Update app.py

app.py

@@ -101,18 +101,38 @@ def get_text_chunks(pages):
 
 
 
-def get_vectorstore(text_chunks : list) -> FAISS:
-    model = "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
-    encode_kwargs = {
-        "normalize_embeddings": True
-    }  # set True to compute cosine similarity
-    embeddings = HuggingFaceBgeEmbeddings(
-        model_name=model, encode_kwargs=encode_kwargs, model_kwargs={"device": "cpu"}
-    )
-    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+#def get_vectorstore(text_chunks : list) -> FAISS:
+#    model = "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2"
+#    encode_kwargs = {
+#        "normalize_embeddings": True
+#    }  # set True to compute cosine similarity
+#    embeddings = HuggingFaceBgeEmbeddings(
+#        model_name=model, encode_kwargs=encode_kwargs, model_kwargs={"device": "cpu"}
+#    )
+#    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+#    return vectorstore
+
+
+def get_vectorstore(text_chunks):
+    """
+    Generate a vector store from a list of text chunks using HuggingFace BgeEmbeddings.
+    Parameters
+    ----------
+    text_chunks : list
+        List of text chunks to be embedded.
+    Returns
+    -------
+    FAISS
+        A FAISS vector store containing the embeddings of the text chunks.
+    """
+    MODEL_NAME = "sentence-transformers/all-MiniLM-L6-v2"
+    hf_embeddings = HuggingFaceEmbeddings(model_name=MODEL_NAME)
+    vectorstore = Chroma.from_documents(text_chunks, hf_embeddings, persist_directory="db")
     return vectorstore
 
 
+
+
 def get_conversation_chain(vectorstore:FAISS) -> ConversationalRetrievalChain:
     # llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-0613")
     llm = HuggingFaceHub(