Update app.py

app.py

@@ -7,11 +7,6 @@ Original file is located at
     https://colab.research.google.com/drive/1wUztAR4EdQUL3vkpM3Is-ps0TEocClry
 """
 
-# !pip install langchain openai qdrant-client gradio pandas tiktoken -U langchain-community
-
-# from google.colab import userdata
-# openai_api_key=userdata.get('openai_api_key')
-
 import gradio as gr
 import pandas as pd
 from langchain.document_loaders.csv_loader import CSVLoader
@@ -21,10 +16,6 @@ from langchain.vectorstores import Qdrant
 from langchain.chains import VectorDBQA
 from langchain.llms import OpenAI
 
-# qdrant_url=userdata.get('Qdrant')
-# qdrant_api_key=userdata.get('qdrant_api_key')
-# openai_api_key=userdata.get('openai_api_key')
-# # groq_api_key=userdata.get('GROQ_API_KEY')
 
 import os
 
@@ -32,7 +23,6 @@ openai_api_key = os.getenv('openai_api_key')
 qdrant_url = os.getenv('QDRANT_URL')
 qdrant_api_key = os.getenv('qdrant_api_key')
 
-# Now you can use these keys in your application
 
 
 #csv loader
@@ -43,7 +33,6 @@ data=loader.load()
 text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
 texts = text_splitter.split_documents(data)
 
-len(texts)
 
 #embeding
 embeding=OpenAIEmbeddings(openai_api_key=openai_api_key, model="text-embedding-3-small")
@@ -82,15 +71,6 @@ from re import search
 #retriver
 retriver=qdrant.as_retriever( search_type="similarity", search_kwargs={"k":2})
 
-#search query
-query="show me a best darmatology doctor in peshawar  "
-docs=retriver.get_relevant_documents(query)
-
-#write a code for prety print
-# for i in docs:
-#   print(i.page_content)
-
-# docs[0].metadata.items()
 
 from langchain import PromptTemplate
 
@@ -134,13 +114,7 @@ prompt = PromptTemplate(
     input_variables=["context", "question"]
 )
 
-# #import conversation
-# from langchain.memory import ConversationBufferMemory
-# memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
-
-# !pip install langchain-openai
 
-#import ChatOpenAI
 from langchain.chat_models import ChatOpenAI
 llm = ChatOpenAI(model_name="gpt-4o", temperature=0, openai_api_key=openai_api_key)
 
@@ -168,64 +142,17 @@ rag_chain = (
             | StrOutputParser()
         )
 
-rag_chain.invoke("show me a best darmatology doctor in lahore  ")
-
-# import random
-# import gradio as gr
-
-# # Gradio Interface
-# def search_doctor(input_text):
-#     return rag_chain.invoke(input_text)
-
-# # Create the Gradio interface
-# iface = gr.Interface(
-#     fn=search_doctor,
-#     inputs=gr.Textbox(lines=1, label="Ask a medical question"),
-#     outputs=gr.Textbox(label="Answer"),
-#     title="Medical Assistant",
-#     description="Find the best doctors based on your medical needs.",
-#     allow_flagging="never",
-#     theme="default",
-#     css=".gradio-container {border-radius: 10px; padding: 10px; background-color: #f9f9f9;} .gr-button {visibility: hidden;}"
-# )
-
-# # Launch the interface without the Gradio logo
-# iface.launch(show_api=False)
-
-# import gradio as gr
-
-# # Example RAG model invocation function (replace with your actual function)
-# def rag_model_query(query):
-#     # Replace with actual RAG model invocation
-#     return rag_chain.invoke(query)
-
-# # Define the Gradio function to handle both echo and RAG queries
-# def handle_message(message, history):
-#     # Check if the message contains a keyword to trigger RAG model
-#     if "doctor" in message["text"].lower():
-#         response = rag_model_query(message["text"])
-#     else:
-#         response = message["text"]
-#     return response
-
-# # Create the Gradio interface
-# demo = gr.ChatInterface(
-#     fn=handle_message,
-#     title="Medical Assistant",
-#     multimodal=True,
-# )
-
-# demo.launch()
+
+
+
 
 from langchain.chat_models import ChatOpenAI
 from langchain.schema import AIMessage, HumanMessage
 import openai
 import os
 import gradio as gr
-# os.environ["OPENAI_API_KEY"] = openai_api_key  # Replace with your key
 
 llm = ChatOpenAI(temperature=1.0, model='gpt-4o', openai_api_key=openai_api_key)
-# llm = ChatOpenAI(model_name="gpt-4o", temperature=0, openai_api_key=openai_api_key, memory=memory)
 
 def reg(message, history):
     history_langchain_format = []
@@ -235,13 +162,6 @@ def reg(message, history):
     history_langchain_format.append(HumanMessage(content=message))
     gpt_response = llm(history_langchain_format)
     return rag_chain.invoke(message)
-# # Gradio ChatInterface
-# demo = gr.ChatInterface(
-#     fn=reg,
-#     title="Medical Assistant",
-#     # theme="soft",
-# )
-
-# demo.launch(show_api=False)
-gr.ChatInterface(predict).launch()
+
+gr.ChatInterface(reg).launch()