Skip to content
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.

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

Langgraph examples #165

Closed

Conversation

gabrielrfg
Copy link
Contributor

LLMstudio Version 1.0.0

What was done in this PR:

Added Langgraph example notebook

How it was tested:

Ran the notebook and did not see any red text :)

Additional notes:

Was necessary to create an auxiliary function to pretty print the results of a langgraph agent because for some reason if printing while messages are being generated langgraph misses printing parallel tool calls (not related to llmstudio)

claudiolemos and others added 15 commits September 9, 2024 22:23
## LLMstudio Version 0.3.11

### What was done in this version:

- Updated the method input_to_string in provider.py to ensure
compatibility with vision models -- [PR
126](#126)
- Added events to the startup process of tracking, ui and engine. This
removes the race conditions we were experiencing repeatedly, also
removes the need to run start_server() as early as possible -- [PR
129](#129).
- Improved exception handling for invalid Azure endpoints -- [PR
129](#129).


### How it was tested:

- Ran projects with LLMStudio server dependencies

### Additional notes:

- Any breaking changes? 
    - No
- Any new dependencies added?
    - No
- Any performance improvements?
- Yes. Servers will be launched synchronously preventing parent PIDs to
call LLMStudio before being up.
* Add Docker build and push to workflows

Updated upload-pypi-dev and upload-pypi to build and push a docker image with the most recent version of LLMstudio (including dev releases) to tensoropsai dockerhub.

* Fix some lint issues
* Add LLM docs

* Add how to guides

1. Add how-to deploy-on-gke and build-a-tool-agent.
## LLMstudio Version 0.3.12

### What was done in this PR:

- Update how server waits when started from cli.
- Add automatic docker build/push when dev or main release is published.
- Add LLM and how-to docs.
## LLMstudio Version 0.3.12

### What was done in this PR:

- Updated llmstudio version on `pyproject.toml` from 0.3.11 to 0.3.12
## LLMstudio Version 0.3.12

### What was done in this PR:

1. Add Dockerfile.
2. Add small code change to troubleshoot workflow behavior.
3. Add new lines at the end of workflows.
1. Change path of images in the guide from how-to/deploy-on-gke/images/ to images, since images are stored here https://mintlify.s3-us-west-1.amazonaws.com/tensorops/how-to/deploy-on-gke/images/
## LLMstudio Version 0.3.12

### What was done in this PR:

- Fixed image pathing for `how-to` `deploy-on-gke` guide.
- Fixed lettering for the title of `deploy-on-gke` guide.
## LLMstudio Version 0.3.12

### What was done in this PR:

- Fix GKE guide.
@diogoncalves diogoncalves changed the base branch from main to feat/modularization_shift_and_lift October 24, 2024 08:16
Copy link
Collaborator

@diogoncalves diogoncalves left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@gabrielrfg cherry picked to the right branch

@diogoncalves
Copy link
Collaborator

picked the notebook to version 1.0.0

@diogoncalves diogoncalves deleted the feat/langgraph-example branch November 6, 2024 12:20
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants