT
MEDIUMDOCKER_README.md76### RAG API Container (rag-api)COMMENT
MEDIUMDOCKER_README.md174# RAG API container (most debugging happens here)COMMENT
MEDIUMDOCKER_README.md186# Test RAG system initializationCOMMENT
MEDIUMREADME.md180# Skip frontend (backend + RAG API only)COMMENT
MEDIUMREADME.md204# Terminal 2: Start RAG APICOMMENT
MEDIUMREADME.md266# Database Paths (used by backend and RAG system)COMMENT
MEDIUMsetup_rag_system.sh237# Step 4: Setup RAG SystemCOMMENT
MEDIUMsetup_rag_system.sh367# Start RAG SystemCOMMENT
MEDIUMsetup_rag_system.sh377# Stop RAG SystemCOMMENT
MEDIUMsetup_rag_system.sh387# Check RAG System StatusCOMMENT
MEDIUMsetup_rag_system.sh2# setup_rag_system.sh - Complete RAG System Setup ScriptCOMMENT
MEDIUMsetup_rag_system.sh402# Backup RAG System DataCOMMENT
MEDIUMsetup_rag_system.sh431# Update RAG SystemCOMMENT
MEDIUMdocker-compose.yml23 # RAG API serverCOMMENT
MEDIUMDOCKER_TROUBLESHOOTING.md95#### Problem: RAG API can't connect to OllamaCOMMENT
MEDIUMDOCKER_TROUBLESHOOTING.md115# Test Ollama connection from RAG API containerCOMMENT
MEDIUMDOCKER_TROUBLESHOOTING.md188pkill -f "api_server" # RAG APICODE
MEDIUMDOCKER_TROUBLESHOOTING.md286# RAG API container (most issues happen here)COMMENT
MEDIUMDOCKER_TROUBLESHOOTING.md378# Test RAG API aloneCOMMENT
MEDIUMDOCKER_TROUBLESHOOTING.md540#### 2. Minimal Docker (RAG API only)COMMENT
MEDIUMDOCKER_TROUBLESHOOTING.md542# Run only RAG API in DockerCOMMENT
MEDIUMdocker-compose.local-ollama.yml2 # RAG API server (connects to host Ollama)COMMENT
MEDIUMtest_docker_build.sh75# 1. RAG API (no dependencies)COMMENT
MEDIUMtest_docker_build.sh82# 2. Backend (depends on RAG API)COMMENT
MEDIUMDocumentation/api_reference.md1# 📚 API Reference (Backend & RAG API)COMMENT
MEDIUMDocumentation/api_reference.md36## RAG API (Python `rag_system/api_server.py`)COMMENT
MEDIUMDocumentation/api_reference.md46### RAG ChatRequest (Advanced Options)COMMENT
MEDIUMDocumentation/system_overview.md1# 🏗️ RAG System - Complete System OverviewCOMMENT
MEDIUMDocumentation/system_overview.md400### **Graph RAG Mode** (`"graph_rag"`)COMMENT
MEDIUMDocumentation/deployment_guide.md1# 🚀 RAG System Deployment GuideCOMMENT
MEDIUMDocumentation/deployment_guide.md139curl http://localhost:8001/models # RAG APICODE
MEDIUMDocumentation/deployment_guide.md229# Terminal 1: RAG APICOMMENT
MEDIUMDocumentation/deployment_guide.md249curl http://localhost:8001/models # RAG APICODE
MEDIUMDocumentation/deployment_guide.md269python -m rag_system.api_server # RAG API on port 8001CODE
MEDIUMDocumentation/deployment_guide.md560# Scale RAG API instances based on loadCOMMENT
MEDIUMDocumentation/improvement_plan.md1# RAG System – Improvement Road-mapCOMMENT
MEDIUMDocumentation/installation_guide.md1# 📦 RAG System Installation GuideCOMMENT
MEDIUMDocumentation/installation_guide.md138### 3.2 Clone and Setup RAG SystemCOMMENT
MEDIUMDocumentation/installation_guide.md324#### **RAG System Test:**COMMENT
MEDIUMDocumentation/installation_guide.md326# Test RAG system initializationCOMMENT
MEDIUMDocumentation/installation_guide.md452ollama pull nomic-embed-text # Alternative embedding modelCODE
MEDIUMDocumentation/installation_guide.md471sudo ufw deny 8001/tcp # RAG API (internal only)CODE
MEDIUMDocumentation/quick_start.md1# ⚡ Quick Start Guide - RAG SystemCOMMENT
MEDIUMDocumentation/quick_start.md72curl http://localhost:8001/models # RAG APICODE
MEDIUMDocumentation/quick_start.md126# Terminal 1: RAG APICOMMENT
MEDIUMDocumentation/quick_start.md145curl http://localhost:8001/models # RAG APICODE
MEDIUMDocumentation/quick_start.md205python -m rag_system.api_server # RAG API onlyCODE
MEDIUMDocumentation/docker_usage.md1# 🐳 Docker Usage Guide - RAG SystemCOMMENT
MEDIUMDocumentation/docker_usage.md174# After RAG system changesCOMMENT
MEDIUMbackend/server.py15# Import RAG system modules for complete metadataCOMMENT
MEDIUMbackend/server.py299 # 🎯 SMART ROUTING: Decide between direct LLM vs RAGCOMMENT
MEDIUMbackend/server.py305 # 🔍 --- Use RAG Pipeline for Document-Related Queries ---COMMENT
MEDIUMbackend/server.py353 # No indexes = definitely no RAG neededCOMMENT
MEDIUMbackend/server.py535 # Check for strong RAG indicatorsCOMMENT
MEDIUMbackend/server.py540 # Question words + substantial length might benefit from RAGCOMMENT
MEDIUMbackend/server.py593 # Build payload for RAG APICOMMENT
MEDIUMbackend/server.py756 # Very naive classification - same logic as RAG API serverCOMMENT
MEDIUMbackend/server.py814 # Add complete metadata from RAG system configuration if availableCOMMENT
MEDIUMbackend/server.py916 # Delegate to advanced RAG API same as session indexingCOMMENT
22 more matches not shown…
Excessive Try-Catch Wrapping162 hits · 164 pts
SeverityFileLineSnippetContext
LOWsystem_health_check.py27 except Exception as e:CODE
LOWsystem_health_check.py52 except Exception as e:CODE
LOWsystem_health_check.py64 except Exception as e:CODE
LOWsystem_health_check.py89 except Exception as e:CODE
LOWsystem_health_check.py112 except Exception as e:CODE
LOWsystem_health_check.py142 except Exception as e:CODE
LOWdemo_batch_indexing.py191 except Exception as e:CODE
LOWdemo_batch_indexing.py379 except Exception as e:STRING
LOWcreate_index_script.py64 except Exception as e:CODE
LOWcreate_index_script.py234 except Exception as e:CODE
LOWcreate_index_script.py257 except Exception as e:CODE
LOWcreate_index_script.py308 except Exception as e:CODE
LOWcreate_index_script.py365 except Exception as e:CODE
LOWsimple_create_index.sh165 except Exception as e:CODE
MEDIUMsimple_create_index.sh118def create_index_simple():CODE
LOWrun_system.py301 except Exception as e:CODE
LOWrun_system.py334 except Exception as e:CODE
LOWrun_system.py464 except Exception as e:CODE
LOWDocumentation/indexing_pipeline.md479 except Exception as e:CODE
MEDIUMDocumentation/indexing_pipeline.md480 print(f"Error processing file: {e}")CODE
LOWDocumentation/indexing_pipeline.md507 except Exception as e:CODE
LOWDocumentation/indexing_pipeline.md538 except Exception as e:CODE
LOWDocumentation/retrieval_pipeline.md370 except Exception as e:CODE
LOWDocumentation/retrieval_pipeline.md391 except Exception as e:CODE
LOWDocumentation/retrieval_pipeline.md400 except Exception as e2:CODE
LOWDocumentation/retrieval_pipeline.md446 except Exception as e:CODE
LOWDocumentation/retrieval_pipeline.md490 except Exception as e:CODE
MEDIUMbackend/server.py784def handle_get_indexes(self):CODE
MEDIUMbackend/server.py801def handle_create_index(self):CODE
LOWbackend/server.py721 except Exception as e:CODE
LOWbackend/server.py729 except Exception as e:CODE
LOWbackend/server.py779 except Exception as e:CODE
LOWbackend/server.py788 except Exception as e:CODE
LOWbackend/server.py798 except Exception as e:CODE
LOWbackend/server.py985 except Exception as e:CODE
LOWbackend/server.py992 except Exception as e:CODE
LOWbackend/server.py172 except Exception as e:CODE
LOWbackend/server.py185 except Exception as e:CODE
LOWbackend/server.py198 except Exception as e:CODE
LOWbackend/server.py219 except Exception as e:CODE
LOWbackend/server.py242 except Exception as e:CODE
LOWbackend/server.py267 except Exception as e:CODE
LOWbackend/server.py333 except Exception as e:CODE
LOWbackend/server.py362 except Exception as e:CODE
LOWbackend/server.py403 except Exception as e:CODE
LOWbackend/server.py429 except Exception as e:CODE
LOWbackend/server.py502 except Exception as e:CODE
LOWbackend/server.py578 except Exception as e:CODE
LOWbackend/server.py623 except Exception:CODE
LOWbackend/server.py638 except Exception as e:CODE
LOWbackend/server.py655 except Exception as e:CODE
LOWbackend/server.py839 except Exception as e:CODE
LOWbackend/server.py903 except Exception:CODE
LOWbackend/server.py963 except Exception as e:CODE
LOWbackend/server.py974 except Exception:CODE
LOWbackend/server.py1011 except Exception as e:CODE
LOWbackend/server.py1022 except Exception as e:CODE
LOWbackend/server.py1056 except Exception as e:CODE
LOWbackend/server.py1075 except Exception as e:CODE
LOWbackend/server.py1097 except Exception as e:CODE
102 more matches not shown…
Decorative Section Separators42 hits · 136 pts
SeverityFileLineSnippetContext
MEDIUMrag_system/__init__.py4# ---------------------------------------------------------COMMENT
MEDIUMrag_system/__init__.py6# ---------------------------------------------------------COMMENT
MEDIUMrag_system/__init__.py10# ---------------------------------------------------------COMMENT
MEDIUMrag_system/__init__.py27# ---------------------------------------------------------COMMENT
MEDIUMrag_system/__init__.py29# ---------------------------------------------------------COMMENT
MEDIUMrag_system/main.py19# ==================================COMMENT
MEDIUMrag_system/main.py23# ============================================================================COMMENT
MEDIUMrag_system/main.py25# ============================================================================COMMENT
MEDIUMrag_system/main.py54# ============================================================================COMMENT
MEDIUMrag_system/main.py56# ============================================================================COMMENT
MEDIUMrag_system/main.py163# ============================================================================COMMENT
MEDIUMrag_system/main.py165# ============================================================================COMMENT
MEDIUMrag_system/main.py238# ============================================================================COMMENT
MEDIUMrag_system/main.py240# ============================================================================COMMENT
MEDIUMrag_system/ingestion/docling_chunker.py39 # ------------------------------------------------------------------COMMENT
MEDIUMrag_system/ingestion/docling_chunker.py85 # ------------------------------------------------------------------COMMENT
MEDIUMrag_system/ingestion/docling_chunker.py87 # ------------------------------------------------------------------COMMENT
MEDIUMrag_system/ingestion/docling_chunker.py199 # --------------------------------------------------------------COMMENT
MEDIUMrag_system/ingestion/docling_chunker.py202 # --------------------------------------------------------------COMMENT
MEDIUMrag_system/rerankers/sentence_pruner.py30 # ---------------------------------------------------------------------COMMENT
MEDIUMrag_system/rerankers/sentence_pruner.py32 # ---------------------------------------------------------------------COMMENT
MEDIUMrag_system/rerankers/sentence_pruner.py55 # ------------------------------------------------------------------COMMENT
MEDIUMrag_system/rerankers/sentence_pruner.py57 # ------------------------------------------------------------------COMMENT
MEDIUMrag_system/pipelines/retrieval_pipeline.py25# ---------------------------------------------------------------------------COMMENT
MEDIUMrag_system/pipelines/retrieval_pipeline.py27# ---------------------------------------------------------------------------COMMENT
MEDIUMrag_system/pipelines/retrieval_pipeline.py309 # -----------------------------------------------------------STRING
MEDIUMrag_system/pipelines/retrieval_pipeline.py311 # -----------------------------------------------------------STRING
MEDIUMrag_system/pipelines/retrieval_pipeline.py286 # ---------------------------------------------------------------STRING
MEDIUMrag_system/pipelines/retrieval_pipeline.py288 # ---------------------------------------------------------------STRING
MEDIUMrag_system/pipelines/retrieval_pipeline.py444 # ------------------------------------------------------------------STRING
MEDIUMrag_system/pipelines/retrieval_pipeline.py446 # ------------------------------------------------------------------STRING
MEDIUMrag_system/pipelines/retrieval_pipeline.py512 # ------------------------------------------------------------------STRING
MEDIUMrag_system/pipelines/retrieval_pipeline.py514 # ------------------------------------------------------------------STRING
MEDIUMrag_system/pipelines/indexing_pipeline.py118 # ------------------------------------------------------------------COMMENT
MEDIUMrag_system/pipelines/indexing_pipeline.py120 # ------------------------------------------------------------------COMMENT
MEDIUMrag_system/pipelines/indexing_pipeline.py280 # ---------------------------------------------------COMMENT
MEDIUMrag_system/pipelines/indexing_pipeline.py282 # ---------------------------------------------------COMMENT
MEDIUMrag_system/utils/ollama_client.py84 # -------------------------------------------------------------COMMENT
MEDIUMrag_system/utils/ollama_client.py87 # -------------------------------------------------------------COMMENT
MEDIUMrag_system/utils/ollama_client.py118 # -------------------------------------------------------------COMMENT
MEDIUMrag_system/utils/ollama_client.py120 # -------------------------------------------------------------COMMENT
MEDIUMrag_system/agent/loop.py638 # ------------------------------------------------------------------STRING
Structural Annotation Overuse29 hits · 46 pts
SeverityFileLineSnippetContext
LOWsetup_rag_system.sh127# Step 3: Install DockerCOMMENT
LOWsetup_rag_system.sh237# Step 4: Setup RAG SystemCOMMENT
LOWsetup_rag_system.sh361# Step 8: Create Helper ScriptsCOMMENT
LOWsetup_rag_system.sh42# Step 1: System Requirements CheckCOMMENT
LOWsetup_rag_system.sh74# Step 2: Install DependenciesCOMMENT
LOWsetup_rag_system.sh302# Step 5: Build and Start ServicesCOMMENT
LOWsetup_rag_system.sh319# Step 6: Install AI ModelsCOMMENT
LOWsetup_rag_system.sh344# Step 7: System VerificationCOMMENT
LOWsetup_rag_system.sh457# Step 9: Final SetupCOMMENT
LOWDocumentation/quick_start.md26### Step 1: Clone and SetupCOMMENT
LOWDocumentation/quick_start.md37### Step 2: Install Ollama LocallyCOMMENT
LOWDocumentation/quick_start.md53### Step 3: Start Docker ContainersCOMMENT
LOWDocumentation/quick_start.md63### Step 4: Verify DeploymentCOMMENT
LOWDocumentation/quick_start.md75### Step 5: Access ApplicationCOMMENT
LOWDocumentation/quick_start.md88### Step 1: Clone and Install DependenciesCOMMENT
LOWDocumentation/quick_start.md102### Step 2: Install and Configure OllamaCOMMENT
LOWDocumentation/quick_start.md116### Step 3: Start the SystemCOMMENT
LOWDocumentation/quick_start.md136### Step 4: Verify InstallationCOMMENT
LOWDocumentation/quick_start.md148### Step 5: Access ApplicationCOMMENT
LOWDocumentation/docker_usage.md38### Step 1: Clone and SetupCOMMENT
LOWDocumentation/docker_usage.md49### Step 2: Install and Configure Ollama (Required)COMMENT
LOWDocumentation/docker_usage.md71### Step 3: Start Docker ContainersCOMMENT
LOWrag_system/api_server_with_progress.py200 # Step 1: Document ProcessingCOMMENT
LOWrag_system/pipelines/indexing_pipeline.py149 # Step 1: Document Processing and ChunkingCOMMENT
LOWrag_system/pipelines/indexing_pipeline.py209 # Step 3: Optional Contextual Enrichment (before indexing for consistency)COMMENT
LOWrag_system/pipelines/indexing_pipeline.py246 # Step 4: Create BM25 Index from enriched chunks (for consistency with vector index)COMMENT
LOWrag_system/pipelines/indexing_pipeline.py321 # Step 6: Knowledge Graph Extraction (Optional)COMMENT
LOWrag_system/indexing/graph_extractor.py20 # Step 1: Extract EntitiesCOMMENT
LOWrag_system/indexing/graph_extractor.py53 # Step 2: Extract RelationshipsSTRING
Self-Referential Comments14 hits · 42 pts
SeverityFileLineSnippetContext
MEDIUMcreate_index_script.py206 # Create the indexCOMMENT
MEDIUMsimple_create_index.sh104 # Create a temporary Python script to create the indexCOMMENT
MEDIUMsimple_create_index.sh219 # Create the indexCOMMENT
MEDIUMrun_system.py109 # Create main loggerCOMMENT
MEDIUMbackend/server.py738 # This function is now deprecated in favor of the new indexing workflowCOMMENT
MEDIUMbackend/server.py677 # Create a unique filename to avoid overwritesCOMMENT
MEDIUMbackend/database.py673 # Create a test sessionSTRING
MEDIUMrag_system/api_server.py597 # Create a temporary pipeline instance with the overridden configCOMMENT
MEDIUMrag_system/main.py20# This file contains the MASTER configuration for all models used in the RAG system.COMMENT
MEDIUMrag_system/ingestion/chunking.py121 "chunk_id": f"{document_id}_{i}", # Create a more unique IDCODE
MEDIUMrag_system/pipelines/retrieval_pipeline.py193 # Define the window for the searchCOMMENT
MEDIUMrag_system/utils/ollama_client.py164 # Create a dummy black image for testingCOMMENT
MEDIUMrag_system/agent/loop.py286 # Create a contextual query that includes history for most operationsCOMMENT
MEDIUMrag_system/indexing/contextualizer.py11# Define the structured prompt templates, adapted from the exampleCOMMENT
Unused Imports33 hits · 29 pts
SeverityFileLineSnippetContext
LOWsystem_health_check.py9CODE
LOWrun_system.py30CODE
LOWrun_system.py34CODE
LOWbackend/server.py7CODE
LOWbackend/server.py918CODE
LOWbackend/database.py5CODE
LOWrag_system/api_server.py4CODE
LOWrag_system/ingestion/docling_chunker.py1CODE
LOWrag_system/ingestion/docling_chunker.py12CODE
LOWrag_system/ingestion/docling_chunker.py13CODE
LOWrag_system/ingestion/docling_chunker.py15CODE
LOWrag_system/rerankers/sentence_pruner.py1CODE
LOWrag_system/pipelines/retrieval_pipeline.py1CODE
LOWrag_system/pipelines/retrieval_pipeline.py2CODE
LOWrag_system/pipelines/retrieval_pipeline.py3CODE
LOWrag_system/pipelines/retrieval_pipeline.py15CODE
LOWrag_system/pipelines/retrieval_pipeline.py22CODE
LOWrag_system/pipelines/retrieval_pipeline.py23CODE
LOWrag_system/utils/batch_processor.py3CODE
LOWrag_system/utils/watsonx_client.py1CODE
LOWrag_system/retrieval/retrievers.py1CODE
LOWrag_system/retrieval/retrievers.py2CODE
LOWrag_system/retrieval/retrievers.py5CODE
LOWrag_system/retrieval/retrievers.py7CODE
LOWrag_system/retrieval/retrievers.py8CODE
LOWrag_system/retrieval/retrievers.py9CODE
LOWrag_system/retrieval/retrievers.py9CODE
LOWrag_system/retrieval/retrievers.py10CODE
LOWrag_system/indexing/multimodal.py5CODE
LOWrag_system/indexing/multimodal.py5CODE
LOWrag_system/indexing/multimodal.py5CODE
LOWrag_system/indexing/latechunk.py1CODE
LOWrag_system/indexing/overview_builder.py1CODE
Hyper-Verbose Identifiers30 hits · 29 pts
SeverityFileLineSnippetContext
LOWsystem_health_check.py56def check_agent_initialization():CODE
LOWcreate_index_script.py314def create_sample_batch_config():CODE
LOWCONTRIBUTING.md211def test_embedding_generation():CODE
LOWDocumentation/indexing_pipeline.md272def _generate_context_summary(self, chunk_text: str, surrounding_context: str) -> str:CODE
LOWDocumentation/indexing_pipeline.md346 def create_table_if_not_exists(self, table_name: str, schema: Schema):CODE
LOWDocumentation/indexing_pipeline.md523def recover_from_partial_failure(self, table_name: str, document_id: str):CODE
LOWDocumentation/retrieval_pipeline.md134def _get_surrounding_chunks_lancedb(self, chunk, window_size):CODE
LOWDocumentation/retrieval_pipeline.md249 def generate_hypothetical_doc(self, query: str) -> str:STRING
LOWDocumentation/retrieval_pipeline.md337def _build_conversation_context(self, history: List[Dict]) -> str:CODE
LOWDocumentation/retrieval_pipeline.md430def recover_from_embedding_failure(self, query: str, **kwargs):STRING
LOWbackend/test_backend.py59def test_conversation_history():CODE
LOWbackend/server.py988 def handle_link_index_to_session(self, session_id: str, index_id: str):CODE
LOWbackend/server.py995 def handle_get_session_indexes(self, session_id: str):CODE
LOWbackend/server.py224 def handle_get_session_documents(self, session_id: str):CODE
LOWbackend/database.py315 def get_documents_for_session(self, session_id: str) -> List[str]:STRING
LOWbackend/database.py443 def inspect_and_populate_index_metadata(self, index_id: str) -> dict:STRING
LOWbackend/simple_pdf_processor.py192def initialize_simple_pdf_processor():STRING
LOWrag_system/api_server_with_progress.py145def run_indexing_with_progress(file_paths: List[str], session_id: str):CODE
LOWrag_system/api_server_with_progress.py294 def handle_index_with_progress(self):CODE
LOWrag_system/api_server.py42def _apply_index_embedding_model(idx_ids):CODE
LOWrag_system/api_server.py71def _get_table_name_for_session(session_id):CODE
LOWrag_system/ingestion/document_converter.py113 def _convert_general_to_markdown(self, file_path: str, input_format: InputFormat) -> List[Tuple[str, Dict[str, Any]]CODE
LOWrag_system/pipelines/retrieval_pipeline.py170 def _get_surrounding_chunks_lancedb(self, chunk: Dict[str, Any], window_size: int) -> List[Dict[str, Any]]:CODE
LOWrag_system/utils/ollama_client.py88 async def generate_completion_async(CODE
LOWrag_system/utils/watsonx_client.py149 async def generate_completion_async(CODE
LOWrag_system/utils/validate_model_config.py39def validate_configuration_consistency():CODE
LOWrag_system/utils/validate_model_config.py154def check_pipeline_configurations():CODE
LOWrag_system/agent/loop.py74 def load_overviews_for_indexes(self, idx_ids: list[str]):CODE
LOWrag_system/agent/loop.py152 def _format_query_with_history(self, query: str, history: list) -> str:CODE
LOWrag_system/retrieval/query_transformer.py309 def _generate_translation_prompt(self, query: str) -> str:STRING
Deep Nesting33 hits · 27 pts
SeverityFileLineSnippetContext
LOWcreate_index_script.py77CODE
LOWrun_system.py346CODE
LOWrun_system.py469CODE
LOWbackend/test_backend.py59CODE
LOWbackend/server.py49CODE
LOWbackend/server.py84CODE
LOWbackend/server.py368CODE
LOWbackend/server.py658CODE
LOWbackend/server.py842CODE
LOWbackend/server.py995CODE
LOWbackend/ollama_client.py33CODE
LOWbackend/ollama_client.py111CODE
LOWbackend/database.py393CODE
LOWbackend/database.py443CODE
LOWbackend/simple_pdf_processor.py36CODE
LOWrag_system/api_server.py145CODE
LOWrag_system/api_server.py304CODE
LOWrag_system/main.py318CODE
LOWrag_system/ingestion/chunking.py36CODE
LOWrag_system/ingestion/docling_chunker.py88CODE
LOWrag_system/rerankers/reranker.py30CODE
LOWrag_system/pipelines/retrieval_pipeline.py135CODE
LOWrag_system/pipelines/retrieval_pipeline.py170CODE
LOWrag_system/pipelines/retrieval_pipeline.py259CODE
LOWrag_system/pipelines/retrieval_pipeline.py515CODE
LOWrag_system/pipelines/indexing_pipeline.py131CODE
LOWrag_system/utils/batch_processor.py76CODE
LOWrag_system/utils/watsonx_client.py177CODE
LOWrag_system/agent/loop.py55CODE
LOWrag_system/agent/loop.py74CODE
LOWrag_system/agent/loop.py260CODE
LOWrag_system/retrieval/retrievers.py72CODE
LOWrag_system/indexing/graph_extractor.py14CODE
Verbosity Indicators16 hits · 23 pts
SeverityFileLineSnippetContext
LOWsetup_rag_system.sh127# Step 3: Install DockerCOMMENT
LOWsetup_rag_system.sh237# Step 4: Setup RAG SystemCOMMENT
LOWsetup_rag_system.sh361# Step 8: Create Helper ScriptsCOMMENT
LOWsetup_rag_system.sh42# Step 1: System Requirements CheckCOMMENT
LOWsetup_rag_system.sh74# Step 2: Install DependenciesCOMMENT
LOWsetup_rag_system.sh302# Step 5: Build and Start ServicesCOMMENT
LOWsetup_rag_system.sh319# Step 6: Install AI ModelsCOMMENT
LOWsetup_rag_system.sh344# Step 7: System VerificationCOMMENT
LOWsetup_rag_system.sh457# Step 9: Final SetupCOMMENT
LOWrag_system/api_server_with_progress.py200 # Step 1: Document ProcessingCOMMENT
LOWrag_system/pipelines/indexing_pipeline.py149 # Step 1: Document Processing and ChunkingCOMMENT
LOWrag_system/pipelines/indexing_pipeline.py209 # Step 3: Optional Contextual Enrichment (before indexing for consistency)COMMENT
LOWrag_system/pipelines/indexing_pipeline.py246 # Step 4: Create BM25 Index from enriched chunks (for consistency with vector index)COMMENT
LOWrag_system/pipelines/indexing_pipeline.py321 # Step 6: Knowledge Graph Extraction (Optional)COMMENT
LOWrag_system/indexing/graph_extractor.py20 # Step 1: Extract EntitiesCOMMENT
LOWrag_system/indexing/graph_extractor.py53 # Step 2: Extract RelationshipsSTRING
Redundant / Tautological Comments16 hits · 21 pts
SeverityFileLineSnippetContext
LOWsimple_create_index.sh47 # Check if we're in the right directoryCOMMENT
LOWsimple_create_index.sh53 # Check if Ollama is runningCOMMENT
LOWsetup_rag_system.sh137 # Check if Homebrew is installedCOMMENT
LOWsetup_rag_system.sh31# Check if running as rootCOMMENT
LOWrun_system.py254 # Check if port is in useCOMMENT
LOWrun_system.py293 # Check if process is still runningCOMMENT
LOWrun_system.py393 # Check if Ollama is already runningCOMMENT
LOWbackend/test_backend.py107 # Check if the AI remembered the nameCOMMENT
LOWbackend/server.py152 # Check if Ollama is runningCOMMENT
LOWbackend/ollama_client.py173 # Check if Ollama is runningCOMMENT
LOWbackend/database.py454 # Check if metadata is already populatedSTRING
LOWbackend/database.py473 # Check if table existsSTRING
LOWbackend/database.py564 # Check if FTS index existsSTRING
LOWbackend/database.py591 # Check if this is actually a legacy index by looking at creation dateSTRING
LOWrag_system/api_server.py186 # Check if this is the first message by calling the backend serverCOMMENT
LOWrag_system/api_server.py345 # Check if this is the first message by calling the backend serverCOMMENT
Magic Placeholder Names2 hits · 10 pts
SeverityFileLineSnippetContext
HIGHWATSONX_README.md137 api_key="your_api_key",CODE
HIGHrag_system/utils/watsonx_client.py237 api_key="your-api-key",CODE
Docstring Block Structure1 hit · 5 pts
SeverityFileLineSnippetContext
HIGHCONTRIBUTING.md260Create a searchable index from documents. This function processes documents through the complete indexing pipelSTRING
Modern Structural Boilerplate4 hits · 4 pts
SeverityFileLineSnippetContext
LOWrag_system/api_server_with_progress.py16logger = logging.getLogger(__name__)CODE
LOWrag_system/utils/batch_processor.py9logger = logging.getLogger(__name__)CODE
LOWrag_system/indexing/contextualizer.py9logger = logging.getLogger(__name__)CODE
LOWrag_system/indexing/overview_builder.py6logger = logging.getLogger(__name__)CODE
Over-Commented Block3 hits · 3 pts
SeverityFileLineSnippetContext
LOWDocumentation/deployment_guide.md541```bashCOMMENT
LOWrag_system/pipelines/retrieval_pipeline.py21COMMENT
LOWrag_system/agent/loop.py261 start_time = time.time()COMMENT
AI Slop Vocabulary3 hits · 2 pts
SeverityFileLineSnippetContext
MEDIUMdemo_batch_indexing.py255 """Create a comprehensive sample configuration file."""STRING
LOWrag_system/pipelines/retrieval_pipeline.py553 # Any issues (missing table, bad schema, etc.) –> just return []STRING
MEDIUMrag_system/utils/validate_model_config.py91 """Print a comprehensive map of which models are used where."""STRING
AI Structural Patterns2 hits · 2 pts
SeverityFileLineSnippetContext
LOWrag_system/agent/loop.py251CODE
LOWrag_system/agent/loop.py260CODE
Fake / Example Data1 hit · 1 pts
SeverityFileLineSnippetContext
LOWrag_system/ingestion/chunking.py140 doc_meta = {"title": "My Awesome Document", "author": "Jane Doe", "year": 2024}CODE