8000 Support gemini as a model provider · Issue #872 · obot-platform/obot · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Support gemini as a model provider #872

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
cjellick opened this issue Dec 16, 2024 · 3 comments
Closed

Support gemini as a model provider #872

cjellick opened this issue Dec 16, 2024 · 3 comments
Assignees
@iwilltry42
Labels
8000 feature

Comments

@cjellick
Copy link
Contributor
cjellick commented Dec 16, 2024 •
edited
Loading

See #832 for some more details
@iwilltry42 iwilltry42 mentioned this issue Jan 10, 2025
Merged
@sangee2004
Copy link

@iwilltry42 I was able to configure the Google Gemini Vertex AI Model Provider provider successfully.

But I am not able to chat with models from this provider.

I tried using gemini.1.5-pro-002 and gemini.1.0-pro and see the same results as below:

  1. Create an agent (all capability tools are enabled by default) . Chat with it.

We will be provided with the following error message

failed to run: failed calling model for completion: request exceeded retry limits: #6/6 error response received: error, status code: 500, message: client error. Code: 400, Message: At most one tool is supported., Status: INVALID_ARGUMENT, Details: []
  1. Create an agent. Disable all the capability tools for the agent. chat with this agent.

First message gets no response.
Second message fails with following error

failed to run: failed calling model for completion: request exceeded retry limits: #6/6 error response received: error, status code: 500, message: client error. Code: 400, Message: Unable to submit request because it must include at least one parts field, which describes the prompt input. Learn more: https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/gemini, Status: INVALID_ARGUMENT, Details: []

Threads that encountered this problem:
gemini.1.5-pro-002 as Language Model
https://test.acornlabs.com/admin/agents/a1bzxgd?threadId=t1v9xjc
https://test.acornlabs.com/admin/agents/a1bzxgd?threadId=t1v7c47
gemini.1.0-pro as Language Model
https://test.acornlabs.com/admin/agents/a1ctgg4?threadId=t1zcsn9

@iwilltry42
Copy link
Contributor

@sangee2004 - confirmed. No idea how that happened. Seems like I missed something after rebasing.
Fix is on its way 👍

@sangee2004
Copy link

Tested with latest version of tool - github.com/obot-platform/enterprise-tools:5badb39

This issue is not seen anymore.

Able to configure Gemini model provider and use the models for chatting .

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@iwilltry42 iwilltry42

Labels
feature
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@cjellick @iwilltry42 @sangee2004
0