app.py

import gradio as gr
from typing import TypedDict, Annotated
from huggingface_hub import InferenceClient, login, list_models
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFacePipeline
from langgraph.graph.message import add_messages
from langchain.docstore.document import Document
from langgraph.prebuilt import ToolNode, tools_condition
from langchain_core.messages import AnyMessage, HumanMessage, AIMessage
from langchain_community.retrievers import BM25Retriever
import os
from langgraph.graph import START, StateGraph
from langchain.tools import Tool
"""
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
"""
HUGGINGFACEHUB_API_TOKEN = os.environ["HUGGINGFACEHUB_API_TOKEN"]
login(token=HUGGINGFACEHUB_API_TOKEN, add_to_git_credential=True)

llm = HuggingFaceEndpoint(
    #repo_id="HuggingFaceH4/zephyr-7b-beta",
    repo_id="Qwen/Qwen2.5-Coder-32B-Instruct",
    task="text-generation",
    max_new_tokens=512,
    do_sample=False,
    repetition_penalty=1.03,
    timeout=240,
)

model = ChatHuggingFace(llm=llm, verbose=True)

def get_hub_stats(author: str) -> str:
    """
    You are a helpful chatbot for programmers and data scientists with access to the Hugging Face Hub. 
    Users will want to know the most popular models from Hugging Face. This tool will enable
    you to fetch the most downloaded model from a specific author on the Hugging Face Hub.
    """
    try:
        # List models from the specified author, sorted by downloads
        models = list(list_models(author=author, sort="downloads", direction=-1, limit=1))

        if models:
            model = models[0]
            return f"The most downloaded model by {author} is {model.id} with {model.downloads:,} downloads."
        else:
            return f"No models found for author {author}."
    except Exception as e:
        return f"Error fetching models for {author}: {str(e)}"

# Initialize the tool
hub_stats_tool = Tool(
    name="get_hub_stats",
    func=get_hub_stats,
    description="Fetches the most downloaded model from a specific author on the Hugging Face Hub."
)


def predict(message, history):
    # Convert Gradio history to LangChain message format
    history_langchain_format = []
    for msg in history:
        if msg['role'] == "user":
            history_langchain_format.append(HumanMessage(content=msg['content']))
        elif msg['role'] == "assistant":
            history_langchain_format.append(AIMessage(content=msg['content']))
    
    # Add new user message
    history_langchain_format.append(HumanMessage(content=message))
    
    # Invoke Alfred agent with full message history
    response = alfred.invoke(
        input={"messages": history_langchain_format},
        config={"recursion_limit": 100}
    )
    
    # Extract final assistant message
    return response["messages"][-1].content


# setup agents
tools = [hub_stats_tool]
#tools = [guest_info_tool]
chat_with_tools = model.bind_tools(tools)

# Generate the AgentState and Agent graph
class AgentState(TypedDict):
    messages: Annotated[list[AnyMessage], add_messages]

def assistant(state: AgentState):
    return {
        "messages": [chat_with_tools.invoke(state["messages"])],
    }

## The graph
builder = StateGraph(AgentState)

# Define nodes: these do the work
builder.add_node("assistant", assistant)
builder.add_node("tools", ToolNode(tools))

# Define edges: these determine how the control flow moves
builder.add_edge(START, "assistant")
builder.add_conditional_edges(
    "assistant",
    # If the latest message requires a tool, route to tools
    # Otherwise, provide a direct response
    tools_condition,
)
builder.add_edge("tools", "assistant")
alfred = builder.compile()


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    predict,
    type="messages"
)


if __name__ == "__main__":
    demo.launch()