Runtime model configurability #146
Merged
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
* Added an error check when embedding change causes read error * Refactored provider load, decompose logic, aded model provider list api * Re-indexes dirs when embeddings change, learn list command * Fixed typo, simplified adding metadata * Moved index dir, metadata path to constants
* remove unused div * automatically create config if not present * allow all-caps envvars in config * implement basic chat settings UI * hide API key text inputs * limit popup size, show success banner * show welcome message if no LM is selected * fix buggy UI with no selected LM/EM * exclude legacy OpenAI chat provider used in magics * Added a button with welcome message --------- Co-authored-by: Jain <pijain@3c22fb64c9fa.amazon.com>
* fix /clear command * use model IDs to compare LLMs instead * specify stop sequence in chat chain * add empty AI message, improve system prompt * add RTD configuration
dbelgrod
pushed a commit
to dbelgrod/jupyter-ai
that referenced
this pull request
Jun 10, 2024
* Refactored provider load, decompose logic, aded model provider list api * Renamed model * Sorted the provider names * WIP: Embedding providers * Added embeddings provider api * Added missing import * Moved providers to ray actor, added config actor * Ability to load llm and embeddings from config * Moved llm creation to specific actors * Added apis for fetching, updating config. Fixed config update, error handling * Updated as per PR feedback * Fixes issue with cohere embeddings, api keys not working * Added an error check when embedding change causes read error * Delete and re-index docs when embedding model changes (jupyterlab#137) * Added an error check when embedding change causes read error * Refactored provider load, decompose logic, aded model provider list api * Re-indexes dirs when embeddings change, learn list command * Fixed typo, simplified adding metadata * Moved index dir, metadata path to constants * Chat settings UI (jupyterlab#141) * remove unused div * automatically create config if not present * allow all-caps envvars in config * implement basic chat settings UI * hide API key text inputs * limit popup size, show success banner * show welcome message if no LM is selected * fix buggy UI with no selected LM/EM * exclude legacy OpenAI chat provider used in magics * Added a button with welcome message --------- Co-authored-by: Jain <pijain@3c22fb64c9fa.amazon.com> * Various chat chain enhancements and fixes (jupyterlab#144) * fix /clear command * use model IDs to compare LLMs instead * specify stop sequence in chat chain * add empty AI message, improve system prompt * add RTD configuration --------- Co-authored-by: Piyush Jain <piyushjain@duck.com> Co-authored-by: Jain <pijain@3c22fb64c9fa.amazon.com>
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
Implements configurability of the language model and embedding model being used in the chat panel. Includes: