File size: 8,473 Bytes
acfd37c |
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 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 |
import os
from smolagents import CodeAgent, LiteLLMModel, load_tool, ToolCollection, HfApiModel, InferenceClientModel, TransformersModel, OpenAIServerModel
from smolagents import ToolCallingAgent, PythonInterpreterTool, tool, WikipediaSearchTool
from smolagents import DuckDuckGoSearchTool, FinalAnswerTool, VisitWebpageTool, SpeechToTextTool
from mcp import StdioServerParameters
from huggingface_hub import HfApi, login
from dotenv import load_dotenv
from typing import Optional
from models.gemini_model import GeminiModel
import requests
import re
import string
import random
import textwrap
import nltk
import spacy
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
@tool
def download_file(task_id: str) -> str:
"""
Returns the file path of the downloaded file.
Args:
task_id: the ID of the task to download the file for.
"""
# Implement your file download logic here
data = requests.get(f"{DEFAULT_API_URL}/files/{task_id}")
if data.status_code == 200:
file_path = f"/tmp/{task_id}"
with open(file_path, "wb") as file:
file.write(data.content)
return file_path
else:
raise Exception(f"Failed to download file: {data.status_code}")
@tool
def get_file_content_as_text(task_id: str) -> str:
"""
Returns the content of the file as text.
Args:
task_id: the ID of the task to get the file content for.
"""
# Implement your file content retrieval logic here
data = requests.get(f"{DEFAULT_API_URL}/files/{task_id}")
if data.status_code == 200:
return data.text
else:
raise Exception(f"Failed to get file content: {data.status_code}")
def load_hf_model(modelName: str):
"""
Lädt ein Hugging Face Modell und gibt den Agenten zurück.
:param modelName: Name des Modells
:return: model
"""
load_dotenv() # Lädt automatisch .env im Projektordner
hf_token = os.getenv("hugging_face")
login(token=hf_token) # Authentifizierung bei Hugging Face
# Modell initialisieren
model = HfApiModel(model_id=modelName)
return model
def load_ollama_model(modelName: str):
"""
Lädt ein Ollama Modell und gibt den Agenten zurück.
:param modelName: Name des Modells
:return: model
"""
# Modell initialisieren
model = OpenAIServerModel(model_id=modelName, api_base="http://localhost:11434/v1")
return model
def load_lmStudio_model(modelName: str):
"""
Lädt ein LM Studio Modell und gibt den Agenten zurück.
:param modelName: Name des Modells
:return: model
"""
# Modell initialisieren
#model = LiteLLMModel(model_id=modelName, api_base="http://localhost:1234")
model = OpenAIServerModel(model_id=modelName, api_base="http://localhost:1234/v1")
return model
def load_gemini_model():
"""
Lädt ein Gemini Modell und gibt den Agenten zurück.
:return: model
"""
try:
print(f"Gemini API Key: {os.getenv('GEMINI_API_KEY')}")
model = LiteLLMModel(model_id="gemini/gemini-2.0-flash-exp",
api_key=os.getenv("GEMINI_API_KEY"))
#model = GeminiModel(api_key=os.getenv("GEMINI_API_KEY"))
return model
except Exception as e:
print("Error loading Gemini model:", e)
return None
def get_agent(model_name:str, model_type:str) -> Optional[CodeAgent]:
# Modell initialisieren
match model_type:
case "hugging face":
model = load_hf_model(model_name)
case "Ollama":
model = load_ollama_model(model_name)
case "Gemini":
model = load_gemini_model()
case "LMStudio":
model = load_lmStudio_model(model_name)
case _:
print("Model type not supported.")
return None
#model = load_lmStudio_model("gemma-3-4b-it")
#model = load_gemini_model()
#mopip del = HfApiModel()
#model=InferenceClientModel(model_id="meta-llama/Meta-Llama-3.1-8B-Instruct")
#model = TransformersModel(model_id="HuggingFaceTB/SmolLM-135M-Instruct")
# Tools laden
web_search_tool = DuckDuckGoSearchTool()
final_answer_tool = FinalAnswerTool()
visit_webpage_tool = VisitWebpageTool()
#speech_to_text_tool = SpeechToTextTool()
#transcript_tool = load_tool("maguid28/TranscriptTool", trust_remote_code=True)
#mcp_tool_collection = ToolCollection.from_mcp(server_parameters, trust_remote_code=True)
#with ToolCollection.from_mcp(server_parameters, trust_remote_code=True) as tool_collection:
# mcp_tool_agent = CodeAgent(tools=[*tool_collection.tools], add_base_tools=True)
#server_parameters = StdioServerParameters(
# command="uv",
# args=["--quiet", "[email protected]"],
# env={"UV_PYTHON": "3.12", **os.environ},
#)
#
#with ToolCollection.from_mcp(server_parameters, trust_remote_code=True) as tool_collection:
# mcp_agent = CodeAgent(tools=[*tool_collection.tools], model=model, add_base_tools=True)
variation_agent = CodeAgent(
model=model,
tools=[PythonInterpreterTool()],
name="variation_agent",
description="Get the user question and checks if the given question makes sense at all, if not, we try to modify the text like reverse. Provide the content / the questin as the 'task' argument." \
"The agent can write professional python code, focused on modifiying texts." \
"It has access to the following libraries: re, string, random, textwrap, nltk and spacy." \
"The goal is to find out, if a user question is a trick, and we might modify the content.",
additional_authorized_imports=[
"re",
"string",
"random",
"textwrap",
"nltk",
"spacy"
]
)
variation_agent.system_prompt = "You are a text variation agent. You can write professional python code, focused on modifiying texts." \
"You can use the following libraries: re, string, random, textwrap, nltk and spacy." \
"Your goal is to find out, if a user question is a trick, and we might modify the content."
code_agent = CodeAgent(
name="code_agent",
description="Can generate code an run it. It provides the possibility to download additional files if needed.",
model=model,
tools=[download_file, PythonInterpreterTool(), get_file_content_as_text],
additional_authorized_imports=[
"geopandas",
"plotly",
"shapely",
"json",
"pandas",
"numpy",
],
verbosity_level=2,
#final_answer_checks=[FinalAnswerTool()],
max_steps=5,
)
final_answer_tool = FinalAnswerTool()
final_answer_tool.description = "You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string."
tool_agent = CodeAgent(
model=model,
tools=[web_search_tool, visit_webpage_tool, WikipediaSearchTool(), final_answer_tool],
verbosity_level=2,
max_steps=15,
managed_agents=[code_agent, variation_agent],
planning_interval=5,
)
return tool_agent
# return tool_agent
manager_agent = CodeAgent(
#model=HfApiModel("deepseek-ai/DeepSeek-R1", provider="together", max_tokens=8096),
model=model,
tools=[web_search_tool, visit_webpage_tool],
# managed_agents=[mcp_tool_agent],
additional_authorized_imports=[
"geopandas",
"plotly",
"shapely",
"json",
"pandas",
"numpy",
],
planning_interval=5,
verbosity_level=2,
#final_answer_checks=[FinalAnswerTool()],
max_steps=15
)
return manager_agent |