Skip to content

Release v6.3.0 into Main#799

Merged
estohlmann merged 24 commits into
mainfrom
release/v6.3.0
Feb 27, 2026
Merged

Release v6.3.0 into Main#799
estohlmann merged 24 commits into
mainfrom
release/v6.3.0

Conversation

@github-actions
Copy link
Copy Markdown

@github-actions github-actions Bot commented Feb 27, 2026

v6.3.0

UI Updates

  • Added RAG citation document preview side panel in Chat UI
  • Exposed the document preview panel in the document library for viewing documents
  • Added "Dismiss all" button for notification stacks
  • Fixed "Loading Configuration..." text styling to match LISA UI using Cloudscape components
  • Added last updated date/time to session displays

Other Key Changes

  • Updated VLLM image to latest AWS deep-learning base with GPU settings for ECS, memory reservation, and tensor parallelization from GPU count
  • Dockerfiles for embedding (instructor, tei), text generation (tgi), and VLLM now run OS package upgrades during build
  • Removed deprecated LISA Serve V1 endpoints and supporting infrastructure
  • Updated dependencies across the codebase

Bug Fixes

  • Fixed RAG pipeline collection ID resolution (find_by_id_or_name fallback) and EventBus update mismatches on deployment
  • Resolved max_tokens handling for non-Anthropic models on Anthropic routes
  • Improved RAG PDF parsing quality (excessive whitespace and invisible Unicode characters)
  • Addressed consistency of UI validation warnings for field format and required fields
  • Added missing required role for batch ingestion
  • Added cache clearing at login to prevent cache corruption issues

Documentation

  • Added Claude Code setup guide for LISA Serve integration
  • Updated deployment guide

Acknowledgements

Full Changelog: https://github.com/awslabs/LISA/compare/v6.2.1..v6.3.0

estohlmann and others added 22 commits February 13, 2026 22:52
* split image build

* Add trigger release

* Use absolute path for tiktoken script
Co-authored-by: Evan Stohlmann <evmann@amazon.com>
… scheduling mode for improved performance. When set to "true", the entrypoint script now passes the --async-scheduling flag to the vLLM server. (#758)
* PDF and multi-file support for file context

* non-rag multifile uploads

* add FileTypes and cull allowed extensions

* pre-commit

* fixing pdf worker import

* update FileTypes to use standard MIME types

---------

Co-authored-by: jmharold <jmharold@amazon.com>
Co-authored-by: Evan Stohlmann <estohlmann@gmail.com>
…hropic routes (#779)

Add model info lookup to determine actual provider before resetting token limits.
Previously, max_tokens was nullified for all models when Anthropic-specific
headers were present. Now it only resets for non-Anthropic models, preventing
incorrect token limit handling when routing Anthropic models through the
Anthropic endpoint.

Changes:
- Add get_model_info() function to fetch model details from LiteLLM API
- Extract actual provider/model path from litellm_params
- Conditionally reset max_tokens only when model is not an Anthropic model
- Fix typo in condition checking (max_tokens not in params -> max_tokens in params)
- Added a Cache to store model Info with a Time to live (TTL) of 5 minutes by default.
Add comprehensive documentation for configuring Claude Code to work with
LISA Serve models. The guide includes:

- Prerequisites and reference links
- Environment variable configuration steps
- Model ID mapping for LISA endpoints
- Verification and troubleshooting procedures
- VSCode extension testing instructions

Also adds navigation link in VitePress config to make the guide accessible
from the documentation sidebar under the configuration section.

This enables users to integrate Claude Code with their LISA deployments
for local development workflows.
Comment thread test/python/integration-setup-test.py Dismissed
@estohlmann estohlmann marked this pull request as ready for review February 27, 2026 20:50
@estohlmann estohlmann merged commit fae6c47 into main Feb 27, 2026
19 checks passed
@estohlmann estohlmann deleted the release/v6.3.0 branch February 27, 2026 21:25
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