| Name | haiku.rag JSON |
| Version |
0.3.3
JSON |
| download |
| home_page | None |
| Summary | Retrieval Augmented Generation (RAG) with SQLite |
| upload_time | 2025-07-09 07:50:26 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.10 |
| license | MIT |
| keywords |
rag
mcp
ml
sqlite
sqlite-vec
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Haiku SQLite RAG
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
- **Local SQLite**: No external servers required
- **Multiple embedding providers**: Ollama, VoyageAI, OpenAI
- **Multiple QA providers**: Ollama, OpenAI, Anthropic
- **Hybrid search**: Vector + full-text search with Reciprocal Rank Fusion
- **Question answering**: Built-in QA agents on your documents
- **File monitoring**: Auto-index files when run as server
- **40+ file formats**: PDF, DOCX, HTML, Markdown, audio, URLs
- **MCP server**: Expose as tools for AI assistants
- **CLI & Python API**: Use from command line or Python
## Quick Start
```bash
# Install
uv pip install haiku.rag
# Add documents
haiku-rag add "Your content here"
haiku-rag add-src document.pdf
# Search
haiku-rag search "query"
# Ask questions
haiku-rag ask "Who is the author of haiku.rag?"
# Rebuild database (re-chunk and re-embed all documents)
haiku-rag rebuild
# Start server with file monitoring
export MONITOR_DIRECTORIES="/path/to/docs"
haiku-rag serve
```
## Python Usage
```python
from haiku.rag.client import HaikuRAG
async with HaikuRAG("database.db") as client:
# Add document
doc = await client.create_document("Your content")
# Search
results = await client.search("query")
for chunk, score in results:
print(f"{score:.3f}: {chunk.content}")
# Ask questions
answer = await client.ask("Who is the author of haiku.rag?")
print(answer)
```
## MCP Server
Use with AI assistants like Claude Desktop:
```bash
haiku-rag serve --stdio
```
Provides tools for document management and search directly in your AI assistant.
## Documentation
Full documentation at: https://ggozad.github.io/haiku.rag/
- [Installation](https://ggozad.github.io/haiku.rag/installation/) - Provider setup
- [Configuration](https://ggozad.github.io/haiku.rag/configuration/) - Environment variables
- [CLI](https://ggozad.github.io/haiku.rag/cli/) - Command reference
- [Python API](https://ggozad.github.io/haiku.rag/python/) - Complete API docs
- [Benchmarks](https://ggozad.github.io/haiku.rag/benchmarks/) - Performance Benchmarks
Raw data
{
"_id": null,
"home_page": null,
"name": "haiku.rag",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": null,
"keywords": "RAG, mcp, ml, sqlite, sqlite-vec",
"author": null,
"author_email": "Yiorgis Gozadinos <ggozadinos@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/65/7a/e00e3141c16d8f95534e5d8ac6463e9a0c80ac4fc688231478c18df3e634/haiku_rag-0.3.3.tar.gz",
"platform": null,
"description": "# Haiku SQLite RAG\n\nRetrieval-Augmented Generation (RAG) library on SQLite.\n\n`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.\n\n## Features\n\n- **Local SQLite**: No external servers required\n- **Multiple embedding providers**: Ollama, VoyageAI, OpenAI\n- **Multiple QA providers**: Ollama, OpenAI, Anthropic\n- **Hybrid search**: Vector + full-text search with Reciprocal Rank Fusion\n- **Question answering**: Built-in QA agents on your documents\n- **File monitoring**: Auto-index files when run as server\n- **40+ file formats**: PDF, DOCX, HTML, Markdown, audio, URLs\n- **MCP server**: Expose as tools for AI assistants\n- **CLI & Python API**: Use from command line or Python\n\n## Quick Start\n\n```bash\n# Install\nuv pip install haiku.rag\n\n# Add documents\nhaiku-rag add \"Your content here\"\nhaiku-rag add-src document.pdf\n\n# Search\nhaiku-rag search \"query\"\n\n# Ask questions\nhaiku-rag ask \"Who is the author of haiku.rag?\"\n\n# Rebuild database (re-chunk and re-embed all documents)\nhaiku-rag rebuild\n\n# Start server with file monitoring\nexport MONITOR_DIRECTORIES=\"/path/to/docs\"\nhaiku-rag serve\n```\n\n## Python Usage\n\n```python\nfrom haiku.rag.client import HaikuRAG\n\nasync with HaikuRAG(\"database.db\") as client:\n # Add document\n doc = await client.create_document(\"Your content\")\n\n # Search\n results = await client.search(\"query\")\n for chunk, score in results:\n print(f\"{score:.3f}: {chunk.content}\")\n\n # Ask questions\n answer = await client.ask(\"Who is the author of haiku.rag?\")\n print(answer)\n```\n\n## MCP Server\n\nUse with AI assistants like Claude Desktop:\n\n```bash\nhaiku-rag serve --stdio\n```\n\nProvides tools for document management and search directly in your AI assistant.\n\n## Documentation\n\nFull documentation at: https://ggozad.github.io/haiku.rag/\n\n- [Installation](https://ggozad.github.io/haiku.rag/installation/) - Provider setup\n- [Configuration](https://ggozad.github.io/haiku.rag/configuration/) - Environment variables\n- [CLI](https://ggozad.github.io/haiku.rag/cli/) - Command reference\n- [Python API](https://ggozad.github.io/haiku.rag/python/) - Complete API docs\n- [Benchmarks](https://ggozad.github.io/haiku.rag/benchmarks/) - Performance Benchmarks\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Retrieval Augmented Generation (RAG) with SQLite",
"version": "0.3.3",
"project_urls": null,
"split_keywords": [
"rag",
" mcp",
" ml",
" sqlite",
" sqlite-vec"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "8c66d732fc02cf1d73a772598261947f1df68397c661e5440f09671dadc3c901",
"md5": "a9d10340a92461705525f71e4d6a8cb3",
"sha256": "758c41fea731fc9048b103aba3c1276f831d5361c1a186f9943b4e2b301498f0"
},
"downloads": -1,
"filename": "haiku_rag-0.3.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "a9d10340a92461705525f71e4d6a8cb3",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 31061,
"upload_time": "2025-07-09T07:50:25",
"upload_time_iso_8601": "2025-07-09T07:50:25.647825Z",
"url": "https://files.pythonhosted.org/packages/8c/66/d732fc02cf1d73a772598261947f1df68397c661e5440f09671dadc3c901/haiku_rag-0.3.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "657ae00e3141c16d8f95534e5d8ac6463e9a0c80ac4fc688231478c18df3e634",
"md5": "27f2091e71f6bad648c63b8637690af4",
"sha256": "5f023121fa4c7b8641a92c27f3d0b3742f5970ca744dd10950d1be85b3246196"
},
"downloads": -1,
"filename": "haiku_rag-0.3.3.tar.gz",
"has_sig": false,
"md5_digest": "27f2091e71f6bad648c63b8637690af4",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 222897,
"upload_time": "2025-07-09T07:50:26",
"upload_time_iso_8601": "2025-07-09T07:50:26.495101Z",
"url": "https://files.pythonhosted.org/packages/65/7a/e00e3141c16d8f95534e5d8ac6463e9a0c80ac4fc688231478c18df3e634/haiku_rag-0.3.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-09 07:50:26",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "haiku.rag"
}
