Update app.py

app.py

@@ -1,64 +1,135 @@
+# import gradio as gr
+# import fitz  # PyMuPDF
+# import re
+# from langchain_openai.embeddings import OpenAIEmbeddings
+# from langchain_chroma import Chroma
+# from langchain.retrievers.multi_query import MultiQueryRetriever
+# from langchain.chains import ConversationalRetrievalChain
+# from langchain.memory import ConversationBufferMemory
+# from langchain_openai import ChatOpenAI
+# from langchain_experimental.text_splitter import SemanticChunker
+
+# import os
+# openai_api_key = os.getenv("OPENAI_API_KEY")
+
+# vectorstore = None
+# llm = None
+# qa_instance = None
+# chat_history = []  # Global chat history
+
+# def extract_text_from_pdf(pdf_bytes):
+#     document = fitz.open("pdf", pdf_bytes)
+#     text = ""
+#     for page_num in range(len(document)):
+#         page = document.load_page(page_num)
+#         text += page.get_text()
+#     document.close()
+#     return text
+
+# def clean_text(text):
+#     cleaned_text = re.sub(r'\s+', ' ', text)
+#     cleaned_text = re.sub(r'(.)\1{2,}', r'\1', cleaned_text)
+#     cleaned_text = re.sub(r'\b(\w+)\b(?:\s+\1\b)+', r'\1', cleaned_text)
+#     return cleaned_text.strip()
+
+# def initialize_chatbot(cleaned_text, openai_api_key):
+#     global vectorstore, llm, qa_instance
+#     if vectorstore is None:  # Only create embeddings and Chroma once
+#         embeddings = OpenAIEmbeddings(api_key=openai_api_key)
+#         text_splitter = SemanticChunker(embeddings)
+#         docs = text_splitter.create_documents([cleaned_text])
+#         vectorstore = Chroma.from_documents(documents=docs, embedding=embeddings)
+#     if llm is None:
+#         llm = ChatOpenAI(api_key=openai_api_key, temperature=0.5, model="gpt-4o", verbose=True)
+#     retriever = MultiQueryRetriever.from_llm(retriever=vectorstore.as_retriever(), llm=llm)
+#     memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+#     qa_instance = ConversationalRetrievalChain.from_llm(llm, retriever=retriever, memory=memory)
+
+# def setup_qa_system(pdf_file):
+#     global chat_history
+#     if pdf_file is None:
+#         return [("Please upload a PDF file.", "")]
+#     extracted_text = extract_text_from_pdf(pdf_file)
+#     cleaned_text = clean_text(extracted_text)
+#     initialize_chatbot(cleaned_text, openai_api_key)
+#     chat_history = [("Chatbot initialized. Please ask a question.", "")]
+#     return chat_history
+
+# def answer_query(question):
+#     global chat_history
+#     if qa_instance is None:
+#         return [("Please upload a PDF and initialize the system first.", "")]
+#     if not question.strip():
+#         return [("Please enter a question.", "")]
+#     result = qa_instance({"question": question})
+#     chat_history.append((question, result['answer']))
+#     return chat_history
+
+# with gr.Blocks() as demo:
+#     upload = gr.File(label="Upload PDF", type="binary", file_types=["pdf"])
+#     chatbot = gr.Chatbot(label="Chatbot")
+#     question = gr.Textbox(label="Ask a question", placeholder="Type your question after uploading PDF...")
+
+#     upload.change(setup_qa_system, inputs=[upload], outputs=[chatbot])
+#     question.submit(answer_query, inputs=[question], outputs=[chatbot])
+
+# if __name__ == "__main__":
+#     demo.launch()
+
+
+
 import gradio as gr
-import fitz  # PyMuPDF
-import re
+import json
+from typing import List, Dict
 from langchain_openai.embeddings import OpenAIEmbeddings
 from langchain_chroma import Chroma
 from langchain.retrievers.multi_query import MultiQueryRetriever
 from langchain.chains import ConversationalRetrievalChain
 from langchain.memory import ConversationBufferMemory
 from langchain_openai import ChatOpenAI
-from langchain_experimental.text_splitter import SemanticChunker
+from langchain.schema import Document
 
-import os
-openai_api_key = os.getenv("OPENAI_API_KEY")
+openai_api_key = "sk-proj-bxh8lX8T6EoQaDWm2cljT3BlbkFJylU5bVGc2eQxB8WCP1Ub"
 
 vectorstore = None
 llm = None
 qa_instance = None
-chat_history = []  # Global chat history
-
-def extract_text_from_pdf(pdf_bytes):
-    document = fitz.open("pdf", pdf_bytes)
-    text = ""
-    for page_num in range(len(document)):
-        page = document.load_page(page_num)
-        text += page.get_text()
-    document.close()
-    return text
-
-def clean_text(text):
-    cleaned_text = re.sub(r'\s+', ' ', text)
-    cleaned_text = re.sub(r'(.)\1{2,}', r'\1', cleaned_text)
-    cleaned_text = re.sub(r'\b(\w+)\b(?:\s+\1\b)+', r'\1', cleaned_text)
-    return cleaned_text.strip()
-
-def initialize_chatbot(cleaned_text, openai_api_key):
+chat_history = []
+
+def load_embeddings_from_json(json_file_path: str):
+    with open(json_file_path, 'r') as f:
+        data = json.load(f)
+    chunks = [item['chunk'] for item in data]
+    embeddings = [item['embeddings'] for item in data]
+    ids = [item.get('id', str(index)) for index, item in enumerate(data)]
+    return chunks, embeddings, ids
+
+def initialize_chatbot_from_json(json_file_path: str, openai_api_key: str):
     global vectorstore, llm, qa_instance
-    if vectorstore is None:  # Only create embeddings and Chroma once
-        embeddings = OpenAIEmbeddings(api_key=openai_api_key)
-        text_splitter = SemanticChunker(embeddings)
-        docs = text_splitter.create_documents([cleaned_text])
-        vectorstore = Chroma.from_documents(documents=docs, embedding=embeddings)
+    if vectorstore is None:
+        chunks, embeddings, ids = load_embeddings_from_json(json_file_path)
+        vectorstore = Chroma(
+            collection_name="my_collection",
+            persist_directory=None,
+            embedding_function=OpenAIEmbeddings(api_key=openai_api_key)
+        )
+        vectorstore._client._add(
+            collection_id=vectorstore._collection.id,
+            ids=ids,
+            embeddings=embeddings,
+            metadatas=[{"source": "json"} for _ in chunks],
+            documents=chunks,
+        )
     if llm is None:
         llm = ChatOpenAI(api_key=openai_api_key, temperature=0.5, model="gpt-4o", verbose=True)
     retriever = MultiQueryRetriever.from_llm(retriever=vectorstore.as_retriever(), llm=llm)
     memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
     qa_instance = ConversationalRetrievalChain.from_llm(llm, retriever=retriever, memory=memory)
 
-def setup_qa_system(pdf_file):
-    global chat_history
-    if pdf_file is None:
-        return [("Please upload a PDF file.", "")]
-    extracted_text = extract_text_from_pdf(pdf_file)
-    cleaned_text = clean_text(extracted_text)
-    initialize_chatbot(cleaned_text, openai_api_key)
-    chat_history = [("Chatbot initialized. Please ask a question.", "")]
-    return chat_history
-
-def answer_query(question):
+def answer_query(question: str):
     global chat_history
     if qa_instance is None:
-        return [("Please upload a PDF and initialize the system first.", "")]
+        return [("Please initialize the system first.", "")]
     if not question.strip():
         return [("Please enter a question.", "")]
     result = qa_instance({"question": question})
@@ -66,12 +137,12 @@ def answer_query(question):
     return chat_history
 
 with gr.Blocks() as demo:
-    upload = gr.File(label="Upload PDF", type="binary", file_types=["pdf"])
     chatbot = gr.Chatbot(label="Chatbot")
-    question = gr.Textbox(label="Ask a question", placeholder="Type your question after uploading PDF...")
+    question = gr.Textbox(label="Ask a question", placeholder="Type your question...")
 
-    upload.change(setup_qa_system, inputs=[upload], outputs=[chatbot])
     question.submit(answer_query, inputs=[question], outputs=[chatbot])
+    initialize_chatbot_from_json("embeddings.json", openai_api_key)
 
 if __name__ == "__main__":
     demo.launch()
+