Open-Source RAG Ecosystem:
Retrieval & Ranking
- FAISS — https://github.com/facebookresearch/faiss
- Weaviate — https://weaviate.io
- Haystack Retrievers — https://haystack.deepset.ai
- JinaAI Rerankers — https://jina.ai
- Elasticsearch KNN — https://www.elastic.co
- FlashRank — https://github.com/PrithivirajDamodaran/FlashRank
- Vespa — https://vespa.ai
- Rank-BM25 — https://github.com/dorianbrown/rank_bm25
- ColBERT — https://github.com/stanford-futuredata/ColBERT
Ingest/Data Processing
- Kubeflow — https://www.kubeflow.org
- Apache Airflow — https://airflow.apache.org
- Apache Nifi — https://nifi.apache.org
- Langchain Document Loaders — https://python.langchain.com
- Haystack Pipelines — https://haystack.deepset.ai
- OpenSearch — https://opensearch.org
- Unstructured.io — https://unstructured.io
- Docling — https://github.com/DS4SD/docling
- LlamaParse — https://github.com/run-llama/llama_parse
- Chonkie — https://github.com/bhavnicksm/chonkie
- Marker — https://github.com/VikParuchuri/marker
Frontend Frameworks
- NextJS — https://nextjs.org
- SvelteKit — https://kit.svelte.dev
- StreamLit — https://streamlit.io
- VueJS — https://vuejs.org
- Gradio — https://gradio.app
- Chainlit — https://chainlit.io
LLM Frameworks
- HuggingFace — https://huggingface.co
- Haystack — https://haystack.deepset.ai
- CrewAI — https://crewai.com
- LlamaIndex — https://www.llamaindex.ai
- LangChain — https://langchain.com
- DSPy — https://github.com/stanfordnlp/dspy
- AutoGen — https://github.com/microsoft/autogen
- Smolagents — https://github.com/huggingface/smolagents
Embedding Models
- HuggingFace Transformers — https://huggingface.co/models
- LLMWare — https://github.com/llmware-ai/llmware
- Sentence Transformers — https://sbert.net
- JinaAI — https://jina.ai
- Cognita — https://github.com/truefoundry/cognita
- Nomic — https://nomic.ai
- BGE (BAAI) — https://github.com/FlagOpen/FlagEmbedding
- FastEmbed — https://github.com/qdrant/fastembed
- E5 Models — https://github.com/microsoft/unilm/tree/master/e5
Vector Database
- Milvus — https://milvus.io
- Weaviate — https://weaviate.io
- PgVector — https://github.com/pgvector/pgvector
- Chroma — https://trychroma.com
- Qdrant — https://qdrant.tech
- FAISS — https://github.com/facebookresearch/faiss
- LanceDB — https://lancedb.com
- Redis Vector — https://redis.io/docs/interact/search-and-query/search/vectors
LLM Models
- phi-2 — https://huggingface.co/microsoft/phi-2
- LLaMA 3.3 — https://github.com/meta-llama/llama3
- Mistral — https://mistral.ai
- Deepseek — https://deepseek.com
- Gemma — https://ai.google.dev/gemma
- Qwen — https://github.com/QwenLM/Qwen
- Mixtral — https://mistral.ai
- Command R — https://cohere.com/command
- Falcon — https://falconllm.tii.ae