Update app.py

app.py

@@ -42,13 +42,12 @@ In the answer try to provide as much text as possible from "response" section in
 If somebody asks "Who are you?" or a similar phrase, state "I am Rishi's assistant built using a Large Language Model!"
 If the answer is not found in the context, kindly state "I don't know. Please ask Rishi on Discord. Discord Invite Link: https://discord.gg/6ezpZGeCcM. Or email at rishi@aiotsmartlabs.com" Don't try to make up an answer.
 CONTEXT: {context}
-HISTORY: {history}
 QUESTION: {question}""")
 
 from langchain_core.runnables import RunnablePassthrough
 
 rag_chain = (
-    {"context": retriever, "history": RunnablePassthrough(), "question": RunnablePassthrough()}
+    {"context": retriever, "question": RunnablePassthrough()}
     | prompt
     | llm
     | StrOutputParser()
@@ -56,21 +55,92 @@ rag_chain = (
 
 # Define the chat response function
 def chatresponse(message, history):
-    history_text = "\n".join([f"User: {h[0]}\nAssistant: {h[1]}" for h in history])
-    
-    inputs = {
-        "context": "",  # context will be retrieved by the retriever
-        "history": history_text,
-        "question": message
-    }
-    
-    output = rag_chain.invoke(inputs)
+    output = rag_chain.invoke(message)
     response = output.split('ANSWER: ')[-1].strip()
     return response
 
 # Launch the Gradio chat interface
 gr.ChatInterface(chatresponse).launch()
 
+# import gradio as gr
+
+
+# import os
+# hftoken = os.environ["hftoken"]
+
+# from langchain_huggingface import HuggingFaceEndpoint
+
+# repo_id = "mistralai/Mistral-7B-Instruct-v0.3"
+# llm = HuggingFaceEndpoint(repo_id = repo_id, max_new_tokens = 128, temperature = 0.7, huggingfacehub_api_token = hftoken)
+
+# from langchain_core.output_parsers import StrOutputParser
+# from langchain_core.prompts import ChatPromptTemplate
+
+# prompt = ChatPromptTemplate.from_template("tell me a joke about {topic}")
+# chain = prompt | llm | StrOutputParser()
+
+# # from langchain.document_loaders.csv_loader import CSVLoader
+# from langchain_community.document_loaders.csv_loader import CSVLoader
+
+
+# loader = CSVLoader(file_path='aiotsmartlabs_faq.csv', source_column = 'prompt')
+# data = loader.load()
+
+# from langchain_huggingface import HuggingFaceEmbeddings
+# from langchain_chroma import Chroma
+# from langchain_huggingface.embeddings import HuggingFaceEndpointEmbeddings
+
+# # CHECK MTEB LEADERBOARD & FIND BEST EMBEDDING MODEL
+# model = "BAAI/bge-m3"
+# embeddings = HuggingFaceEndpointEmbeddings(model = model)
+
+# vectorstore = Chroma.from_documents(documents = data, embedding = embeddings)
+# retriever = vectorstore.as_retriever()
+
+# # from langchain.prompts import PromptTemplate
+
+# from langchain_core.prompts import ChatPromptTemplate
+
+# prompt = ChatPromptTemplate.from_template("""Given the following context and a question, generate an answer based on the context only.
+# In the answer try to provide as much text as possible from "response" section in the source document context without making much changes.
+# If somebody asks "Who are you?" or a similar phrase, state "I am Rishi's assistant built using a Large Language Model!"
+# If the answer is not found in the context, kindly state "I don't know. Please ask Rishi on Discord. Discord Invite Link: https://discord.gg/6ezpZGeCcM. Or email at rishi@aiotsmartlabs.com" Don't try to make up an answer.
+# CONTEXT: {context}
+# QUESTION: {question}""")
+
+# from langchain_core.runnables import RunnablePassthrough
+
+# # rag_chain = (
+# #     {"context": retriever, "history": RunnablePassthrough(), "question": RunnablePassthrough()}
+# #     | prompt
+# #     | llm
+# #     | StrOutputParser()
+# # )
+
+# rag_chain = (
+#     {"context": retriever, "question": RunnablePassthrough()}
+#     | prompt
+#     | llm
+#     | StrOutputParser()
+# )
+
+# # Define the chat response function
+# def chatresponse(message, history):
+#     # history_text = "\n".join([f"User: {h[0]}\nAssistant: {h[1]}" for h in history])
+    
+#     # inputs = {
+#     #     # "context": retriever,  # context will be retrieved by the retriever
+#     #     # "history": history_text,
+#     #     "question": message
+#     # }
+    
+#     output = rag_chain.invoke(message)
+#     response = output.split('ANSWER: ')[-1].strip()
+#     return response
+
+# # Launch the Gradio chat interface
+# gr.ChatInterface(chatresponse).launch()
+
 # import gradio as gr
 # from langchain.schema import AIMessage, HumanMessage