Update app.py

app.py

@@ -1,64 +1,71 @@
+import pandas as pd
+import os
 import gradio as gr
-from huggingface_hub import InferenceClient
+from langchain.document_loaders import CSVLoader
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.chains import RetrievalQA
+from langchain_groq import ChatGroq
 
-"""
-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")
+# Set up your API key for ChatGroq
+os.environ["GROQ_API_KEY"] = "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"  # Replace with your actual API key
 
+# Initialize the HuggingFace embeddings
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")  # Lightweight embedding model
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Instantiate the ChatGroq model
+llm = ChatGroq(
+    model="mixtral-8x7b-32768",  # Replace with your desired model
+    temperature=0,
+    max_tokens=None,
+    timeout=None,
+    max_retries=2
+)
+
+# Define the function to process the query and CSV
+def process_query(file, query):
+    try:
+        # Load the CSV as documents for retrieval
+        loader = CSVLoader(file_path=file.name)
+        documents = loader.load()
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+        # Create a FAISS vector store
+        vector_store = FAISS.from_documents(documents, embeddings)
 
-    messages.append({"role": "user", "content": message})
+        # Create a retriever from the vector store
+        retriever = vector_store.as_retriever()
 
-    response = ""
+        # Create a RetrievalQA pipeline
+        qa_chain = RetrievalQA.from_chain_type(
+            llm=llm,
+            retriever=retriever,
+            return_source_documents=True
+        )
 
-    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
+        # Get the response
+        response = qa_chain({"query": query})
+        result = response["result"]
+        sources = "\n".join([doc.page_content for doc in response["source_documents"]])
 
-        response += token
-        yield response
+        return result, sources
 
+    except Exception as e:
+        return f"An error occurred: {str(e)}", ""
 
-"""
-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)",
-        ),
+# Create a Gradio interface
+interface = gr.Interface(
+    fn=process_query,
+    inputs=[
+        gr.File(label="Upload CSV File"),  # File input for the CSV
+        gr.Textbox(label="Enter your query")  # Text input for the query
     ],
+    outputs=[
+        gr.Textbox(label="Answer"),  # Text output for the answer
+        gr.Textbox(label="Source Documents")  # Text output for the source documents
+    ],
+    title="CSV Query Assistant",
+    description="Upload a CSV file and enter a query to retrieve relevant information."
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Launch the Gradio app
+interface.launch(share=True)