updated app.py using huggingface space

app.py

@@ -1,27 +1,24 @@
 import gradio as gr
-import json
+
+import langchain, langchain_huggingface
+
 from langchain.llms import GooglePalm
+from langchain.document_loaders.csv_loader import CSVLoader
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
 
 api_key = "AIzaSyCdM_aAIsW_nPbjarOF83mbX1_z1cVX2_M"
 
 llm = GooglePalm(google_api_key = api_key, temperature=0.7)
 
-from langchain.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.vectorstores import FAISS
 
-# instructor_embeddings = HuggingFaceEmbeddings(model_name = "Alibaba-NLP/gte-Qwen2-7B-instruct") # best model <-- but too big
 instructor_embeddings = HuggingFaceEmbeddings(model_name = "BAAI/bge-m3")
-# instructor_embeddings = HuggingFaceEmbeddings()
-
 vectordb = FAISS.from_documents(documents = data, embedding = instructor_embeddings)
 
-# e = embeddings_model.embed_query("What is your refund policy")
-
 retriever = vectordb.as_retriever()
 
 from langchain.prompts import PromptTemplate
@@ -49,104 +46,161 @@ chain = RetrievalQA.from_chain_type(llm = llm,
             return_source_documents=True,
             chain_type_kwargs = {"prompt": PROMPT})
 
-# Load your LLM model and necessary components
-# Assume `chain` is a function defined in your notebook that takes a query and returns the output as shown
-# For this example, we'll assume the model and chain function are already available
-
-def chatbot(query):
-    response = chain(query)
-    # Extract the 'result' part of the response
-    result = response.get('result', 'Sorry, I could not find an answer.')
-    return result
-
-# Define the Gradio interface
-iface = gr.Interface(
-    fn=chatbot,  # Function to call
-    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter your question here..."),  # Input type
-    outputs="text",  # Output type
-    title="Hugging Face LLM Chatbot",
-    description="Ask any question related to the documents and get an answer from the LLM model.",
-)
+def chatresponse(message, history):
+    output = chain(message)
+    return output['result']
 
-# Launch the interface
-iface.launch()
+gr.ChatInterface(chatresponse).launch()
 
-# Save this file as app.py and push it to your Hugging Face Space repository
 
 # import gradio as gr
+# from langchain.llms import GooglePalm
 
-# def greet(name, intensity):
-#     return "Hello, " + name + "!" * int(intensity)
+# api_key = "AIzaSyCdM_aAIsW_nPbjarOF83mbX1_z1cVX2_M"
 
-# demo = gr.Interface(
-#     fn=greet,
-#     inputs=["text", "slider"],
-#     outputs=["text"],
-# )
+# llm = GooglePalm(google_api_key = api_key, temperature=0.7)
 
-# demo.launch()
+# from langchain.document_loaders.csv_loader import CSVLoader
 
+# loader = CSVLoader(file_path='aiotsmartlabs_faq.csv', source_column = 'prompt')
+# data = loader.load()
 
-# import gradio as gr
-# from huggingface_hub import InferenceClient
-
-# """
-# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-# """
-# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-# def respond(
-#     message,
-#     history: list[tuple[str, str]],
-#     system_message,
-#     max_tokens,
-#     temperature,
-#     top_p,
-# ):
-#     messages = [{"role": "system", "content": system_message}]
-
-#     for val in history:
-#         if val[0]:
-#             messages.append({"role": "user", "content": val[0]})
-#         if val[1]:
-#             messages.append({"role": "assistant", "content": val[1]})
-
-#     messages.append({"role": "user", "content": message})
-
-#     response = ""
-
-#     for message in client.chat_completion(
-#         messages,
-#         max_tokens=max_tokens,
-#         stream=True,
-#         temperature=temperature,
-#         top_p=top_p,
-#     ):
-#         token = message.choices[0].delta.content
-
-#         response += token
-#         yield response
-
-# """
-# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-# """
-# demo = gr.ChatInterface(
-#     respond,
-#     additional_inputs=[
-#         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-#         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-#         gr.Slider(
-#             minimum=0.1,
-#             maximum=1.0,
-#             value=0.95,
-#             step=0.05,
-#             label="Top-p (nucleus sampling)",
-#         ),
-#     ],
+# from langchain_huggingface import HuggingFaceEmbeddings
+# from langchain.vectorstores import FAISS
+
+# # instructor_embeddings = HuggingFaceEmbeddings(model_name = "Alibaba-NLP/gte-Qwen2-7B-instruct") # best model <-- but too big
+# instructor_embeddings = HuggingFaceEmbeddings(model_name = "BAAI/bge-m3")
+# # instructor_embeddings = HuggingFaceEmbeddings()
+
+# vectordb = FAISS.from_documents(documents = data, embedding = instructor_embeddings)
+
+# # e = embeddings_model.embed_query("What is your refund policy")
+
+# retriever = vectordb.as_retriever()
+
+# from langchain.prompts import PromptTemplate
+
+# prompt_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 [email protected]" Don't try to make up an answer.
+
+# CONTEXT: {context}
+
+# QUESTION: {question}"""
+
+# PROMPT = PromptTemplate(
+#     template = prompt_template, input_variables = ["context", "question"]
 # )
 
+# from langchain.chains import RetrievalQA
+
+# chain = RetrievalQA.from_chain_type(llm = llm,
+#             chain_type="stuff",
+#             retriever=retriever,
+#             input_key="query",
+#             return_source_documents=True,
+#             chain_type_kwargs = {"prompt": PROMPT})
+
+# # Load your LLM model and necessary components
+# # Assume `chain` is a function defined in your notebook that takes a query and returns the output as shown
+# # For this example, we'll assume the model and chain function are already available
+
+# def chatbot(query):
+#     response = chain(query)
+#     # Extract the 'result' part of the response
+#     result = response.get('result', 'Sorry, I could not find an answer.')
+#     return result
+
+# # Define the Gradio interface
+# iface = gr.Interface(
+#     fn=chatbot,  # Function to call
+#     inputs=gr.inputs.Textbox(lines=2, placeholder="Enter your question here..."),  # Input type
+#     outputs="text",  # Output type
+#     title="Hugging Face LLM Chatbot",
+#     description="Ask any question related to the documents and get an answer from the LLM model.",
+# )
 
-# if __name__ == "__main__":
-#     demo.launch()
+# # Launch the interface
+# iface.launch()
+
+# # Save this file as app.py and push it to your Hugging Face Space repository
+
+# # import gradio as gr
+
+# # def greet(name, intensity):
+# #     return "Hello, " + name + "!" * int(intensity)
+
+# # demo = gr.Interface(
+# #     fn=greet,
+# #     inputs=["text", "slider"],
+# #     outputs=["text"],
+# # )
+
+# # demo.launch()
+
+
+# # import gradio as gr
+# # from huggingface_hub import InferenceClient
+
+# # """
+# # For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+# # """
+# # client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+
+
+# # def respond(
+# #     message,
+# #     history: list[tuple[str, str]],
+# #     system_message,
+# #     max_tokens,
+# #     temperature,
+# #     top_p,
+# # ):
+# #     messages = [{"role": "system", "content": system_message}]
+
+# #     for val in history:
+# #         if val[0]:
+# #             messages.append({"role": "user", "content": val[0]})
+# #         if val[1]:
+# #             messages.append({"role": "assistant", "content": val[1]})
+
+# #     messages.append({"role": "user", "content": message})
+
+# #     response = ""
+
+# #     for message in client.chat_completion(
+# #         messages,
+# #         max_tokens=max_tokens,
+# #         stream=True,
+# #         temperature=temperature,
+# #         top_p=top_p,
+# #     ):
+# #         token = message.choices[0].delta.content
+
+# #         response += token
+# #         yield response
+
+# # """
+# # For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
+# # """
+# # demo = gr.ChatInterface(
+# #     respond,
+# #     additional_inputs=[
+# #         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+# #         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
+# #         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
+# #         gr.Slider(
+# #             minimum=0.1,
+# #             maximum=1.0,
+# #             value=0.95,
+# #             step=0.05,
+# #             label="Top-p (nucleus sampling)",
+# #         ),
+# #     ],
+# # )
+
+
+# # if __name__ == "__main__":
+# #     demo.launch()