Update ingest.py

ingest.py

@@ -1,14 +1,15 @@
 import os
 import logging
+import faiss
+import numpy as np
 from langchain_community.document_loaders import PDFMinerLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain_community.vectorstores import Chroma
 
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
 
-def create_chroma_db():
+def create_faiss_index():
     documents = []
     docs_dir = "docs"
 
@@ -52,12 +53,17 @@ def create_chroma_db():
         logger.error(f"Failed to initialize embeddings: {e}")
         return
 
+    embedding_vectors = np.array([embeddings.embed(text) for text in texts])
+    dimension = embedding_vectors.shape[1]
+    
     try:
-        db = Chroma.from_documents(texts, embeddings, persist_directory="chroma_db")
-        logger.info(f"Created Chroma database with {len(texts)} vectors.")
+        faiss_index = faiss.IndexFlatL2(dimension)
+        faiss_index.add(embedding_vectors)
+        faiss.write_index(faiss_index, "faiss_index.index")
+        logger.info(f"Created FAISS index with {len(texts)} vectors.")
     except Exception as e:
-        logger.error(f"Failed to create Chroma database: {e}")
+        logger.error(f"Failed to create FAISS index: {e}")
         return
 
 if __name__ == "__main__":
-    create_chroma_db()
+    create_faiss_index()