The notebook uses langchain to split into sentences , FAISS Vector DB is used to store embeddings ehich are generated by Embedding model BAAI/bge-base-en-v1.5 , Then BM25 is used for enseble retrieval. Cohere reranker is used with compression techniques and lastly llm Zypher 7B is used for generation Multiple reranker models used including Maximal Marginal Relevance
-
Notifications
You must be signed in to change notification settings - Fork 0
The notebook uses langchain to split into sentences , FAISS Vector DB is used to store embeddings ehich are generated by Embedding model BAAI/bge-base-en-v1.5 , Then BM25 is used for enseble retrieval. Cohere reranker is used with compression techniques and lastly llm Zypher 7B is used for generation
AreebAhmad-02/Rag-using-Langchain-with-Cohere-reranker-and-Zypher7B
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
The notebook uses langchain to split into sentences , FAISS Vector DB is used to store embeddings ehich are generated by Embedding model BAAI/bge-base-en-v1.5 , Then BM25 is used for enseble retrieval. Cohere reranker is used with compression techniques and lastly llm Zypher 7B is used for generation
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published