Spaces:
Build error
Build error
File size: 3,024 Bytes
d973e31 0e92e7d d973e31 1b85a7a 4366345 9b24efa 1b4ef3e 0752362 0e92e7d d973e31 4366345 2985c1b 0e92e7d 4366345 2985c1b 4366345 d973e31 1b85a7a d973e31 1b85a7a 1b4ef3e 1b85a7a 44c9f2d d973e31 ecd84d3 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 |
import gradio as gr
import os
from huggingface_hub import InferenceClient
from langgraph.prebuilt import create_react_agent
from search_agent import tools
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
from search_agent import tools
from langchain_core.messages import HumanMessage, AIMessage, SystemMessage
huggingfacehub_api_token = os.getenv('hf_api')
"""
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")
llm = HuggingFaceEndpoint(
repo_id="meta-llama/Llama-3.2-1B-Instruct" ,
huggingfacehub_api_token=huggingfacehub_api_token,
)
chat_model = ChatHuggingFace(llm=llm, verbose = True)
graph = create_react_agent(chat_model, tools=tools)
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
def convert(msg):
if msg["role"] in ["user", "human"]:
return HumanMessage(content=msg["content"])
elif msg["role"] in ["assistant", "ai"]:
return AIMessage(content=msg["content"])
elif msg["role"] == "system":
return SystemMessage(content=msg["content"])
else:
raise ValueError(f"Unsupported role: {msg['role']}")
inputs = {"messages": [convert(m) for m in messages]}
# Get the response from the agent (this integrates your agent with the model)
agent_response = graph.invoke(inputs) # Process the inputs through your agent
# Return the final message from the agent
return agent_response['messages'][-1][1]
"""
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()
|