Create app.py

app.py

@@ -0,0 +1,119 @@
+from langchain.chains import RetrievalQA
+from langchain.chat_models import ChatOpenAI
+from IPython.display import display, Markdown
+from langchain.llms import OpenAI
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.indexes import VectorstoreIndexCreator
+from langchain.document_loaders import PyPDFLoader
+from langchain.embeddings import OpenAIEmbeddings
+from langchain_core.vectorstores import InMemoryVectorStore
+from langchain.vectorstores import FAISS
+from langchain.retrievers import BM25Retriever,EnsembleRetriever
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.output_parsers import StrOutputParser
+from langchain.schema.runnable import RunnablePassthrough
+import gradio as gr
+import os
+
+pdf_folder_path = "files"
+
+documents = []
+for filename in os.listdir(pdf_folder_path):
+    if filename.endswith(".pdf"):
+        file_path = os.path.join(pdf_folder_path, filename)
+        loader = PyPDFLoader(file_path)
+        documents.extend(loader.load())
+
+text_splitter = CharacterTextSplitter()
+text_splits=text_splitter.split_documents(documents)
+
+
+openai_api_key = os.genenv("OPENAI_API_KEY")
+openai_api_key  = openai_api_key 
+
+
+
+embeddings = OpenAIEmbeddings()
+
+vector_store = FAISS.from_documents(documents, embeddings)
+
+retriever_vectordb = vector_store.as_retriever(search_kwargs={"k": 5})
+keyword_retriever = BM25Retriever.from_documents(text_splits)
+keyword_retriever.k =  5
+ensemble_retriever = EnsembleRetriever(retrievers=[retriever_vectordb,keyword_retriever],
+                                       weights=[0.5, 0.5])
+
+
+
+llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0.4, api_key=adminkey)
+
+memory = ConversationBufferMemory(
+    memory_key="chat_history",
+    input_key="question" ,
+    return_messages=True
+)
+
+
+conversation_chain = ConversationalRetrievalChain.from_llm(
+    retriever=ensemble_retriever,
+    llm=llm,
+    memory=memory,
+    verbose=False
+)
+
+
+template = """
+<|system|>>
+You are an AI Assistant that follows instructions extremely well.
+Please be truthful and give direct answers. Please tell 'I don't know' if user query is not in CONTEXT
+
+CONTEXT: {context}
+</s>
+<|user|>
+{query}
+</s>
+<|assistant|>
+"""
+
+prompt = ChatPromptTemplate.from_template(template)
+output_parser = StrOutputParser()
+
+chain = (
+    {"context": conversation_chain, "query": RunnablePassthrough()}
+    | prompt
+    | llm
+    | output_parser
+)
+
+
+
+def chat_with_ai(user_input, chat_history):
+    response = chain.invoke(user_input)
+
+    chat_history.append((user_input, str(response)))
+
+    return chat_history, ""
+
+
+def gradio_chatbot():
+    with gr.Blocks() as demo:
+        gr.Markdown("# Chat Interface for LlamaIndex")
+
+        chatbot = gr.Chatbot(label="Langchain Chatbot")
+        user_input = gr.Textbox(
+            placeholder="Ask a question...", label="Enter your question"
+        )
+
+        submit_button = gr.Button("Send")
+
+        chat_history = gr.State([])
+
+        submit_button.click(chat_with_ai, inputs=[user_input, chat_history], outputs=[chatbot, user_input])
+
+        user_input.submit(chat_with_ai, inputs=[user_input, chat_history], outputs=[chatbot, user_input])
+
+    return demo
+
+gradio_chatbot().launch(debug=True)