Spaces:
Sleeping
Sleeping
Download src/retrieval.py from mohamedamgad2002/Simple-RAG: direct link, hf CLI and curl.
- Browser
- Download file 1.08 kB
-
https://huggingface.co/spaces/mohamedamgad2002/Simple-RAG/resolve/main/src/retrieval.py
- Command line
-
hf download hf://spaces/mohamedamgad2002/Simple-RAG/src/retrieval.py
-
curl -L -o retrieval.py https://huggingface.co/spaces/mohamedamgad2002/Simple-RAG/resolve/main/src/retrieval.py
1.08 kB
| # import basics | |
| import os | |
| from dotenv import load_dotenv | |
| # import pinecone | |
| from pinecone import Pinecone, ServerlessSpec | |
| # import langchain | |
| from langchain_pinecone import PineconeVectorStore | |
| from langchain_google_genai import GoogleGenerativeAIEmbeddings | |
| from langchain_core.documents import Document | |
| load_dotenv() | |
| # initialize pinecone database | |
| pc = Pinecone(api_key=os.environ.get("PINECONE_API_KEY")) | |
| # set the pinecone index | |
| index_name = os.environ.get("PINECONE_INDEX_NAME") | |
| index = pc.Index(index_name) | |
| # initialize embeddings model + vector store | |
| embeddings = GoogleGenerativeAIEmbeddings(model="models/gemini-embedding-001") | |
| vector_store = PineconeVectorStore(index=index, embedding=embeddings) | |
| # retrieval | |
| retriever = vector_store.as_retriever( | |
| search_type="similarity_score_threshold", | |
| search_kwargs={"k": 5, "score_threshold": 0.5}, | |
| ) | |
| results = retriever.invoke("what is retrieval augmented generation?") | |
| # show results | |
| print("RESULTS:") | |
| for res in results: | |
| print(f"* {res.page_content} [{res.metadata}]") |