danvics/haiku.rag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Minor doc fixes

Browse source
This commit is contained in:
Yiorgis Gozadinos 2025-06-27 19:58:34 +03:00
parent e07c849d3c
commit 7a1b09d5e2
No known key found for this signature in database
5 changed files with 7 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
README.md
View file

@ -2,6 +2,8 @@
Retrieval-Augmented Generation (RAG) library on SQLite. Retrieval-Augmented Generation (RAG) library on SQLite.
`haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work on SQLite alone without the need for external vector databases. It uses [sqlite-vec](https://github.com/asg017/sqlite-vec) for storing the embeddings and performs semantic (vector) search as well as full-text search combined through Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
## Features ## Features
- **Local SQLite**: No external servers required - **Local SQLite**: No external servers required

2
docs/configuration.md
View file

@ -1,6 +1,6 @@
# Configuration # Configuration
Configuration is done through environment variables. Configuration is done through the use of environment variables.
## File Monitoring ## File Monitoring

3
docs/index.md
View file

@ -1,6 +1,7 @@
# haiku.rag # haiku.rag
A Retrieval-Augmented Generation (RAG) library on SQLite. `haiku.rag` is a Retrieval-Augmented Generation (RAG) library built to work on SQLite alone without the need for external vector databases. It uses [sqlite-vec](https://github.com/asg017/sqlite-vec) for storing the embeddings and performs semantic (vector) search as well as full-text search combined through Reciprocal Rank Fusion. Both open-source (Ollama) as well as commercial (OpenAI, VoyageAI) embedding providers are supported.
## Features ## Features

11
docs/mcp.md
View file

@ -1,6 +1,6 @@
# Model Context Protocol (MCP) # Model Context Protocol (MCP)
The MCP server exposes RAG functionality as tools for AI assistants like Claude Desktop. The MCP server exposes `haiku.rag` as MCP tools for compatible MCP clients.
## Available Tools ## Available Tools
@ -19,7 +19,7 @@ The MCP server exposes RAG functionality as tools for AI assistants like Claude
## Starting MCP Server ## Starting MCP Server
The MCP server starts automatically with the serve command: The MCP server starts automatically with the serve command and supports `Streamable HTTP`, `stdio` and `SSE` transports:
```bash ```bash
# Default HTTP transport # Default HTTP transport
@ -31,10 +31,3 @@ haiku-rag serve --stdio
# SSE transport # SSE transport
haiku-rag serve --sse haiku-rag serve --sse
``` ```
## Integration
The MCP server follows the Model Context Protocol specification, making it compatible with:
- Claude Desktop
- Other MCP-compatible AI assistants
- Custom MCP clients

7
docs/python.md
View file

@ -92,10 +92,3 @@ for chunk, relevance_score in results:
print(f"Content: {chunk.content}") print(f"Content: {chunk.content}")
print(f"From document: {chunk.document_id}") print(f"From document: {chunk.document_id}")
``` ```
## Search Technology
`haiku.rag` uses hybrid search combining:
- **Vector search** using `sqlite-vec` for semantic similarity
- **Full-text search** using SQLite's `FTS5` for keyword matching
- **Reciprocal Rank Fusion** to combine and rank results