Spaces:
Runtime error
Runtime error
Download ingest.py from Praneethdodedu/RyBot: direct link, hf CLI and curl.
- Browser
- Download file 997 Bytes
-
https://huggingface.co/spaces/Praneethdodedu/RyBot/resolve/main/ingest.py
- Command line
-
hf download hf://spaces/Praneethdodedu/RyBot/ingest.py
-
curl -L -o ingest.py https://huggingface.co/spaces/Praneethdodedu/RyBot/resolve/main/ingest.py
997 Bytes
| from langchain.embeddings import HuggingFaceEmbeddings | |
| from langchain.vectorstores import FAISS | |
| from langchain.document_loaders import PyPDFLoader, DirectoryLoader | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| DATA_PATH = 'data/' | |
| DB_FAISS_PATH = 'vectorstore/db_faiss' | |
| # Create vector database | |
| def create_vector_db(): | |
| loader = DirectoryLoader(DATA_PATH, | |
| glob='*.pdf', | |
| loader_cls=PyPDFLoader) | |
| documents = loader.load() | |
| text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, | |
| chunk_overlap=50) | |
| texts = text_splitter.split_documents(documents) | |
| embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2', | |
| model_kwargs={'device': 'cpu'}) | |
| db = FAISS.from_documents(texts, embeddings) | |
| db.save_local(DB_FAISS_PATH) | |
| if __name__ == "__main__": | |
| create_vector_db() | |