update app.py

app.py

@@ -6,10 +6,11 @@ from langchain.llms import Replicate
 from langchain.text_splitter import CharacterTextSplitter
 from langchain.vectorstores import FAISS
 from langchain.memory import ConversationBufferMemory
-from langchain.document_loaders import PyPDFLoader, TextLoader, Docx2txtLoader
+from langchain.document_loaders import PyPDFLoader
+from langchain.document_loaders import TextLoader
+from langchain.document_loaders import Docx2txtLoader
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 import os
-from dotenv import load_dotenv
 import tempfile
 
 load_dotenv()
@@ -29,7 +30,7 @@ def conversation_chat(query, chain, history):
     history.append((query, result["answer"]))
     return result["answer"]
 
-def display_chat_history(chain):
+def display_chat_history():
     reply_container = st.container()
     container = st.container()
 
@@ -47,27 +48,16 @@ def display_chat_history(chain):
                     message(st.session_state["past"][i], is_user=True, key=str(i) + '_user', avatar_style="thumbs")
                     message(st.session_state["generated"][i], key=str(i), avatar_style="fun-emoji")
 
-def create_conversational_chain(vector_store):
+def create_conversational_chain(vector_store, text_chunks, embeddings):
     replicate_api_token = "r8_AA3K1fhDykqLa5M74E5V0w5ss1z0P9S3foWJl"  # Replace with your actual token
     os.environ["REPLICATE_API_TOKEN"] = replicate_api_token
 
-    # Add debugging statements
-    st.write("Text chunks lengths:", [len(chunk) for chunk in text_chunks])
-    st.write("Text chunks content:", text_chunks)
-
-    # Create embeddings
-    st.write("Creating embeddings...")
-    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2",
-                                       model_kwargs={'device': 'cpu'})
-    
-    # Add debugging statements
-    st.write("Embeddings lengths:", [len(emb) for emb in embeddings])
-    st.write("Embeddings content:", embeddings)
-
-    vector_store = FAISS.from_documents(text_chunks, embedding=embeddings)
-    
-    st.write("Creating conversation chain...")
-    
+    print("Length of text_chunks:", len(text_chunks))
+    print("Content of text_chunks:", text_chunks)
+
+    print("Length of embeddings:", len(embeddings))
+    print("Content of embeddings:", embeddings)
+
     llm = Replicate(
         streaming=True,
         model="replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781",
@@ -82,9 +72,8 @@ def create_conversational_chain(vector_store):
                                                  memory=memory)
     return chain
 
-
-
 def main():
+    load_dotenv()
     initialize_session_state()
     st.title("Chat With Your Doc")
     st.sidebar.title("Document Processing")
@@ -101,7 +90,7 @@ def main():
             loader = None
             if file_extension == ".pdf":
                 loader = PyPDFLoader(temp_file_path)
-            elif file_extension in (".docx", ".doc"):
+            elif file_extension == ".docx" or file_extension == ".doc":
                 loader = Docx2txtLoader(temp_file_path)
             elif file_extension == ".txt":
                 loader = TextLoader(temp_file_path)
@@ -113,11 +102,12 @@ def main():
         text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=100, length_function=len)
         text_chunks = text_splitter.split_documents(text)
 
-        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2",
-                                           model_kwargs={'device': 'cpu'})
+        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2", model_kwargs={'device': 'cpu'})
         vector_store = FAISS.from_documents(text_chunks, embedding=embeddings)
-        chain = create_conversational_chain(vector_store)
-        display_chat_history(chain)
+
+        chain = create_conversational_chain(vector_store, text_chunks, embeddings)
+
+        display_chat_history()
 
 if __name__ == "__main__":
     main()