Fix response routing and improve exception handling #17
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…/6270623501/events/e450d637fd014f8380064ad7026f39dc/ Update LLM response queues to be unique to match responses to requests
…ddle of a conversation round)
NeonDaniel
force-pushed
the
FIX_ResponseRouting
branch
from
1f0a9c5 to
6c11093
Compare
NeonDaniel
changed the title
NeonBohdan
approved these changes
Feb 5, 2025
Merged
NeonDaniel
added a commit
that referenced
this pull request
Mar 3, 2025
# Changelog ## [0.1.1a20](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a20) (2025-02-27) [Full Changelog](0.1.1a19...0.1.1a20) **Merged pull requests:** - Update to stable dependencies [\#25](#25) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a19](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a19) (2025-02-25) [Full Changelog](0.1.1a18...0.1.1a19) **Merged pull requests:** - Handle model exceptions with default responses [\#24](#24) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a18](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a18) (2025-02-25) [Full Changelog](0.1.1a17...0.1.1a18) **Merged pull requests:** - Update logging and appraiser error handling [\#23](#23) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a17](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a17) (2025-02-25) [Full Changelog](0.1.1a16...0.1.1a17) **Merged pull requests:** - Update logging so Sentry only logs once instead of 3x for voting errors [\#22](#22) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a16](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a16) (2025-02-22) [Full Changelog](0.1.1a15...0.1.1a16) **Merged pull requests:** - Handle voting exceptions to prevent more errors in handlers [\#21](#21) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a15](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a15) (2025-02-20) [Full Changelog](0.1.1a14...0.1.1a15) **Merged pull requests:** - Update async handling and logging to address Sentry Errors [\#20](#20) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a14](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a14) (2025-02-11) [Full Changelog](0.1.1a13...0.1.1a14) **Merged pull requests:** - Default disable sync thread and update obsserver thread behavior [\#19](#19) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a13](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a13) (2025-02-10) [Full Changelog](0.1.1a12...0.1.1a13) **Merged pull requests:** - Update Dependencies [\#18](#18) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a12](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a12) (2025-02-05) [Full Changelog](0.1.1a11...0.1.1a12) **Merged pull requests:** - Fix response routing and improve exception handling [\#17](#17) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a11](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a11) (2025-02-03) [Full Changelog](0.1.1a10...0.1.1a11) **Implemented enhancements:** - \[FEAT\] Event-driven persona updates [\#8](#8) **Merged pull requests:** - Handle Klat persona update events [\#10](#10) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a10](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a10) (2025-01-23) [Full Changelog](0.1.1a9...0.1.1a10) **Merged pull requests:** - Raise an exception if MQ is not connected during connector startup [\#16](#16) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a9](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a9) (2025-01-17) [Full Changelog](0.1.1a8...0.1.1a9) **Merged pull requests:** - Update PersonasProvider to use default personas when none are configured [\#15](#15) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a8](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a8) (2025-01-16) [Full Changelog](0.1.1a7...0.1.1a8) **Merged pull requests:** - Update dependencies and Add test for ConsumerThread [\#14](#14) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a7](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a7) (2025-01-06) [Full Changelog](0.1.1a6...0.1.1a7) **Merged pull requests:** - Implement Pydantic models from `neon-data-models` [\#9](#9) ([NeonDaniel](https://github.com/NeonDaniel)) ## [0.1.1a6](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a6) (2025-01-02) [Full Changelog](0.1.1a5...0.1.1a6) **Merged pull requests:** - Incremented minimal required MQ version to 0.7.2a9 [\#13](#13) ([NeonKirill](https://github.com/NeonKirill)) ## [0.1.1a5](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a5) (2024-12-14) [Full Changelog](0.1.1a4...0.1.1a5) **Merged pull requests:** - Added support for async consumers in LLM MQ Connector [\#12](#12) ([NeonKirill](https://github.com/NeonKirill)) ## [0.1.1a4](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a4) (2024-10-30) [Full Changelog](0.1.1a3...0.1.1a4) **Merged pull requests:** - injected dependency with sentry [\#7](#7) ([NeonKirill](https://github.com/NeonKirill)) ## [0.1.1a3](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a3) (2024-04-01) [Full Changelog](0.1.1a2...0.1.1a3) **Merged pull requests:** - Fixing issue with Persona Provider [\#6](#6) ([NeonKirill](https://github.com/NeonKirill)) ## [0.1.1a2](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a2) (2024-03-22) [Full Changelog](0.1.1a1...0.1.1a2) **Merged pull requests:** - Synchronization with Klat Personas [\#5](#5) ([NeonKirill](https://github.com/NeonKirill)) ## [0.1.1a1](https://github.com/NeonGeckoCom/neon-llm-core/tree/0.1.1a1) (2023-12-21) [Full Changelog](0.1.0...0.1.1a1) **Merged pull requests:** - Add alpha release automation [\#4](#4) ([NeonDaniel](https://github.com/NeonDaniel)) - LLM Chatbots with Personas [\#3](#3) ([NeonDaniel](https://github.com/NeonDaniel)) \* *This Changelog was automatically generated by [github_changelog_generator](https://github.com/github-changelog-generator/github-changelog-generator)*
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Add check to prevent observed IndexError in Sentry
Update LLM response queues to be unique to match responses to requests
Add type checks to prevent uncaught exceptions observed in testing
Issues
Other Notes
Currently implemented with vllm deployment on alpha