znbne/telco-retrieve

How znbne/telco-retrieve works

TelcoRetrieve is a telecom-specification RAG product: users ingest standards corpora, then ask questions and receive generated answers with source passages. The principal path runs from CLI-selected source loaders through cleaning, chunking, embedding and indexing, then retrieval, optional reranking and generation. README-documented capabilities also include hybrid/multi-collection search, prebuilt Hugging Face chunks, and evaluation/challenge workflows. Edges are limited to relationships explicit in the README or shown by the supplied excerpts and SOURCE INDEX; other plausible runtime connections are omitted.

Main entry points: main.py CLI commands · retrieval.py Retrieval and fusion · pipeline.py Ingest pipeline · evaluate.py RAG evaluation

Components 23

Corpus ingestion

Standards loaders open_telco_rag/sources
Text cleaning open_telco_rag/core/cleaning.py
Chunking and bounds open_telco_rag/core/chunking.py
Chunk enrichment open_telco_rag/core/enrichment.py
Embedding backends open_telco_rag/embedders
Ingest pipeline open_telco_rag/core/pipeline.py

Search and retrieval

Vector index open_telco_rag/stores/chroma.py
Keyword index open_telco_rag/stores/fts.py
Retrieval and fusion open_telco_rag/core/retrieval.py
Multi-collection search open_telco_rag/core/multi_search.py
Reranking open_telco_rag/embedders/reranker.py
Prebuilt chunks open_telco_rag/stores/hf.py

Answer generation

LLM generators open_telco_rag/generators

Evaluation and challenge

RAG evaluation open_telco_rag/evaluation/evaluate.py
Evaluation metrics open_telco_rag/evaluation/metrics
Evaluation results open_telco_rag/evaluation/results.py
Challenge workflow open_telco_rag/challenge/cli.py
Challenge index open_telco_rag/challenge/index.py
Challenge client open_telco_rag/challenge/client.py
Challenge scoring open_telco_rag/challenge/score.py

Other components

CLI user
CLI commands cli/main.py
LLM services

Connections 28

CLI user → CLI commands: runs commands
CLI commands → Standards loaders: selects corpus cli/main.py
Standards loaders → Text cleaning: cleans text open_telco_rag/sources/camara.py
Ingest pipeline → Chunking and bounds: chunks documents open_telco_rag/core/pipeline.py
Ingest pipeline → Chunk enrichment: enriches chunks open_telco_rag/core/pipeline.py
Ingest pipeline → Vector index: writes vectors open_telco_rag/core/pipeline.py
Ingest pipeline → Keyword index: writes text index open_telco_rag/core/pipeline.py
Chunking and bounds → Embedding backends: prepares passages
CLI commands → Ingest pipeline: starts ingestion cli/main.py
CLI commands → Retrieval and fusion: configures search cli/main.py
Retrieval and fusion → Embedding backends: embeds query open_telco_rag/core/retrieval.py
Retrieval and fusion → Vector index: queries vectors open_telco_rag/core/retrieval.py
Retrieval and fusion → Keyword index: searches terms open_telco_rag/core/retrieval.py
Retrieval and fusion → Reranking: reranks hits
Multi-collection search → Vector index: opens collections open_telco_rag/core/multi_search.py
CLI commands → Multi-collection search: configures search cli/main.py
CLI commands → Prebuilt chunks: loads dataset cli/main.py
CLI commands → LLM generators: selects generator cli/main.py
LLM generators → LLM services: requests completion open_telco_rag/generators/openrouter.py
RAG evaluation → Retrieval and fusion: runs retrieval open_telco_rag/evaluation/evaluate.py
RAG evaluation → LLM generators: runs generation open_telco_rag/evaluation/evaluate.py
RAG evaluation → Evaluation metrics: scores outputs open_telco_rag/evaluation/evaluate.py
RAG evaluation → Evaluation results: records results open_telco_rag/evaluation/evaluate.py
CLI commands → RAG evaluation: starts evaluation cli/main.py
Challenge workflow → Challenge client: uses client open_telco_rag/challenge/cli.py
Challenge workflow → Challenge index: uses index open_telco_rag/challenge/cli.py
Challenge workflow → Challenge scoring: checks scores open_telco_rag/challenge/cli.py
CLI commands → Challenge workflow: delegates challenge cli/main.py

Drawn by GitDiagram on November 12, 2026 from the repository's file tree, README and source files. Read as Markdown ·