https://github.com/chleba/chunkerbot
LLM documents spliting with AI agent that wrap chunks within document's context and store into a vector DB with simple chat
https://github.com/chleba/chunkerbot
agentic-ai ai chatbot cli qdrant rag rust-lang vector-database
Last synced: about 2 months ago
JSON representation
LLM documents spliting with AI agent that wrap chunks within document's context and store into a vector DB with simple chat
- Host: GitHub
- URL: https://github.com/chleba/chunkerbot
- Owner: Chleba
- Created: 2025-03-24T10:51:08.000Z (about 1 year ago)
- Default Branch: master
- Last Pushed: 2025-05-17T13:36:03.000Z (about 1 year ago)
- Last Synced: 2026-03-30T12:36:47.768Z (3 months ago)
- Topics: agentic-ai, ai, chatbot, cli, qdrant, rag, rust-lang, vector-database
- Language: Rust
- Homepage:
- Size: 83 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# chunk_contextor
LLM document spliting with ai agent that wrap chunks with document's context, store in vector DB with simple chat
## Install
`cargo build --release --bin chat_contextor`
You can find a binary in `target/release/chat_extractor`
## Qdrant
Install & run `qdrant` vector database docker
`docker run -p 6333:6333 -p 6334:6334 \
-e QDRANT__SERVICE__GRPC_PORT="6334" \
qdrant/qdrant`
You need to start `gRpc` service for client to be able to connect to DB.
> [!CAUTION]
> I Recommend to setup storage path on local machine, because of losing data when container is stopped.
## Usage
`chunk_contextor --help` will tell you all
> [!NOTE]
> Testing project for simple vector RAG search application. I will leave it here left free to use or update.
> Very simple contextual chunking and storing into a vector DB (qdrant).
> No Q/A chunking. No BM25 fulltext search. No TUI. Only CLI chat mod and CLI chunk generation.