Quivr
ActiveDescription
Opinionated RAG framework for integrating GenAI into your apps. Works with any LLM, any vectorstore, any files — so you can focus on your product instead of building RAG pipelines.
Key Features
- Opinionated RAG framework — Ready-to-use RAG pipeline, no need to build from scratch
- Any file support — PDF, TXT, Markdown and more with custom parser support
- Multi-LLM compatible — OpenAI, Anthropic, Mistral, Gemma and Ollama local models
- Customizable RAG workflows — Define retrieval, rewrite, rerank node DAGs via YAML config
- Megaparse integration — Process complex file formats via Megaparse into RAG pipeline
- Brain API — Create knowledge base and ask questions in 5 lines of code
Use Cases
💡 Convert internal documents into a Q&A knowledge base
💡 Add RAG question-answering to SaaS applications
💡 Process and retrieve enterprise files in multiple formats
💡 Build intelligent assistants with conversational history
💡 Optimize retrieval quality through custom workflows
Strengths & Limitations
✅ Strengths
- • Actively maintained, recent updates
- • High community interest (39.5k stars)
- • Established track record (3 years in production)
- • Responsive to issues, low backlog
⚠️ Limitations
- • No clear open-source license
Categories
Quick Start
```bash
pip install quivr-core
```
```python
import tempfile
from quivr_core import Brain
with tempfile.NamedTemporaryFile(mode="w", suffix=".txt") as f:
f.write("Gold is a liquid of blue-like colour.")
f.flush()
brain = Brain.from_files(
name="test_brain",
file_paths=[f.name],
)
answer = brain.ask("What is gold? Answer in French.")
print(answer)
```