app.py

from transformers import AutoModelForCausalLM, AutoTokenizer
import gradio as gr
import torch

import gradio as gr

from langchain import hub
from langchain.agents import AgentExecutor, create_openai_tools_agent, load_tools
from langchain_openai import ChatOpenAI
from gradio import ChatMessage
import gradio as gr

from dotenv import load_dotenv

load_dotenv()
# Environment variables
HF_TOKEN = os.environ.get('HF_TOKEN')  # Ensure token is set
#model = ChatOpenAI(temperature=0, streaming=True)

from langchain_community.llms import HuggingFaceEndpoint
from langchain_community.chat_models.huggingface import ChatHuggingFace

from transformers import BitsAndBytesConfig
#quantization to 8bit, must have GPU.
quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype="float16",
    bnb_4bit_use_double_quant=True,
)

# 2. Create model
model = HuggingFacePipeline.from_model_id(
    model_id="EpistemeAI/Fireball-Meta-Llama-3.1-8B-Instruct-Agent-0.003",
    task="text-generation",
    pipeline_kwargs=dict(
        max_new_tokens=2048,
        do_sample=False,
        repetition_penalty=1.03,
        return_full_text=False,
    ),
    model_kwargs={"quantization_config": quantization_config},
)

tools = load_tools(["serpapi"])

# Get the prompt to use - you can modify this!
prompt = hub.pull("hwchase17/openai-tools-agent")
# print(prompt.messages) -- to see the prompt
agent = create_openai_tools_agent(
    model.with_config({"tags": ["agent_llm"]}), tools, prompt
)
agent_executor = AgentExecutor(agent=agent, tools=tools).with_config(
    {"run_name": "Agent"}
)
async def interact_with_langchain_agent(prompt, messages):
    messages.append(ChatMessage(role="user", content=prompt))
    yield messages
    async for chunk in agent_executor.astream(
        {"input": prompt}
    ):
        if "steps" in chunk:
            for step in chunk["steps"]:
                messages.append(ChatMessage(role="assistant", content=step.action.log,
                                  metadata={"title": f"🛠️ Used tool {step.action.tool}"}))
                yield messages
        if "output" in chunk:
            messages.append(ChatMessage(role="assistant", content=chunk["output"]))
            yield messages


with gr.Blocks() as demo:
    gr.Markdown("# Chat with a LangChain Agent 🦜⛓️ and see its thoughts 💭")
    chatbot = gr.Chatbot(
        type="messages",
        label="Agent",
        avatar_images=(
            None,
            "https://em-content.zobj.net/source/twitter/141/parrot_1f99c.png",
        ),
    )
    input = gr.Textbox(lines=1, label="Chat Message")
    input.submit(interact_with_langchain_agent, [input_2, chatbot_2], [chatbot_2])

demo.launch()