AutoGen Studio and AutoGen v0.4 [Status Updates, Discussion]

[victordibia]

Hi all,

We are rewriting AutoGen Studio to take advantage of new features coming in AutoGen 0.4, as outlined in our readme. The goal of AutoGen Studio remains to create a tool to rapidly prototype, and debug multi-agent applications. This post updates developers on our progress and provides information for those interested in contributing or testing.

Note: See the documentation and FAQ page here for questions

See this video for a walkthrough of features - https://youtu.be/oum6EI7wohM

Installation Options

You can find the current version's code in autogen/python/packages/autogen-studio. There are two ways to install:

1. Recommended Method: Install the latest dev version from PyPI:

pip install -U autogenstudio 

run the app

autogenstudio ui --appdir new

The command above tells AGS to store files in the new directory (avoiding conflicts with previous versions)

if you would like to force autoupgrade your db (still experimental)

autogenstudio ui --upgrade-database

2. Advanced Method: Install from source by following the AutoGen Studio readme. Note that this method is more complex and better suited for experienced users.

Development Status

While we're still in early development, you can view our planned features here.

Some Key Improvements

The new AutoGen v0.4 API introduces asynchronous operation, which enables seamless message passing between agents. This enhancement particularly benefits end-user applications by adding several crucial features that were difficult to implement in the previous version:

New Features Already Available:

• Real-time agent updates streaming to the frontend
• Run control: You can now stop agents mid-execution if they're heading in the wrong direction, adjust the team, and continue
• Interactive feedback: Add a UserProxyAgent to get human input through the UI during team runs
• Message flow visualization: See how agents communicate with each other
• Ability to import specifications from external galleries
• Ability to wrap agent teams into an API using the AutoGen Studio CLI

Features Coming Soon:

See the roadmap here for planned features. Some include:

• Implement a drag and drop team builder interface for AGS #4202
• Ability to attach 3rd party or local gallery of components to AGS #4203

We welcome your feedback and contributions if you've had a chance to try the new version.

[SailorJoe6]

Just wanted to say, this looks pretty amazing!

[victordibia]

Thanks! @SailorJoe6, I seem to have gotten a notification on a session issue you reported, but cant seem to find that right now.
Any chance you can point me to it (assuming there was indeed an issue)?
Many thanks

[inayatwali]

This is great!

[SailorJoe6]

Last issue I reported was on the old version. Nothing reported against this one.

[victordibia]

Got it, thank you!

[mkarpovi-amd]

Attempting to create a team gives me an error reading: "POST /api/teams/ HTTP/1.1" 422 Unprocessable Entity. I made a clean Conda environment and installed ags v.0.4.0.dev37 with pip. Do you have any idea what might cause this?

[victordibia]

Thanks. Let me debug this a bit more in a new GH spaces env.
Will post any updates.

[victordibia]

I am unable to replicate this issue in fresh GH space.

autogenstudio ui --appdir new

Runs the app in a new directory, teams can be created and tasks run (after an openai_api_key is set).

Any chance you can share full logs from autogenstudio ui --appdir new

[mkarpovi-amd]

I seem to get a lot of messages like this:

INFO: Will watch for changes in these directories: ['C:\Users\mkarpovi']
INFO: Uvicorn running on http://127.0.0.1:7002 (Press CTRL+C to quit)
WARNING: --reload-include and --reload-exclude have no effect unless watchfiles is installed.
INFO: Started reloader process [636724] using StatReload
2024-11-22 14:20:49.704 | INFO | autogenstudio.web.initialization:init:38 - Initialized application data folder: new
INFO: Started server process [624616]
INFO: Waiting for application startup.
2024-11-22 14:20:49.738 | INFO | autogenstudio.web.app:lifespan:34 - Initializing application...
2024-11-22 14:20:49.746 | INFO | autogenstudio.database.schema_manager:init:64 - Initializing new Alembic configuration
2024-11-22 14:20:49.748 | INFO | autogenstudio.database.schema_manager:_initialize_alembic:141 - Initializing Alembic configuration...
2024-11-22 14:20:49.751 | INFO | autogenstudio.database.schema_manager:_initialize_alembic:152 - Created new env.py
2024-11-22 14:20:49.752 | INFO | autogenstudio.database.schema_manager:_initialize_alembic:158 - Created alembic.ini
2024-11-22 14:20:49.767 | INFO | autogenstudio.database.db_manager:init:56 - Schema status: Schema needs upgrade but auto_upgrade is disabled. Status: Unmigrated changes detected:
('add_table', Table('agent', MetaData(), Column('id', Integer(), table=, primary_key=True, nullable=False), Column('created_at', DateTime(timezone=True), table=, server_default=DefaultClause(<sqlalchemy.sql.functions.now at 0x287a457dd00; now>, for_update=False)), Column('updated_at', DateTime(timezone=True), table=, onupdate=ColumnElementColumnDefault(<sqlalchemy.sql.functions.now at 0x287a457df70; now>)), Column('user_id', AutoString(), table=), Column('version', AutoString(), table=, default=ScalarElementColumnDefault('0.0.1')), Column('config', JSON(), table=), schema=None))
('add_table', Table('model', MetaData(), Column('id', Integer(), table=, primary_key=True, nullable=False), Column('created_at', DateTime(timezone=True), table=, server_default=DefaultClause(<sqlalchemy.sql.functions.now at 0x287a4542450; now>, for_update=False)), Column('updated_at', DateTime(timezone=True), table=, onupdate=ColumnElementColumnDefault(<sqlalchemy.sql.functions.now at 0x287a457cb60; now>)), Column('user_id', AutoString(), table=), Column('version', AutoString(), table=, default=ScalarElementColumnDefault('0.0.1')), Column('config', JSON(), table=), schema=None))
('add_table', Table('team', MetaData(), Column('id', Integer(), table=, primary_key=True, nullable=False), Column('created_at', DateTime(timezone=True), table=, server_default=DefaultClause(<sqlalchemy.sql.functions.now at 0x287a457c9e0; now>, for_update=False)), Column('updated_at', DateTime(timezone=True), table=, onupdate=ColumnElementColumnDefault(<sqlalchemy.sql.functions.now at 0x287a457d340; now>)), Column('user_id', AutoString(), table=), Column('version', AutoString(), table=, default=ScalarElementColumnDefault('0.0.1')), Column('config', JSON(), table=), schema=None))
('add_table', Table('tool', MetaData(), Column('id', Integer(), table=, primary_key=True, nullable=False), Column('created_at', DateTime(timezone=True), table=, server_default=DefaultClause(<sqlalchemy.sql.functions.now at 0x287a4127140; now>, for_update=False)), Column('updated_at', DateTime(timezone=True), table=, onupdate=ColumnElementColumnDefault(<sqlalchemy.sql.functions.now at 0x287a442a000; now>)), Column('user_id', AutoString(), table=), Column('version', AutoString(), table=, default=ScalarElementColumnDefault('0.0.1')), Column('config', JSON(), table=), schema=None))
('add_table', Table('agentmodellink', MetaData(), Column('agent_id', Integer(), ForeignKey('agent.id'), table=, primary_key=True, nullable=False), Column('model_id', Integer(), ForeignKey('model.id'), table=, primary_key=True, nullable=False), Column('sequence', Integer(), table=, primary_key=True, nullable=False, default=ScalarElementColumnDefault(0)), schema=None))
('add_table', Table('agenttoollink', MetaData(), Column('agent_id', Integer(), ForeignKey('agent.id'), table=, primary_key=True, nullable=False), Column('tool_id', Integer(), ForeignKey('tool.id'), table=, primary_key=True, nullable=False), Column('sequence', Integer(), table=, primary_key=True, nullable=False, default=ScalarElementColumnDefault(0)), schema=None))
('add_table', Table('session', MetaData(), Column('id', Integer(), table=, primary_key=True, nullable=False), Column('created_at', DateTime(timezone=True), table=, server_default=DefaultClause(<sqlalchemy.sql.functions.now at 0x287a45c8080; now>, for_update=False)), Column('updated_at', DateTime(timezone=True), table=, onupdate=ColumnElementColumnDefault(<sqlalchemy.sql.functions.now at 0x287a45c9eb0; now>)), Column('user_id', AutoString(), table=), Column('version', AutoString(), table=, default=ScalarElementColumnDefault('0.0.1')), Column('team_id', Integer(), ForeignKey('team.id'), table=), Column('name', AutoString(), table=), schema=None))
('add_table', Table('teamagentlink', MetaData(), Column('team_id', Integer(), ForeignKey('team.id'), table=, primary_key=True, nullable=False), Column('agent_id', Integer(), ForeignKey('agent.id'), table=, primary_key=True, nullable=False), Column('sequence', Integer(), table=, primary_key=True, nullable=False, default=ScalarElementColumnDefault(0)), schema=None))
('add_table', Table('run', MetaData(), Column('id', Uuid(), table=, primary_key=True, nullable=False, default=CallableColumnDefault(<function uuid4 at 0x00000287A46107C0>)), Column('created_at', DateTime(timezone=True), table=, server_default=DefaultClause(<sqlalchemy.sql.functions.now at 0x287a45ca4b0; now>, for_update=False)), Column('updated_at', DateTime(timezone=True), table=, onupdate=ColumnElementColumnDefault(<sqlalchemy.sql.functions.now at 0x287a45ca7b0; now>)), Column('session_id', Integer(), ForeignKey('session.id'), table=, nullable=False), Column('status', Enum('CREATED', 'ACTIVE', 'COMPLETE', 'ERROR', 'STOPPED', name='runstatus'), table=, nullable=False, default=ScalarElementColumnDefault(<RunStatus.CREATED: 'created'>)), Column('error_message', AutoString(), table=), Column('run_meta', JSON(), table=), Column('version', AutoString(), table=, default=ScalarElementColumnDefault('0.0.1')), schema=None))
('add_index', Index('ix_run_id', Column('id', Uuid(), table=, primary_key=True, nullable=False, default=CallableColumnDefault(<function uuid4 at 0x00000287A46107C0>))))
('add_table', Table('message', MetaData(), Column('id', Integer(), table=, primary_key=True, nullable=False), Column('created_at', DateTime(timezone=True), table=, server_default=DefaultClause(<sqlalchemy.sql.functions.now at 0x287a457f6b0; now>, for_update=False)), Column('updated_at', DateTime(timezone=True), table=, onupdate=ColumnElementColumnDefault(<sqlalchemy.sql.functions.now at 0x287a457f3b0; now>)), Column('user_id', AutoString(), table=), Column('version', AutoString(), table=, default=ScalarElementColumnDefault('0.0.1')), Column('config', JSON(), table=), Column('session_id', Integer(), ForeignKey('session.id'), table=), Column('run_id', Uuid(), ForeignKey('run.id'), table=), Column('message_meta', JSON(), table=), schema=None))
2024-11-22 14:20:49.882 | INFO | autogenstudio.database.db_manager:create_db_and_tables:128 - Database tables created successfully
2024-11-22 14:20:49.884 | INFO | autogenstudio.web.app:lifespan:38 - Managers initialized successfully
2024-11-22 14:20:49.884 | INFO | autogenstudio.web.app:lifespan:41 - Application startup complete
INFO: Application startup complete.

The other issue is that I intend to do LLM inference through a local corporate gateway (which i accessed on 0.1.5 by modifying source to pass the relevant headers)--but I don't think I have got to the relevant point yet.

[victordibia]

I agree that we have not gotten to the LLM part yet (there is some work to be done there as its mostly the OpenAI client supported now).

I just made a dev release - 0.4.0.dev38 that fixes the Unmigrated changes detected issues above (though I dont think that should be what is preventing teams from being created).

pip install autogenstudio==0.4.0.dev38 

[victordibia]

@mkarpovi-amd .. still having issues?

[rajramakalai]

Can you help with how to define a ollama model on the json structure please
"model_client": {
"component_type": "model",
"model": "gpt-4o-2024-08-06",
"model_type": "OpenAIChatCompletionClient"
}

[ekzhu]

You need to add model capabilities.

[rajramakalai]

Got it working, Thank you, but running from source, and adding the model names to the _model_info.py
with model client as
"model_client": {
"api_key": ".",
"base_url": "http://localhost:11434/v1",
"component_type": "model",
"model": "phi3.5",
"model_type": "OpenAIChatCompletionClient"
}

[Umopepisdn]

Is there a way to do this without editing core files and building from source? Some way to apply these via config?

[victordibia]

Hi @Umopepisdn ,

Can you try the updated documenation here? You should not need to build from source to use a custom model ...
https://microsoft.github.io/autogen/dev/user-guide/autogenstudio-user-guide/faq.html#q-can-i-use-other-models-with-autogen-studio

Please ensure you have the latest autogenstudio install.

{
  "provider": "autogen_ext.models.openai.OpenAIChatCompletionClient",
  "component_type": "model",
  "version": 1,
  "component_version": 1,
  "description": "Chat completion client for OpenAI hosted models.",
  "label": "OpenAIChatCompletionClient",
  "config": {
    "model": "TheBloke/Mistral-7B-Instruct-v0.2-GGUF",
    "model_info": {
      "vision": false,
      "function_calling": true,
      "json_output": false,
      "family": "unknown"
    },
    "base_url": "http://localhost:1234/v1"
  }
}

[asheeshgarg]

I have pip install dev38 I am trying to use AzureOpenAIChatCompletionClient what all env varibale need to set or is there any way to set in studio directly?

[victordibia]

Hi @asheeeshgarg,

There is a bit of work to be done here.
Mostly around supporting the AzureOpenAI client Params as defined here https://microsoft.github.io/autogen/dev/user-guide/core-user-guide/framework/model-clients.html#azure-openai

I’ll take a look later today or tomorrow and provide updates

[lbalceda]

Hello @victordibia any updates on this one ? I also tried setting the various params but it seems to be requiring an OpenAIChatCompletionClient currently

[victordibia]

Hi @lbalceda ,

This took a while but now AOAI client spec with an api_key field is now supported.
Docs here

{
  "provider": "autogen_ext.models.openai.AzureOpenAIChatCompletionClient",
  "component_type": "model",
  "version": 1,
  "component_version": 1,
  "description": "Chat completion client for Azure OpenAI hosted models.",
  "label": "AzureOpenAIChatCompletionClient",
  "config": {
    "model": "gpt-4o",
    "api_key": "sk-...",
    "azure_endpoint": "https://{your-custom-endpoint}.openai.azure.com/",
    "azure_deployment": "{your-azure-deployment}",
    "api_version": "2024-06-01"
  }
}

You will need the latest version https://pypi.org/project/autogenstudio/#history

[joslat]

As mentioned at https://www.linkedin.com/posts/dibiavictor_multiagentsystems-multiagentbook-autogen-activity-7271945150925299712-4g_u?utm_source=share&utm_medium=member_desktop I'd like to beta-test and provide feedback - Is there anything additional to the instructions already stated here?
Or just install and "let the games begin"?

If I've got the "old one" in place, any recommendation on how to properly "clean up" previously?

One additional question, is there a timeline where this will be "released"?

[harrywang]

I am also curious about the release date. thanks!

[victordibia]

Hi @joslat ,

The installation instructions are as above. A new conda env and using the --appdir flag is recommended.
Release date ~ Jan 15.
Roadmap is here #4006

[Knucklessg1]

This is so cool, I missed this update as I was working on the forked repository build-with-ag2. What are the plans on moving Studio to its own Repo?
It'll help avoid this confusion 😅

[victordibia]

@Knucklessg1 ,I agree that there should be an easy way to keep track of progress. Perhaps a separate repo might be valuable at some point. We will consider this.
In the meantime, please try out the new capabilities and share feedback!
v1 for the drag and drop composition feature just landed yesterday - what do you think?

ags_1080.mp4

[harrywang]

I can't agree more - a separate repo should be much better - it's hard to follow the updates in the current setup.

[Knucklessg1]

@victordibia I would like to add a section for RAG. Would that be a "Tool" item that can be added to only User Proxy Agents? Or would that be it's own section?

[victordibia]

Hi @Knucklessg1 ,
I agree that supporting some type of generalized RAG pattern would extremely useful.
What do you think of the proposal and plan in issue #4707
#4707

cc @ekzhu

[ekzhu]

A stateful Tool for RAG is a good start and super easy to integrate.

[lepulepu1198]

Hi there, I'm a university student from China. Can't wait to apply this amazing framework into my research!

I'm wondering if model: qwen by Aliyun could be supported in the future? I've tried to link it to this framework but failed in the end.

[lepulepu1198]

Thanks for reply, but the Qwen model is running by Alibaba Cloud rather than working on my local server. It used to work at previous version of 0.1.5.

What I did in the past to call this model is just fill the api key, model name and base_url in version of 0.1.5; But it seems that no place for me to do the same thing.

THANKS!

[victordibia]

Yes, the updated model client needs the model_capabilities field.
As long as your model is OpenAI compliant, the solution I mentioned above should work (after you add model_capabilities) ... it does not have to be a local model. Any model API endpoint that is openai compliant should work.
This link says the Alibaba ChatCompletion endpoints are openai compliant, so it should work

"model": "qwen-max-latext",
  "model_type": "OpenAIChatCompletionClient",
  "base_url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", #..replace this
  "api_version": "1.0",
  "component_type": "model",
  "model_capabilities": {
    "vision": false,
    "function_calling": false,
    "json_output": false
  }

What errors are you seeing?
You can also open a new discussion thread for us to discuss this more

[lepulepu1198]

Thanks for the reply,

I've changed the code as you said, and firstly it requires me to allow the function calling capability.

Once I set "true" for function_calling, there is no reported errors in the playground, but I can see errors in the terminal of pycharm, which shows that my api_key is invalid.

Thanks for your help again!

[victordibia]

Good progress. I think we are almost there.

• The error suggests that it tried to hit the OpenAI endpoint ....(this is not what we want)
• To provide the right endpoint, we need to set the base_url. I see in your screenshot that you have not set the base URL.
• You will need to set base url to your alibaba cloud base url"base_url": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1",

Can you confirm you have set it?

[lepulepu1198]

Appreciate it, but this is what happens after setting the "base_url" that you provided.

Then I tried to check the instructions on Alibaba cloud, it shows the "base_url" I need to use is "base_url": "https://dashscope.aliyuncs.com/compatible-mode/v1".

But here is what happened after changing the base_url.

[brandonscottbarney]

You mentioned on X that "If you’d like to beta test and provide feedback (or are already beta testing) , comment on the GitHub discussion thread in the comment section below," so I'm very interested as I just came across your research scrolling through NeurIPS2024 posts

[victordibia]

Hi @brandonscottbarney ,

Thanks! The installation instructions are exactly as above nothing else required ...

---

1. Recommended Method: Install the latest dev version from PyPI:

pip install autogenstudio==0.4.0.dev41

run the app

autogenstudio ui --appdir new

The command above tells AGS to store files in the new directory (avoiding conflicts with previous versions)

if you would like to force autoupgrade your db (still experimental)

autogenstudio ui --upgrade-database

[sean-josiah7]

Suggestion: on project/task executions... make Orcehstrator plans moderated/editable in interface by human in the loop.
On completion... Have the orchestator perform an afteraction analysis, looking to improve the prompt, the plan and product, convert this summarize where possible, abstract into a recipe/blueprint with configurable elements.

[ekzhu]

This is a great suggestion. Could you open an issue with the suggestions?

This requirement touches on the AgentChat library which runs the backend of studio. You can take a look at the orchestrator here:

python/packages/autogen-agentchat/src/autogen_agentchat/teams/_group_chat/_magentic_one

[victordibia]

I agree with Eric. There are several good ideas that could be come patterns that we support in AgentChat.

• A planner orchestrator (iterates with users on a plan before exploring the task to a set of fixed teams)
• An automatic orchestrator (iterates on plan with user, defines teams automatically etc)

[sean-josiah7]

done: #4764

…

On Thu, Dec 19, 2024 at 1:35 PM Victor Dibia ***@***.***> wrote: I agree with Eric. There are several good ideas that could be come patterns that we support in AgentChat. - A planner orchestrator (iterates with users on a plan before exploring the task to a set of fixed teams) - An automatic orchestrator (iterates on plan with user, defines teams automatically etc) — Reply to this email directly, view it on GitHub <#4208 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AXSWEMPW3BI2FKXW4HFA4CL2GMGWLAVCNFSM6AAAAABR2JZNSCVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTCNRSGA4DCNA> . You are receiving this because you commented.Message ID: ***@***.***>

[soichisumi]

The progress in v0.4 of autogen is excellent.
Are there any plans to support a production environment like semantic kernel?
I am concerning that it will only cover a portion of the autogen functionality I need.
ref: https://devblogs.microsoft.com/semantic-kernel/microsofts-agentic-ai-frameworks-autogen-and-semantic-kernel/

Or I would like to know if there is a guide for deploying a multi-AI agent system developed with autogen v0.4 in the cloud.

[cbyitina]

Hi team,
Does the latest v0.4 autogen-studio support LocalCommandLineCodeExecutor in any of the agents? Just like what we have in v0.2? e.g automatically execute the code blocks from the previous agent response. Thanks.

[victordibia]

Hi @cbyitina ,

We do not have this fully integrated.
I just opened an issue to track progress on this #5009

[cbyitina]

@victordibia Awesome! Looking forward to it. Thanks, Victor.

[harrywang]

Given the stable v0.4 is released today, I am looking forward to trying the updated Autogen Studio for v0.4 - any updates on the progress? the target date for the official first stable release? thanks!

[victordibia]

Hi @harrywang, we do have a release, testing is in progress ..

pip install autogenstudio

Let me know if you are having any issues.

[TanzeelurRashid]

Yes, I faced many issues, like agents are not able to use skills. Workflow is just providing empty messages amongst agents.

[asheeshgarg]

@victordibia I install the autogenstudio 0.4.0.1
autogen-agentchat 0.4.0.dev13
autogen-core 0.4.0.dev13
autogen-ext 0.4.0.dev13
autogenstudio 0.4.0.1

Seems agentstudio is still pulling dev dependencies

[victordibia]

Hi @asheeshgarg ,

Thanks for pointing out the issue.
We have fixed with an updated version 0.4.0.1

Please use pip install -U autogenstudio

Let me know if you are still seeing these errors.

[ekzhu]

0.4.0.2

[highyield3011]

Hi @victordibia,

We are using AutoGen Studio but didn't find where to configure api key for Azure Open AI.
Could you please guide us on this point?

There is no api key field in team builder configuration panel:

Switching code view and added api key manually as below, it still didn't work:

Also the setting page is always in status of "Work in process...":

[highyield3011]

Hi @victordibia @ivanvaccarics

Thank you both for guiding me on this configuration. It works now~!

[highyield3011]

Hi @victordibia ,

The AutoGen is running good after testing.

I'm actually not a very experienced programmer so I am not able to dig the coding very deeply. So I want to understand if it is possible to refer the coding under main branch to implement a totally local multi-agent AI application ourselves?

[highyield3011]

I mean, implement coding changes ourselves based on this project

[victordibia]

Yes,
If you would like a simple example with a UI, try the following:

• AutoGen + Chainlit example - https://github.com/microsoft/autogen/tree/main/python/samples/agentchat_chainlit .. you can easily build a UI with little code
• AutoGen + Web App (React) https://github.com/victordibia/autogen-ui - needs some familiarity with react/web apps but shows how you cna build one.

[highyield3011]

Hi @victordibia ,

Great!!! Thanks a lot~~~

[hgulersen]

Hi there - I looked and searched everywhere in the v0.4 docs however I couldn't find anything related to AWS Bedrock support. For v0.2 there is comprehensive documentation around non-OpenAI models: https://microsoft.github.io/autogen/0.2/docs/topics/non-openai-models/cloud-bedrock/

Can you shed some light on this? I couldn't find it in the extensions either. Does this mean there is no AWS Bedrock support for v0.4 at the moment?

[asheeshgarg]

Bedrock support is a important support feature we are looking at as well.

[ekzhu]

@asheeshgarg For v0.2, we have extensive clients, but they were not maintained well. Going forward, for hosted LLM APIs, we recommend ecosystem integration, and community-based management:

1. Use ecosystem adapters such as SemanticKernelModelClientAdapter Semantic kernel model adapter #4851 to use Semantic Kernel's AWS Bedrock client (https://devblogs.microsoft.com/semantic-kernel/introducing-aws-bedrock-with-semantic-kernel/)
2. You or others in the community to create and maintain a client for AWS bedrock.

We take this approach because we want less fragmentations, and better maintenance experience for everyone.

[asheeshgarg]

Thanks

[hgulersen]

If anyone bumps into this, v0.4 still works with LiteLLM, which supports Bedrock (and many other non openai providers). It just adds complexity since you'll have to also maintain the proxy but in case you are willing to do that, this is how it works.

@asheeshgarg @ekzhu I'd suggest making this approach much more visible in documentation. Someone who doesn't know this option might just walk away. Is there a reason why this is not being promoted?

• Install LiteLLM proxy
  pip install 'litellm[proxy]'

• Create a config.yaml. For example:

litellm_settings:
  modify_params: true
model_list:
  - model_name: llama70
    litellm_params:
      model: bedrock/meta.llama3-1-70b-instruct-v1:0
      aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
      aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
      aws_session_token: os.environ/AWS_SESSION_TOKEN
      aws_region_name: us-west-2

• Start the proxy:
  litellm --config path/to/your/config.yaml

• Then in your code, you can just use the OpenAIChatCompletionClient like so:

OpenAIChatCompletionClient(
        model="llama70", # this is the model name from your litellm config
        api_key="not-required",
        base_url="http://0.0.0.0:4000",
        model_info={
            "json_output": False,
            "vision": False,
            "function_calling": True,
            "family": "foobar",
        },
    )

[ekzhu]

@hgulersen thank you!

You are right, we should document this. Created issue: #5118

[TanzeelurRashid]

I have successfully run AutoGen Studio 0.4.3. However, the GUI for building a team is currently difficult to handle in the window, especially when adding agents. Additionally, I couldn't install it on Python 3.13 but it works on Python 3.12. Could you please provide a tutorial to start working on the new interface?

[sabrishs]

Is there a way I can add inter-team coordination? Also, the document says "Agents communicate through asynchronous messages, supporting both event-driven and request/response interaction pattern". Is there a way to define this explicitly in the AGS? Basically a proper workflow to control the agent coordination would be very useful.

[joslat]

I support this - I would like for example that one agent produces some content (code, writing an article, analyzing a stock, searching...) and then I can delegate to a critic agent that wraps a set of specialized agent, in case of the writer I could have:

• SEO reviewer
• Style reviewer
• Typho checker
• fact checker (grounding verifier)
• GDPR checker
• Structure reviewer

and more... I'd like to call them in parallel, return to the Critic and the critic delivers a summarized critic with all the specialized agents feedback to the writer...

I believe it makes sense, thoughts?

[ekzhu]

Overwhelming asks for #4623

[vladtsit]

Hi, is it possible to see message history log in AutoGen Studio? I'm learning how it works, but without understanding what is happening during team work it is difficult to craft system messages for selector and agents.

[ekzhu]

LLM call logging can be enabled setting the following logger:

https://microsoft.github.io/autogen/stable/reference/python/autogen_core.html#autogen_core.EVENT_LOGGER_NAME

Also, you can turn on agentchat specific logger: https://microsoft.github.io/autogen/stable/reference/python/autogen_agentchat.html

[ekzhu]

Related issue to follow: #5220 #5127

[vladtsit]

@ekzhu Great to hear about such possibility. I use exclusively autogen studio, could you please help me understand how to enable call logging and agentchat specific logger in team builder json if possible. In case it is possible, please point me to docs which explain how to configure autogen which serves the studio.

[victordibia]

@vladtsit ,
This is not currently a feature in AutoGen Studio?
But we could work together to add it, afterall, AGS is a debugging tool and being able to trace events is valuable for debugging system behaviour.
I just created an issue? #5440
Can you comment on it and describe if it will address the use case you have in mind?

[vladtsit]

commented #5440

[tjroamer]

With the latest version in the main branch, custom galleries are not persisted.

For example, if I opened a browser and added a new gallery, the new gallery is not visible if I open the same link in another browser. By default, teams, runs, and messages are written into autogen0404.db, but the info of gallery is not. Am I missing any configuration, or is it an issue?

[dominiclachance]

Am I wasting my time adding tools? Are they persistent and saved to database?

[zimmermannro]

@victordibia I have been working to connect Autogen-Studio to Azure OpenAI, used the following setting for the model which always gives a 404-error. The endpoint and API-Key are working, I checked that in separate python code in the same VENV. Any idea what is wrong?

What is working perfectly now is a local Ollama-LLM via this setting I found here in the comments:

By the way: Great new video on AutogenStudio, more of that please 👍

[victordibia]

Hi @zimmermannro ,

The config you have looks correct.
Can you do the following? Create your model client python, test it and then export to json.
https://microsoft.github.io/autogen/dev/user-guide/autogenstudio-user-guide/faq.html

from autogen_core.models import UserMessage 
from autogen_ext.models.openai import AzureOpenAIChatCompletionClient 

az_model_client = AzureOpenAIChatCompletionClient(
    azure_deployment="{your-azure-deployment}",
    model="gpt-4o",
    api_version="2024-06-01",
    azure_endpoint="https://{your-custom-endpoint}.openai.azure.com/",
    api_key="sk-...",
)

messages = [
    UserMessage(content="What is the capital of France?", source="user"),
]
response = await az_model_client.create(messages=messages)

# Print the response
print(response.content)

print(az_model_client.dump_component().model_dump_json())

should show something like:

{
  "provider": "autogen_ext.models.openai.AzureOpenAIChatCompletionClient",
  "component_type": "model",
  "version": 1,
  "component_version": 1,
  "description": "Chat completion client for Azure OpenAI hosted models.",
  "label": "AzureOpenAIChatCompletionClient",
  "config": {
    "model": "gpt-4o",
    "api_key": "sk-...",
    "azure_endpoint": "https://{your-custom-endpoint}.openai.azure.com/",
    "azure_deployment": "{your-azure-deployment}",
    "api_version": "2024-06-01"
  }
}

There should be no difference in behaviour between what you have in python and what is in AGS.
Let me know if you figure out the issue

[zimmermannro]

Dear @victordibia
Your code sample brought me to find out, that there is an empty init.py here on the current GIT and it was empty in my installation, too:
python/packages/autogen-ext/src/autogen_ext/models/init.py

I took info from the last previous version and added to the init.py only these to imports:

from .openai import AzureOpenAIChatCompletionClient as AzureOpenAIChatCompletionClientAlias
from .openai import OpenAIChatCompletionClient as OpenAIChatCompletionClientAlias

Then it worked all fine, also the JSON that was generated from your code was exactly as mine. Hope that helps and that this can be fixed on the GIT etc soon.

[dominiclachance]

1- In v0.4.1.5, if I close the browser, my tools disappear. Why would that be? I just recreated 20 tools, and if I open a new browser, they are gone. Where is the Gallery getting saved? It used to be in the database, but now it's nowhere to be found.

2- In previous versions, when a user ran a task, everything was saved in the user folder. Now, nothing gets saved there anymore. Where does AGS save the user files now?

[victordibia]

Great! Let us know how it goes!

[dominiclachance]

Great! Let us know how it goes!

I installed it from a dev container and when I load the URL, the interface flashes for a second and then I get a blank screen with these errors in the console:

After this is fixed, I should be able to test it inside out!

[dominiclachance]

The only error I got when building it was:

[dominiclachance]

Build Log:

success compile gatsby files - 1.398s
warn File '.env.production' is missing. Using default values.
success load gatsby config - 0.027s
success load plugins - 0.210s
success onPreInit - 0.010s
success initialize cache - 0.052s
success copy gatsby files - 0.363s
success Compiling Gatsby Functions - 0.114s
success onPreBootstrap - 0.141s
success createSchemaCustomization - 0.015s
success Checking for changed pages - 0.001s
success source and transform nodes - 0.218s
info Writing GraphQL type definitions to /workspace/frontend/.cache/schema.gql
success building schema - 0.164s
success createPages - 0.001s
success createPagesStatefully - 0.203s
info Total nodes: 57, SitePage nodes: 7 (use --verbose for breakdown)
success Checking for changed pages - 0.000s
success onPreExtractQueries - 0.002s
warn File '.env.production' is missing. Using default values.
warn File '.env.production' is missing. Using default values.
warn File '.env.production' is missing. Using default values.
warn File '.env.production' is missing. Using default values.
warn File '.env.production' is missing. Using default values.
warn File '.env.production' is missing. Using default values.
warn File '.env.production' is missing. Using default values.
warn File '.env.production' is missing. Using default values.
warn File '.env.production' is missing. Using default values.
warn File '.env.production' is missing. Using default values.
warn File '.env.production' is missing. Using default values.
warn File '.env.production' is missing. Using default values.
warn File '.env.production' is missing. Using default values.
success extract queries from components - 2.333s
success write out redirect data - 0.002s
success Build manifest and related icons - 0.464s
success onPostBootstrap - 0.468s
info bootstrap finished - 6.689s
success write out requires - 0.017s
success Building production JavaScript and CSS bundles - 14.278s
success Building HTML renderer - 19.944s
success Execute page configs - 0.042s
success Caching Webpack compilations - 0.000s
success run queries in workers - 0.047s - 7/7 149.44/s
success Merge worker state - 0.030s
success Rewriting compilation hashes - 0.004s
success Writing page-data.json and slice-data.json files to public directory - 0.014s - 7/7 515.76/s

ERROR UNKNOWN

(node:3027) [DEP0040] DeprecationWarning: The punycode module is deprecated. Please use a userland alternative instead.
(Use node --trace-deprecation ... to show where the warning was created)

success Building static HTML for pages - 1.779s - 7/7 3.93/s
info There are no new or changed slice html files to build.
success stitching slices - 0.034s
success onPostBuild - 0.040s
info Done building in 44.095436894 sec

Pages

┌ src/pages/404.tsx
│ ├ /404/
│ └ /404.html
├ src/pages/build.tsx
│ └ /build/
├ src/pages/deploy.tsx
│ └ /deploy/
├ src/pages/gallery.tsx
│ └ /gallery/
├ src/pages/index.tsx
│ └ /
└ src/pages/settings.tsx
└ /settings/

╭────────────────────────────────────────────────────────────────╮
│ │
│ (SSG) Generated at build time │
│ D (DSG) Deferred static generation - page generated at runtime │
│ ∞ (SSR) Server-side renders at runtime (uses getServerData) │
│ λ (Function) Gatsby function │
│ │
╰────────────────────────────────────────────────────────────────╯
Done in 45.16s.
vscode ➜ /workspace/frontend $ autogenstudio ui --port 8081
INFO: Loading environment from '/home/vscode/.autogenstudio/temp_env_vars.env'
2025-02-26 23:36:27.601 | INFO | autogenstudio.web.initialization:init:40 - Initializing application data folder: /home/vscode/.autogenstudio
INFO: Started server process [3239]
INFO: Waiting for application startup.
2025-02-26 23:36:27.620 | INFO | autogenstudio.database.db_manager:initialize_database:57 - Creating database tables...
2025-02-26 23:36:27.648 | INFO | autogenstudio.database.schema_manager:_initialize_alembic:154 - Alembic initialization complete
INFO [alembic.runtime.migration] Context impl SQLiteImpl.
INFO [alembic.runtime.migration] Will assume non-transactional DDL.
2025-02-26 23:36:27.670 | INFO | autogenstudio.web.app:lifespan:35 - Application startup complete. Navigate to http://127.0.0.1:8081
^C2025-02-26 23:38:07.837 | INFO | autogenstudio.web.app:lifespan:47 - Cleaning up application resources...
2025-02-26 23:38:07.837 | INFO | autogenstudio.database.db_manager:close:336 - Closing database connections...
2025-02-26 23:38:07.839 | INFO | autogenstudio.database.db_manager:close:340 - Database connections closed successfully
2025-02-26 23:38:07.839 | INFO | autogenstudio.web.app:lifespan:49 - Application shutdown complete
vscode ➜ /workspace/frontend $ autogenstudio ui --port 8081
INFO: Loading environment from '/home/vscode/.autogenstudio/temp_env_vars.env'
2025-02-26 23:38:15.437 | INFO | autogenstudio.web.initialization:init:40 - Initializing application data folder: /home/vscode/.autogenstudio
INFO: Started server process [3822]
INFO: Waiting for application startup.
2025-02-26 23:38:15.458 | INFO | autogenstudio.database.db_manager:initialize_database:66 - Checking database schema...
2025-02-26 23:38:15.459 | INFO | autogenstudio.database.schema_manager:ensure_schema_up_to_date:537 - Resetting migrations and updating to current schema...
2025-02-26 23:38:15.459 | INFO | autogenstudio.database.schema_manager:ensure_schema_up_to_date:542 - Cleared alembic directory
2025-02-26 23:38:15.466 | INFO | autogenstudio.database.schema_manager:ensure_schema_up_to_date:548 - Reset alembic version
2025-02-26 23:38:15.467 | INFO | autogenstudio.database.schema_manager:_initialize_alembic:154 - Alembic initialization complete
INFO [alembic.runtime.migration] Context impl SQLiteImpl.
INFO [alembic.runtime.migration] Will assume non-transactional DDL.
2025-02-26 23:38:15.488 | INFO | autogenstudio.database.schema_manager:ensure_schema_up_to_date:560 - Generated fresh migration: 247c676c1a40
INFO [alembic.runtime.migration] Context impl SQLiteImpl.
INFO [alembic.runtime.migration] Will assume non-transactional DDL.
INFO [alembic.runtime.migration] Running upgrade -> 247c676c1a40, current_schema
2025-02-26 23:38:15.494 | INFO | autogenstudio.database.schema_manager:upgrade_schema:448 - Schema upgraded successfully to head
2025-02-26 23:38:15.494 | INFO | autogenstudio.database.schema_manager:ensure_schema_up_to_date:566 - Successfully applied migration
2025-02-26 23:38:15.495 | INFO | autogenstudio.web.app:lifespan:35 - Application startup complete. Navigate to http://127.0.0.1:8081
^C2025-02-26 23:43:31.092 | INFO | autogenstudio.web.app:lifespan:47 - Cleaning up application resources...
2025-02-26 23:43:31.092 | INFO | autogenstudio.database.db_manager:close:336 - Closing database connections...
2025-02-26 23:43:31.093 | INFO | autogenstudio.database.db_manager:close:340 - Database connections closed successfully
2025-02-26 23:43:31.093 | INFO | autogenstudio.web.app:lifespan:49 - Application shutdown complete
vscode ➜ /workspace/frontend $ autogenstudio ui --port 8080 --appdir ./promarkia_apis
INFO: Loading environment from '/home/vscode/.autogenstudio/temp_env_vars.env'
2025-02-26 23:43:40.454 | INFO | autogenstudio.web.initialization:init:40 - Initializing application data folder: promarkia_apis
INFO: Started server process [5029]
INFO: Waiting for application startup.
2025-02-26 23:43:40.477 | INFO | autogenstudio.database.db_manager:initialize_database:57 - Creating database tables...
2025-02-26 23:43:40.541 | INFO | autogenstudio.database.schema_manager:_initialize_alembic:154 - Alembic initialization complete
INFO [alembic.runtime.migration] Context impl SQLiteImpl.
INFO [alembic.runtime.migration] Will assume non-transactional DDL.
2025-02-26 23:43:40.634 | INFO | autogenstudio.web.app:lifespan:35 - Application startup complete. Navigate to http://127.0.0.1:8080

[dominiclachance]

This is what I get when I do a quick screenshot before it goes blank:

[dominiclachance]

Hi @victordibia , were you able to find the cause of the issue I am facing?

[dominiclachance]

@victordibia I also looked at the database and the gallery I created is all there:

So everything seems to work and I was able to send a task and get the answer from openai after adding my api key.

[victordibia]

Glad it all worked out!

[victordibia]

There are more updates coming, stay tuned!
In the mean time, if there are any new features you want to contribute upstream, feel free to open an issue to align on design and then an associated PR.
Looking forward to your contributions!

[dominiclachance]

@victordibia While I have you around, I am trying to use the generate image tool and I get this:

Error: The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

The OPENAI_API_KEY is set in dockers and when I echo $OPENAI_API_KEY I get the proper key. What could be the issue?

[KanikaChoudhary1312]

What if someone dont want to use opne_api_key, instead want to use azure open ai? Is it necessary to still set it since now it had become a config

[dharanidharan59]

Hi There, I am trying to setup Azure SQL Server as the database for the Autogen Studio, however the database initialization (Table creation) is not happening.

Below is the command I am trying to run
autogenstudio ui --database-uri ""

While it got connected to the database and gives the following log:

INFO: Loading environment from 'C:\Users\Dh.autogenstudio\temp_env_vars.env'
2025-03-02 09:50:41.117 | INFO | autogenstudio.web.initialization:init:40 - Initializing application data folder: C:\Users\Dh.autogenstudio
INFO: Started server process [8252]
INFO: Waiting for application startup.
2025-03-02 09:50:45.556 | INFO | autogenstudio.web.app:lifespan:35 - Application startup complete. Navigate to http://127.0.0.1:8081
INFO: Application startup complete.
INFO: Uvicorn running on http://127.0.0.1:8081 (Press CTRL+C to quit)

While I am trying to access the UI, I am getting the below error

Also, there are no database tables got created

Kindly guide me here !

[victordibia]

Are you building from source, or using a pypi build?
Also, are you able to run it correctly without the azure db backend? This way we can triangulate to see if there is an issue with the build vs the azure connection.

[dharanidharan59]

Hi @victordibia
I am building from the source and yes, I can run it correctly without the azure db backend.
How should I approach this issue?

[victordibia]

I would recommend the following

• write code to confirm you can indeed connect to azure sql
• the dbmanager in Ags uses sql model . So write code to verify you can connect to azure sql with sqlmodel and a db uri
• Write debug print logs in debmanager to trace errors

let me know what you find

[dharanidharan59]

write code to confirm you can indeed connect to azure sql

`
from loguru import logger
import pyodbc

def connect_to_azure_sql():
    """Simple function to establish connection to Azure SQL Database."""
    try:
        # Connection parameters
        server = ""
        database = ""
        username = ""
        password = ""
        
        # Create connection string for pyodbc
        conn_str = (
            f'DRIVER={{ODBC Driver 17 for SQL Server}};'
            f'SERVER={server};'
            f'DATABASE={database};'
            f'UID={username};'
            f'PWD={password};'
            f'Encrypt=yes;TrustServerCertificate=no;'
        )
        
        # Attempt connection
        logger.info(f"Connecting to Azure SQL Database on {server}...")
        conn = pyodbc.connect(conn_str)
        
        # Test connection with a simple query
        cursor = conn.cursor()
        cursor.execute("SELECT @@VERSION")
        version = cursor.fetchone()[0]
        logger.info(f"Connection successful! SQL Server version: {version}")
        
        # Return the connection if successful
        return conn
    
    except Exception as e:
        logger.error(f"Connection failed: {str(e)}")
        return None

if __name__ == "__main__":
    # Set up logging format
    logger.remove()
    logger.add(lambda msg: print(msg, end=""), colorize=True, format="<green>{time:YYYY-MM-DD HH:mm:ss}</green> | <level>{level: <8}</level> | <cyan>{message}</cyan>")
    
    # Try to connect
    connection = connect_to_azure_sql()
    
    # Check if connection was successful
    if connection:
        logger.success("Database connection established successfully!")
        
        connection.close()
        logger.info("Connection closed")
    else:
        logger.error("Failed to connect to the database")
`

The above code is able to connect to the database

the dbmanager in Ags uses sql model . So write code to verify you can connect to azure sql with sqlmodel and a db uri

`
import os
from loguru import logger
import pyodbc
from sqlmodel import SQLModel, create_engine, Session, text

def connect_to_azure_sql_sqlmodel():
    """Simple function to establish connection to Azure SQL Database using SQLModel."""
    try:
        # Connection parameters
        server = ""
        database = ""
        username = ""
        password = ""
        
        # Create connection string for pyodbc
        driver = '{ODBC Driver 17 for SQL Server}'
        conn_str = (
            f'DRIVER={driver};'
            f'SERVER={server};'
            f'DATABASE={database};'
            f'UID={username};'
            f'PWD={password};'
            f'Encrypt=yes;TrustServerCertificate=no;'
        )
        
        # Construct the SQLModel engine URI
        engine_uri = f"mssql+pyodbc:///?odbc_connect={conn_str}"
        
        # Create the engine
        engine = create_engine(engine_uri, echo=False)  # echo=True for debugging SQL queries
        
        # Test the connection by creating tables (if they don't exist) and running a simple query
        SQLModel.metadata.create_all(engine)
        
        with Session(engine) as session:
            # Execute a simple query
            result = session.execute(text("SELECT @@VERSION")).scalar()
            logger.info(f"SQL Server version: {result}")
        
        logger.info("SQLModel connection to Azure SQL Database successful!")
        return True
    
    except Exception as e:
        logger.error(f"SQLModel connection failed: {str(e)}")
        return False

if __name__ == "__main__":
    # Set up logging format
    logger.remove()
    logger.add(lambda msg: print(msg, end=""), colorize=True, format="<green>{time:YYYY-MM-DD HH:mm:ss}</green> | <level>{level: <8}</level> | <cyan>{message}</cyan>")
    
    # Try to connect using SQLModel
    if connect_to_azure_sql_sqlmodel():
        logger.success("SQLModel Database connection established successfully!")
    else:
        logger.error("SQLModel Failed to connect to the database")
`

The above code also got executed successfully

Write debug print logs in debmanager to trace errors

2025-03-04 22:00:51 | INFO     | Initializing database manager...
2025-03-04 22:00:56 | INFO     | Testing database connection...
2025-03-04 22:00:56 | INFO     | Connected to SQL Server version: Microsoft SQL Azure (RTM) - 12.0.2000.8 
        Feb  9 2025 20:57:20 
        Copyright (C) 2024 Microsoft Corporation

2025-03-04 22:00:56 | INFO     | Initializing database schema...
2025-03-04 22:00:57 | INFO     | Checking database schema...
2025-03-04 22:00:57 | INFO     | Resetting migrations and updating to current schema...
2025-03-04 22:00:57 | INFO     | Cleared alembic directory
2025-03-04 22:00:57 | INFO     | Reset alembic version
2025-03-04 22:00:57 | INFO     | Alembic initialization complete
2025-03-04 22:00:58 | ERROR    | Failed to generate revision: (pyodbc.InterfaceError) ('28000', "[28000] [Microsoft][ODBC Driver 17 for SQL Server][SQL Server]Login failed for user 'abc'. (18456) (SQLDriverConnect); [28000] [Microsoft][ODBC Driver 17 for SQL Server]Invalid connection string attribute (0); [28000] [Microsoft][ODBC Driver 17 for SQL Server][SQL Server]Login failed for user 'abc'. (18456); [28000] [Microsoft][ODBC Driver 17 for SQL Server]Invalid connection string attribute (0)")
(Background on this error at: https://sqlalche.me/e/20/rvf5)
2025-03-04 22:00:58 | ERROR    | Failed to generate new migration
2025-03-04 22:00:58 | ERROR    | Error initializing database: Database upgrade failed

It is getting failed during the Generate revision of schema_manager.py

Please help here!

[victordibia]

Let us proceed in a separate discussion - #5822

[KanikaChoudhary1312]

With the current database schema upgrade, I am trying to run it locally with spqlite and gives the error

2025-03-04 21:38:51.826 | ERROR | autogenstudio.database.schema_manager:upgrade_schema:452 - Schema upgrade failed: (sqlite3.OperationalError) near "ALTER": syntax error
[SQL: ALTER TABLE message ALTER COLUMN run_id TYPE UUID]
(Background on this error at: https://sqlalche.me/e/20/e3q8)
2025-03-04 21:38:51.827 | ERROR | autogenstudio.database.schema_manager:ensure_schema_up_to_date:567 - Failed to apply migration
2025-03-04 21:38:51.827 | INFO | autogenstudio.web.app:lifespan:35 - Application startup complete. Navigate to http://127.0.0.1:8081
2025-03-04 21:47:13.155 | ERROR | autogenstudio.database.db_manager:get:217 - Error while getting items: Run (sqlite3.OperationalError) no such column: run.user_id
[SQL: SELECT run.id, run.created_at, run.updated_at, run.session_id, run.status, run.task, run.team_result, run.error_message, run.version, run.messages, run.user_id
FROM run
WHERE run.session_id = ? ORDER BY run.created_at ASC]
[parameters: (3,)]
(Background on this error at: https://sqlalche.me/e/20/e3q8)
2025-03-04 21:47:19.801 | ERROR | autogenstudio.database.db_manager:get:217 - Error while getting items: Run (sqlite3.OperationalError) no such column: run.user_id
[SQL: SELECT run.id, run.created_at, run.updated_at, run.session_id, run.status, run.task, run.team_result, run.error_message, run.version, run.messages, run.user_id
FROM run
WHERE run.session_id = ? ORDER BY run.created_at ASC]
[parameters: (1,)]
(Background on this error at: https://sqlalche.me/e/20/e3q8)
2025-03-04 21:47:20.850 | ERROR | autogenstudio.database.db_manager:get:217 - Error while getting items: Run (sqlite3.OperationalError) no such column: run.user_id
[SQL: SELECT run.id, run.created_at, run.updated_at, run.session_id, run.status, run.task, run.team_result, run.error_message, run.version, run.messages, run.user_id
FROM run
WHERE run.session_id = ? ORDER BY run.created_at ASC]
[parameters: (3,)]
(Background on this error at: https://sqlalche.me/e/20/e3q8)

[KanikaChoudhary1312]

[KanikaChoudhary1312]

@victordibia Can you please help me with this ? I am running the backend apis locally and while running the frontend gets this error ?

[victordibia]

I have an initial fix here ...
#5845 ..
You can test at pip install autogenstudio==0.4.2.dev0

[EItanya]

@victordibia I'm seeing this locally as well fwiw, I tried digging into it for a couple of hours but haven't been able to figure it out.

[victordibia]

Might be related to this.
#5794

Are you running from a build (pypi)? What happens if you reset your db?
There is a change that for some reason the db gets into an inconsistent state (incorrect team) leading to the error.

autogenstudio ui --appdir ./newdir

Also if you are building from source, does the fix help?

[EItanya]

So I am building from source and unfortunately that didn't fix it.
The following warning always shows up:

INFO  [alembic.runtime.migration] Context impl SQLiteImpl.
INFO  [alembic.runtime.migration] Will assume non-transactional DDL.
INFO  [alembic.autogenerate.compare] Detected type change from NUMERIC() to UUID() on 'message.run_id'
INFO  [alembic.autogenerate.compare] Detected type change from NUMERIC() to UUID() on 'run.id'

And then when I start the server for a 2nd time the following error occurs:

2025-03-05 21:21:06.085 | ERROR    | autogenstudio.database.schema_manager:upgrade_schema:452 - Schema upgrade failed: (sqlite3.OperationalError) near "ALTER": syntax error
[SQL: ALTER TABLE message ALTER COLUMN run_id TYPE UUID]
(Background on this error at: https://sqlalche.me/e/20/e3q8)
2025-03-05 21:21:06.085 | ERROR    | autogenstudio.database.schema_manager:ensure_schema_up_to_date:567 - Failed to apply migration

I tried checking the alembic config and noticed the following autogenerated script:

"""Initial schema

Revision ID: fec4e6893bfb
Revises: 
Create Date: 2025-03-05 20:57:03.262702

"""
from typing import Sequence, Union

from alembic import op
import sqlalchemy as sa
import sqlmodel


# revision identifiers, used by Alembic.
revision: str = 'fec4e6893bfb'
down_revision: Union[str, None] = None
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None


def upgrade() -> None:
    # ### commands auto generated by Alembic - please adjust! ###
    op.alter_column('message', 'run_id',
               existing_type=sa.NUMERIC(),
               type_=sa.UUID(),
               existing_nullable=True)
    op.alter_column('run', 'id',
               existing_type=sa.NUMERIC(),
               type_=sa.UUID(),
               existing_nullable=False)
    # ### end Alembic commands ###


def downgrade() -> None:
    # ### commands auto generated by Alembic - please adjust! ###
    op.alter_column('run', 'id',
               existing_type=sa.UUID(),
               type_=sa.NUMERIC(),
               existing_nullable=False)
    op.alter_column('message', 'run_id',
               existing_type=sa.UUID(),
               type_=sa.NUMERIC(),
               existing_nullable=True)
    # ### end Alembic commands ###

It seems to be trying to switch to it numeric even though the models now have uuid?

FWIW I've been clearing the .autogenstudio folder to try and reset the DB already.

[victordibia]

Its an sqlite problem. SQL lite does not have a native uuid field so it casts to numeric and then alembic autoupgrade gets confused.
An upgrade failure shouldnt be an issue here ... (db is still there/fine, just the attempt to convert a numeric to uuid fails .. I should detect and ignore this specific issue).
I'll need to carve out more time to debug this later today in a new env

[victordibia]

@EItanya , can you create a separate issue with some repro instructions?

[victordibia]

I have an initial fix here ...
#5845 ..
You can test at pip install autogenstudio==0.4.2.dev0

Happy to get feedback

[dominiclachance]

@victordibia Is the new AGS Python package still scheduled for release today? thx

[victordibia]

Hi @dominiclachance,
A few features still need testing, date updated in milestone.

[vvvvvvizard]

Hi I saw your mail now . I'm waiting for the technician to restore my fibre connection, Italian greyhounds pups , it can be done offline , has it been resolved yet?

…

On Tue, Mar 4, 2025, 6:35 PM Dharanidharan M ***@***.***> wrote: *write code to confirm you can indeed connect to azure sql* ` from loguru import logger import pyodbc def connect_to_azure_sql(): """Simple function to establish connection to Azure SQL Database.""" try: # Connection parameters server = "" database = "" username = "" password = "" # Create connection string for pyodbc conn_str = ( f'DRIVER={{ODBC Driver 17 for SQL Server}};' f'SERVER={server};' f'DATABASE={database};' f'UID={username};' f'PWD={password};' f'Encrypt=yes;TrustServerCertificate=no;' ) # Attempt connection logger.info(f"Connecting to Azure SQL Database on {server}...") conn = pyodbc.connect(conn_str) # Test connection with a simple query cursor = conn.cursor() cursor.execute("SELECT @@Version") version = cursor.fetchone()[0] logger.info(f"Connection successful! SQL Server version: {version}") # Return the connection if successful return conn except Exception as e: logger.error(f"Connection failed: {str(e)}") return None if __name__ == "__main__": # Set up logging format logger.remove() logger.add(lambda msg: print(msg, end=""), colorize=True, format="<green>{time:YYYY-MM-DD HH:mm:ss}</green> | <level>{level: <8}</level> | <cyan>{message}</cyan>") # Try to connect connection = connect_to_azure_sql() # Check if connection was successful if connection: logger.success("Database connection established successfully!") connection.close() logger.info("Connection closed") else: logger.error("Failed to connect to the database") ` The above code is able to connect to the database *the dbmanager in Ags uses sql model . So write code to verify you can connect to azure sql with sqlmodel and a db uri* ` import os from loguru import logger import pyodbc from sqlmodel import SQLModel, create_engine, Session, text def connect_to_azure_sql_sqlmodel(): """Simple function to establish connection to Azure SQL Database using SQLModel.""" try: # Connection parameters server = "" database = "" username = "" password = "" # Create connection string for pyodbc driver = '{ODBC Driver 17 for SQL Server}' conn_str = ( f'DRIVER={driver};' f'SERVER={server};' f'DATABASE={database};' f'UID={username};' f'PWD={password};' f'Encrypt=yes;TrustServerCertificate=no;' ) # Construct the SQLModel engine URI engine_uri = f"mssql+pyodbc:///?odbc_connect={conn_str}" # Create the engine engine = create_engine(engine_uri, echo=False) # echo=True for debugging SQL queries # Test the connection by creating tables (if they don't exist) and running a simple query SQLModel.metadata.create_all(engine) with Session(engine) as session: # Execute a simple query result = session.execute(text("SELECT @@Version")).scalar() logger.info(f"SQL Server version: {result}") logger.info("SQLModel connection to Azure SQL Database successful!") return True except Exception as e: logger.error(f"SQLModel connection failed: {str(e)}") return False if __name__ == "__main__": # Set up logging format logger.remove() logger.add(lambda msg: print(msg, end=""), colorize=True, format="<green>{time:YYYY-MM-DD HH:mm:ss}</green> | <level>{level: <8}</level> | <cyan>{message}</cyan>") # Try to connect using SQLModel if connect_to_azure_sql_sqlmodel(): logger.success("SQLModel Database connection established successfully!") else: logger.error("SQLModel Failed to connect to the database") ` The above code also got executed successfully *Write debug print logs in debmanager to trace errors* 2025-03-04 22:00:51 | INFO | Initializing database manager... 2025-03-04 22:00:56 | INFO | Testing database connection... 2025-03-04 22:00:56 | INFO | Connected to SQL Server version: Microsoft SQL Azure (RTM) - 12.0.2000.8 Feb 9 2025 20:57:20 Copyright (C) 2024 Microsoft Corporation 2025-03-04 22:00:56 | INFO | Initializing database schema... 2025-03-04 22:00:57 | INFO | Checking database schema... 2025-03-04 22:00:57 | INFO | Resetting migrations and updating to current schema... 2025-03-04 22:00:57 | INFO | Cleared alembic directory 2025-03-04 22:00:57 | INFO | Reset alembic version 2025-03-04 22:00:57 | INFO | Alembic initialization complete 2025-03-04 22:00:58 | ERROR | Failed to generate revision: (pyodbc.InterfaceError) ('28000', "[28000] [Microsoft][ODBC Driver 17 for SQL Server][SQL Server]Login failed for user 'shellpoc'. (18456) (SQLDriverConnect); [28000] [Microsoft][ODBC Driver 17 for SQL Server]Invalid connection string attribute (0); [28000] [Microsoft][ODBC Driver 17 for SQL Server][SQL Server]Login failed for user 'shellpoc'. (18456); [28000] [Microsoft][ODBC Driver 17 for SQL Server]Invalid connection string attribute (0)") (Background on this error at: https://sqlalche.me/e/20/rvf5) 2025-03-04 22:00:58 | ERROR | Failed to generate new migration 2025-03-04 22:00:58 | ERROR | Error initializing database: Database upgrade failed It is getting failed during the Generate revision of schema_manager.py Please help here! — Reply to this email directly, view it on GitHub <#4208 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ACUEYCLW2FQGFSBWZTBPRYL2SXI33AVCNFSM6AAAAABR2JZNSCVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTEMZZGA4TAMY> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[vvvvvvizard]

For Discord assistance, I always use ***@***.*** to assist . Il look resolve the email conflict , probably something I did on my side . In the meantime il send a solution or two , let me review the code , please use the other email for discord help Always happy to help 😊 Kind Regards Yusuf rawat

…

On Thu, Mar 6, 2025, 7:17 AM Victor Dibia ***@***.***> wrote: I have an initial fix here ... #5845 <#5845> .. You can test at pip install autogenstudio==0.4.2.dev0 Happy to get feedback — Reply to this email directly, view it on GitHub <#4208 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/ACUEYCLRBN7B44KPOBWYCK32S7K65AVCNFSM6AAAAABR2JZNSCVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTENBQHE3DENA> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>