github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9333] autogen #6094

New Issue
Open
opened 2026-04-12 17:25:37 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 17:25:37 -05:00
Owner
Copy Link

Originally created by @harrrrden on GitHub (Feb 25, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9333

When I use this code to build the agent, some local models can be used, while others cannot.

from autogen import AssistantAgent, UserProxyAgent

config_list = [
{
"model": "llama2:latest",
"base_url": "http://localhost:11434/v1",
"api_key": "ollama",
}
]

assistant = AssistantAgent("assistant", llm_config={"config_list": config_list})

user_proxy = UserProxyAgent("user_proxy", code_execution_config={"work_dir": "coding", "use_docker": False})
user_proxy.initiate_chat(assistant, message="Plot a chart of NVDA and TESLA stock price change YTD.")

For example, when I run the command:codellama，deepseek-r1 ，they are usable ，but when I try to use llama2, I get the following error:
openai.InternalServerError: Error code: 502
How can I resolve this issue?

os：windows

ollama version ： 0.5.7

Originally created by @harrrrden on GitHub (Feb 25, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9333 When I use this code to build the agent, some local models can be used, while others cannot. from autogen import AssistantAgent, UserProxyAgent config_list = [ { "model": "llama2:latest", "base_url": "http://localhost:11434/v1", "api_key": "ollama", } ] assistant = AssistantAgent("assistant", llm_config={"config_list": config_list}) user_proxy = UserProxyAgent("user_proxy", code_execution_config={"work_dir": "coding", "use_docker": False}) user_proxy.initiate_chat(assistant, message="Plot a chart of NVDA and TESLA stock price change YTD.") For example, when I run the command:codellama，deepseek-r1 ，they are usable ，but when I try to use llama2, I get the following error: openai.InternalServerError: Error code: 502 How can I resolve this issue? os：windows ollama version ： 0.5.7
GiteaMirror commented 2026-04-12 17:25:39 -05:00
Author
Owner
Copy Link

@lagane-78 commented on GitHub (Mar 5, 2025):

Seeing similar error but getting a 404 error although the model is there. I tried both llama3.2 and llama2. unfortunately we are not allowed to download deepseek :-(

Configure agents for Autogen to explicitly use Ollama
config_list = [{
"api_type": "ollama",
"model": "llama3",
"base_url": ":11434" # Explicitly define base_url
}]
llm_config = {
"config_list": config_list,
"cache_seed": 42
}

Initialize AssistantAgent with explicit Ollama config

assistant = autogen.AssistantAgent(
name="PII_Detector",
llm_config=llm_config, # Use fixed llm_config structure
system_message="You are an AI assistant specialized in detecting PII in text."
)

Debugging AssistantAgent

print(f"Debug: AssistantAgent configured with name '{assistant.name}' and system message '{assistant.system_message}'")

Initialize UserProxyAgent

user_proxy = autogen.UserProxyAgent(
name="User_Proxy",
human_input_mode="NEVER",
max_consecutive_auto_reply=1,
is_termination_msg=lambda x: "TERMINATE" in x.get("content", ""),
)

Debugging UserProxyAgent

print(f"Debug: UserProxyAgent configured with name '{user_proxy.name}' and human_input_mode '{user_proxy.human_input_mode}'")

Initiate the conversation

initial_message = "Identify any PII in this text: 'John Doe's SSN is 123-45-6789 and his account number is 56789 and he was born on 01/01/1990.'"
print(f"Debug: Initiating chat with message: '{initial_message}'")
user_proxy.initiate_chat(
assistant,
message=initial_message
)

raise ResponseError(e.response.text, e.response.status_code) from None

ollama._types.ResponseError: model "llama3" not found, try pulling it first (status code: 404)

Also tried llama2 or llama3.2:latest

<!-- gh-comment-id:2702106961 --> @lagane-78 commented on GitHub (Mar 5, 2025): Seeing similar error but getting a 404 error although the model is there. I tried both llama3.2 and llama2. unfortunately we are not allowed to download deepseek :-( Configure agents for Autogen to explicitly use Ollama config_list = [{ "api_type": "ollama", "model": "llama3", "base_url": "<local host>:11434" # Explicitly define base_url }] llm_config = { "config_list": config_list, "cache_seed": 42 } # Initialize AssistantAgent with explicit Ollama config assistant = autogen.AssistantAgent( name="PII_Detector", llm_config=llm_config, # Use fixed llm_config structure system_message="You are an AI assistant specialized in detecting PII in text." ) # Debugging AssistantAgent print(f"Debug: AssistantAgent configured with name '{assistant.name}' and system message '{assistant.system_message}'") # Initialize UserProxyAgent user_proxy = autogen.UserProxyAgent( name="User_Proxy", human_input_mode="NEVER", max_consecutive_auto_reply=1, is_termination_msg=lambda x: "TERMINATE" in x.get("content", ""), ) # Debugging UserProxyAgent print(f"Debug: UserProxyAgent configured with name '{user_proxy.name}' and human_input_mode '{user_proxy.human_input_mode}'") # Initiate the conversation initial_message = "Identify any PII in this text: 'John Doe's SSN is 123-45-6789 and his account number is 56789 and he was born on 01/01/1990.'" print(f"Debug: Initiating chat with message: '{initial_message}'") user_proxy.initiate_chat( assistant, message=initial_message ) raise ResponseError(e.response.text, e.response.status_code) from None ollama._types.ResponseError: model "llama3" not found, try pulling it first (status code: 404) Also tried llama2 or llama3.2:latest
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#6094
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?