Can someone offer insight onto why I'm getting this error on the chat interface: Final answer:
Error in generating final LLM output:
422 Client Error: Unprocessable Entity for url: https://api-inference.huggingface.co/models/Qwen/Qwen2.5-Coder-32B-Instruct/v1/chat/completions (Request ID: 4hvPgLzd1igXv0lnL5ato)

Input validation error: inputs tokens + max_new_tokens must be <= 16000. Given: 261329 inputs tokens and 2096 max_new_tokens
Make sure 'text-generation' task is supported by the model.

My code is as follows - I just tried to keep it simple with the prebuilt tool just to see if it would work, but no luck:

from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
import datetime
import requests
import pytz
import yaml
from tools.final_answer import FinalAnswerTool

from Gradio_UI import GradioUI
import duckduckgo_search

Below is an example of a tool that does nothing. Amaze us with your creativity !

@tool

class DuckDuckGoSearchTool(Tool):

name = "web_search"

description = "Performs a duckduckgo web search based on your query (think a Google search) then returns the top search results."

inputs = {'query': {'type': 'string', 'description': 'The search query to perform.'}}

output_type = "string"

def init(self, max_results=10, **kwargs):

super().init()

self.max_results = max_results

try:

from duckduckgo_search import DDGS

except ImportError as e:

raise ImportError(

"You must install package duckduckgo_search to run this tool: for instance run pip install duckduckgo-search."

) from e

self.ddgs = DDGS(**kwargs)

def forward(self, query: str) -> str:

results = self.ddgs.text(query, max_results=self.max_results)

if len(results) == 0:

raise Exception("No results found! Try a less restrictive/shorter query.")

postprocessed_results = [f"{result['title']}\n{result['body']}" for result in results]

return "## Search Results\n\n" + "\n\n".join(postprocessed_results)

@tool
def get_current_time_in_timezone(timezone: str) -> str:
"""A tool that fetches the current local time in a specified timezone.
Args:
timezone: A string representing a valid timezone (e.g., 'America/New_York').
"""
try:
# Create timezone object
tz = pytz.timezone(timezone)
# Get current time in that timezone
local_time = datetime.datetime.now(tz).strftime("%Y-%m-%d %H:%M:%S")
return f"The current local time in {timezone} is: {local_time}"
except Exception as e:
return f"Error fetching time for timezone '{timezone}': {str(e)}"

final_answer = FinalAnswerTool()

If the agent does not answer, the model is overloaded, please use another model or the following Hugging Face Endpoint that also contains qwen2.5 coder:

model_id='https://pflgm2locj2t89co.us-east-1.aws.endpoints.huggingface.cloud'

model = HfApiModel(
max_tokens=512,
temperature=0.5,
#model_id='Qwen/Qwen2.5-Coder-32B-Instruct',# it is possible that this model may be overloaded
custom_role_conversions=None,
)

Import tool from Hub

image_generation_tool = load_tool("agents-course/text-to-image", trust_remote_code=True)

with open("prompts.yaml", 'r') as stream:
prompt_templates = yaml.safe_load(stream)

agent = CodeAgent(
model=model,
tools=[get_current_time_in_timezone, final_answer], ## add your tools here (don't remove final answer)
max_steps=6,
verbosity_level=1,
grammar=None,
planning_interval=None,
name=None,
description=None,
prompt_templates=prompt_templates
)

GradioUI(agent).launch()