Update app.py

app.py

@@ -1,68 +1,91 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 import os
+import pandas as pd
+from langchain_openai import ChatOpenAI
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain_experimental.tools import PythonAstREPLTool
+from langchain_core.output_parsers.openai_tools import JsonOutputKeyToolsParser
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.messages import ToolMessage
+from langchain_core.runnables import RunnablePassthrough
+from operator import itemgetter
 
 api_key = os.getenv("secret_test_key")
 print(api_key)
 
-"""
-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 load_model(api_key):
+    return ChatOpenAI(
+        base_url="https://api.together.xyz/v1",
+        api_key=api_key,
+        model="mistralai/Mixtral-8x7B-Instruct-v0.1"
+    )
+def create_chain(df, llm):
+    tool = PythonAstREPLTool(locals={"df": df})
+    llm_with_tools = llm.bind_tools([tool], tool_choice=tool.name)
+    parser = JsonOutputKeyToolsParser(key_name=tool.name, first_tool_only=True)
+    
+    system = f"""You have access to a pandas dataframe `df`. Here is the output of `df.head().to_markdown()`:
+    ```
+    {df.head().to_markdown()}
+    ```
+    Given a user question, write the Python code to answer it. Don't assume you have access to any libraries other than built-in Python ones and pandas.
+    Respond directly to the question once you have enough information to answer it."""
+    
+    prompt = ChatPromptTemplate.from_messages([
+        ("system", system),
+        ("human", "{question}"),
+        MessagesPlaceholder("chat_history", optional=True),
+    ])
 
+    def _get_chat_history(x):
+        ai_msg = x["ai_msg"]
+        tool_call_id = x["ai_msg"].additional_kwargs["tool_calls"][0]["id"]
+        tool_msg = ToolMessage(tool_call_id=tool_call_id, content=str(x["tool_output"]))
+        return [ai_msg, tool_msg]
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+    chain = (
+        RunnablePassthrough.assign(ai_msg=prompt | llm_with_tools)
+        .assign(tool_output=itemgetter("ai_msg") | parser | tool)
+        .assign(chat_history=_get_chat_history)
+        .assign(response=prompt | llm | StrOutputParser())
+        .pick(["tool_output", "response"])
+    )
+    
+    return chain
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+def process_query(csv_file, api_key, query):
+    if not api_key.strip():
+        return "Please provide an API key"
+    
+    try:
+        df = pd.read_csv(csv_file.name)
+        llm = load_model(api_key)
+        chain = create_chain(df, llm)
+        result = chain.invoke({"question": query})
+        return f"Analysis Result:\n{result['response']}\n\nTechnical Details:\n{result['tool_output']}"
+    except Exception as e:
+        return f"Error: {str(e)}"
 
-    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)",
-        ),
+# Create Gradio interface
+iface = gr.Interface(
+    fn=process_query,
+    inputs=[
+        gr.File(label="Upload CSV File"),
+        gr.Textbox(label="Together.ai API Key", type="password"),
+        gr.Textbox(label="Your Question")
     ],
+    outputs=gr.Textbox(label="Result"),
+    title="CSV Analysis Assistant",
+    description="Upload a CSV file and ask questions about it using natural language.",
+    examples=[
+        ["data/titanic_dataset.csv", "your-api-key-here", "Which columns have missing values?"],
+        ["data/titanic_dataset.csv", "your-api-key-here", "What's the correlation between age and fare?"]
+    ]
 )
 
+# For Hugging Face Spaces deployment, add this:
+iface.launch()
 
-if __name__ == "__main__":
-    demo.launch()
+# if __name__ == "__main__":
+  #   demo.launch()