θΏ™ζ˜―indexlocζδΎ›ηš„ζœεŠ‘οΌŒδΈθ¦θΎ“ε…₯任何密码
Skip to content

[FIX] Fix manual input model pref for agents #1848

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
Merged
merged 3 commits into from
Jul 11, 2024
Merged

[FIX] Fix manual input model pref for agents #1848

merged 3 commits into from
Jul 11, 2024

Conversation

@shatfield4
Copy link
Collaborator

@shatfield4 shatfield4 commented Jul 11, 2024

Pull Request Type

  • ✨ feat
  • πŸ› fix
  • ♻️ refactor
  • πŸ’„ style
  • πŸ”¨ chore
  • πŸ“ docs

Relevant Issues

resolves #1840

What is in this change?

  • On some LLM providers, the user needs to manually enter the model pref name and when doing this in the agent settings, it does not update the agentModel column in the workspace table so we need to grab the correct model from the environment and inject it into the agent on provider setup
  • This fixes a bug where a user is using the Generic OpenAI LLM provider model and it never updates to the correct model (would always default back to gpt-3.5-turbo)

Additional Information

Developer Validations

  • I ran yarn lint from the root of the repo & committed changes
  • Relevant documentation has been updated
  • I have tested my code functionality
  • Docker build succeeds locally

@shatfield4 shatfield4 linked an issue Jul 11, 2024 that may be closed by this pull request
Why am I using Agent to access GPT3.5 instead of my local model[BUG]: #1840
Closed
@timothycarambat timothycarambat added needs info / can't replicate Issues that require additional information and/or cannot currently be replicated, but possible bug PR:needs review Needs review by core team and removed needs info / can't replicate Issues that require additional information and/or cannot currently be replicated, but possible bug labels Jul 11, 2024
@timothycarambat
refactor agent model fallback
edacf97 
update UI to show disabled providers to stop questions about provider limitations
@timothycarambat
patch log on startup
0f329e4
@timothycarambat timothycarambat merged commit 8f0af88 into master Jul 11, 2024
@timothycarambat timothycarambat deleted the 1840-why-am-i-using-agent-to-access-gpt35-instead-of-my-local-modelbug branch July 11, 2024 21:03
CrackerCat pushed a commit to CrackerCat/anything-llm that referenced this pull request Jul 31, 2024
@shatfield4 @timothycarambat
[FIX] Fix manual input model pref for agents (Mintplex-Labs#1848)
dbd8a32 
* patch llm providers that have manual inputs for model pref

* refactor agent model fallback
update UI to show disabled providers to stop questions about provider limitations

* patch log on startup

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
CrackerCat pushed a commit to CrackerCat/anything-llm that referenced this pull request Aug 1, 2024
@shatfield4 @timothycarambat
[FIX] Fix manual input model pref for agents (Mintplex-Labs#1848)
c798805 
* patch llm providers that have manual inputs for model pref

* refactor agent model fallback
update UI to show disabled providers to stop questions about provider limitations

* patch log on startup

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
CrackerCat pushed a commit to CrackerCat/anything-llm that referenced this pull request Aug 2, 2024
@shatfield4 @timothycarambat
[FIX] Fix manual input model pref for agents (Mintplex-Labs#1848)
e191530 
* patch llm providers that have manual inputs for model pref

* refactor agent model fallback
update UI to show disabled providers to stop questions about provider limitations

* patch log on startup

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
CrackerCat pushed a commit to CrackerCat/anything-llm that referenced this pull request Aug 3, 2024
@shatfield4 @timothycarambat
[FIX] Fix manual input model pref for agents (Mintplex-Labs#1848)
7d1bab9 
* patch llm providers that have manual inputs for model pref

* refactor agent model fallback
update UI to show disabled providers to stop questions about provider limitations

* patch log on startup

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
cabwds pushed a commit to cabwds/anything-llm that referenced this pull request Jul 3, 2025
@shatfield4 @timothycarambat
[FIX] Fix manual input model pref for agents (Mintplex-Labs#1848)
24737ef 
* patch llm providers that have manual inputs for model pref

* refactor agent model fallback
update UI to show disabled providers to stop questions about provider limitations

* patch log on startup

---------

Co-authored-by: timothycarambat <rambat1010@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@timothycarambat timothycarambat Awaiting requested review from timothycarambat

Assignees

@timothycarambat timothycarambat

Labels

PR:needs review Needs review by core team

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

Why am I using Agent to access GPT3.5 instead of my local model[BUG]:

3 participants

@shatfield4 @timothycarambat