File size: 2,736 Bytes
278550c
 
 
 
9b5b26a
 
 
 
c19d193
6aae614
93a8d57
8fe992b
9b5b26a
 
278550c
9b5b26a
 
278550c
 
 
 
 
e60ce2a
 
 
 
9b5b26a
278550c
 
 
 
 
 
5acca6b
8c01ffb
278550c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8c01ffb
278550c
975a609
 
6aae614
ae7a494
 
 
 
e121372
bf6d34c
 
29ec968
fe328e0
13d500a
8c01ffb
 
9b5b26a
 
8c01ffb
861422e
 
9b5b26a
8c01ffb
8fe992b
975a609
8c01ffb
 
 
 
 
 
861422e
8fe992b
 
9b5b26a
8c01ffb
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
"""
This app.py consitutes an application where users can pose queries to
an agent about plants.
"""
from smolagents import CodeAgent,DuckDuckGoSearchTool, HfApiModel,load_tool,tool
import datetime
import requests
import pytz
import yaml
from tools.final_answer import FinalAnswerTool
from huggingface_hub import InferenceClient

from Gradio_UI import GradioUI



@tool
def describe_plant_image(user_query: str, image_url: str) -> str:
    """
    Describe a plant image and answer the user's query.
    Only to be used if and only if a user provides an image_url or if
    prior chat messages have retrieved image_url(s).

    Args:
        user_query: Any relevant text pertaining to the image_url that has been based off the chat
        image_url: The image url that has been provided by the user 
    """
    system_prompt = (
        "You are an LLM assistant that analyzes plant images and:\n"
        "1. Identifies the plant if possible\n"
        "2. Describes key visible characteristics\n"
        "3. Answers the user's question clearly and concisely"
    )
    vl_model = InferenceClient(model="CohereLabs/aya-vision-32b:cohere")

    response = vl_model.chat.completions.create(
        messages=[
            {
                "role": "system",
                "content": system_prompt,
            },
            {
                "role": "user",
                "content": [
                    {"type": "text", "text": user_query},
                    {
                        "type": "image_url",
                        "image_url": {"url": image_url},
                    },
                ],
            },
        ]
    )

    return response.choices[0].message.content

query_internet = DuckDuckGoSearchTool()
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=2096,
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=[query_internet, describe_plant_image, 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()