riku-afk/ai-rag

How riku-afk/ai-rag works

AiRAG is a local document assistant with two principal workflows: ingest documents into a Redis vector index, then search that index or answer questions from retrieved context. The generation path also checks a semantic answer cache and maintains expiring Redis conversation history. Edges reflect calls visible in the supplied source excerpts or capabilities explicitly documented in the README; Redis and Ollama are external services. app.py is an unused placeholder.

Main entry points: generate.py RAG answer workflow · ingest.py Document vector index · query.py Retrieval test CLI · data Local documents

Components 18

Other components

CLI user
Local documents data
Ollama service
Ollama chat model
Redis service
Unused app placeholder app.py

Connections 25

CLI user → Ingest and chunk: runs ingestion README.md
Local documents → Ingest and chunk: loads files ingest.py
Ingest and chunk → Ollama embeddings: embeds chunks ingest.py
Ollama embeddings → Ollama service: requests embeddings ingest.py
Ingest and chunk → Document vector index: stores chunks ingest.py
Document vector index → Redis service: uses Redis ingest.py
CLI user → Retrieval test CLI: asks question README.md
Retrieval test CLI → Query embeddings: creates embeddings query.py
Query embeddings → Ollama service: requests embeddings query.py
Retrieval test CLI → Document vector index: searches chunks query.py
Document vector index → Redis service: uses Redis
CLI user → RAG answer workflow: asks question README.md
RAG answer workflow → Semantic cache: checks cache generate.py
Semantic cache → Answer cache index: searches and stores generate.py
Answer cache index → Redis service: uses Redis generate.py
RAG answer workflow → Document vector index: retrieves chunks generate.py
Document vector index → Redis service: uses Redis
RAG answer workflow → Context and sources: formats retrieved chunks generate.py
RAG answer workflow → Session history: loads and saves turns generate.py
Session history → Redis session keys: reads and writes generate.py
Redis session keys → Redis service: uses Redis generate.py
RAG answer workflow → Grounded prompt: builds prompt generate.py
Context and sources → Grounded prompt: supplies context generate.py
Grounded prompt → Ollama chat model: generates answer generate.py
RAG answer workflow → Semantic cache: caches answer generate.py

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

How riku-afk/ai-rag works

Main entry points: generate.py RAG answer workflow · ingest.py Document vector index · query.py Retrieval test CLI · data Local documents

Connections 25

CLI user → Ingest and chunk: runs ingestion README.md
Local documents → Ingest and chunk: loads files ingest.py
Ingest and chunk → Ollama embeddings: embeds chunks ingest.py
Ollama embeddings → Ollama service: requests embeddings ingest.py
Ingest and chunk → Document vector index: stores chunks ingest.py
Document vector index → Redis service: uses Redis ingest.py
CLI user → Retrieval test CLI: asks question README.md
Retrieval test CLI → Query embeddings: creates embeddings query.py
Query embeddings → Ollama service: requests embeddings query.py
Retrieval test CLI → Document vector index: searches chunks query.py
Document vector index → Redis service: uses Redis
CLI user → RAG answer workflow: asks question README.md
RAG answer workflow → Semantic cache: checks cache generate.py
Semantic cache → Answer cache index: searches and stores generate.py
Answer cache index → Redis service: uses Redis generate.py
RAG answer workflow → Document vector index: retrieves chunks generate.py
Document vector index → Redis service: uses Redis
RAG answer workflow → Context and sources: formats retrieved chunks generate.py
RAG answer workflow → Session history: loads and saves turns generate.py
Session history → Redis session keys: reads and writes generate.py
Redis session keys → Redis service: uses Redis generate.py
RAG answer workflow → Grounded prompt: builds prompt generate.py
Context and sources → Grounded prompt: supplies context generate.py
Grounded prompt → Ollama chat model: generates answer generate.py
RAG answer workflow → Semantic cache: caches answer generate.py

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

riku-afk/ai-rag

How riku-afk/ai-rag works

Document ingestion

Retrieval and answers

Redis state

Other components

riku-afk/ai-rag

How riku-afk/ai-rag works

Document ingestion

Retrieval and answers

Redis state

Other components