🦊 fennec-rag
A comprehensive, production-ready Retrieval-Augmented Generation (RAG) framework with first-class Arabic language support.
✨ Features
- 🌍 Arabic-first NLP — dedicated Arabic chunker, embedder, and prompt templates
- 🔌 Multi-provider LLMs — OpenAI, Anthropic, Gemini, Mistral, HuggingFace, Ollama
- 🗄️ Multiple vector databases — FAISS, ChromaDB, Pinecone
- 🧩 Advanced RAG strategies — Conversational, Agentic, Graph, Multi-hop, Federated, Self-improving, Streaming
- 🛡️ Hallucination Guard — built-in hallucination detection and grounding
- 📊 Observability & Evaluation — tracing, metrics, dashboards, evaluation suite
- 📄 Rich document loaders — PDF, DOCX, HTML, CSV, JSON, Excel, Web, Directory
📦 Installation
# Basic
pip install fennec-rag
# With specific providers
pip install "fennec-rag[openai,faiss]"
pip install "fennec-rag[anthropic,chroma]"
pip install "fennec-rag[gemini,pinecone]"
# Arabic NLP
pip install "fennec-rag[arabic]"
# Full install
pip install "fennec-rag[all]"
🚀 Quick Start
from fennec.rag.core import RAGSystem, RAGConfig
from fennec.embeddings import OpenAIEmbedder
from fennec.vector_database import FAISSVectorDatabase
from fennec.llm import OpenAIInterface
embedder = OpenAIEmbedder(api_key="your-key")
vector_db = FAISSVectorDatabase(embedder=embedder)
llm = OpenAIInterface(api_key="your-key")
config = RAGConfig(chunk_size=512, overlap=128, top_k=5)
rag = RAGSystem(config=config, vector_db=vector_db, llm=llm)
rag.load_documents(["document.pdf"])
response = rag.query("What is the main topic?")
print(response)
🗂️ Modules
| Module | Description |
|---|---|
fennec.rag.core |
RAGSystem, MultiDocRAG, Reranker, PromptRouter |
fennec.rag.conversational_rag |
Multi-turn conversation RAG |
fennec.rag.agentic_rag |
Agent-based RAG |
fennec.rag.graph_rag |
Knowledge graph RAG |
fennec.rag.hybrid_search |
BM25 + semantic hybrid search |
fennec.rag.multi_hop |
Multi-hop question decomposition |
fennec.rag.self_improving_rag |
HyDE + recursive refinement |
fennec.rag.streaming_rag |
Token streaming |
fennec.embeddings |
OpenAI, Gemini, HuggingFace, Mistral, Ollama, Arabic |
fennec.vector_database |
FAISS, ChromaDB, Pinecone |
fennec.llm |
OpenAI, Anthropic, Gemini, Mistral, HuggingFace, Ollama |
fennec.llm.hallucination |
HallucinationGuard, ProtectedLLMInterface |
fennec.chunks |
Arabic & multilingual text chunkers |
fennec.document_loaders |
PDF, DOCX, HTML, CSV, JSON, Excel, Web, Directory |
fennec.memory |
Buffer, Window, Summary, Entity memory |
fennec.router |
SemanticRouter |
fennec.prompt |
PromptTemplate, ChatTemplate, FewShotTemplate |
fennec.output_parser |
JSON, YAML, CSV, Pydantic parsers |
fennec.evaluator |
RAG evaluation & reporting |
fennec.observability |
Tracing, metrics, dashboards |
fennec.cache |
Multi-level cache |
fennec.persistence |
State persistence & backup |
fennec.plugins |
Extensible plugin system |
📝 License
MIT License
1 maintainer
Metadata
1 maintainer
Release files for fennec-rag 1.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| fennec_rag-1.1.1.tar.gz | 413.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| fennec_rag-1.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 923.5 kB
Release files / fennec_rag-1.1.1.tar.gz
| Download URL | fennec_rag-1.1.1.tar.gz |
|---|---|
| Size | 413.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d2a0a0c7bdb814bda0df05fab6cbcc2af3d17c6189a67de5d055fc9e1d79d5b8
|
|
BLAKE2b-256 checksum How to use checksums |
9d24ba05aab17461b6c2fc4c5a6c6158282ee50e27ddf431c8b0e58d62583e8e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.0
|
Release files / fennec_rag-1.1.1-py3-none-any.whl
| Download URL | fennec_rag-1.1.1-py3-none-any.whl |
|---|---|
| Size | 509.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
243f120396eee25430fb37f446b0c12e7b200c3f7fa536ab8c97b5083ead835a
|
|
BLAKE2b-256 checksum How to use checksums |
cad7451ef17bc696864d20b9fb72f23bedad626abfcd901c18b40d408fd8cc06
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.0
|
