-
Notifications
You must be signed in to change notification settings - Fork 0
Implement RAG Chat #41
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
Open
SiaaG-dev
wants to merge
18
commits into
gkwan-ibm-rag
Choose a base branch
from
sg-rag-mongodb-with-docker-6a
base: gkwan-ibm-rag
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Conversation
This file contains hidden or 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
Signed-off-by: Siaa Gor <[email protected]>
Signed-off-by: Siaa Gor <[email protected]>
Signed-off-by: Siaa Gor <[email protected]>
Signed-off-by: Gilbert Kwan <[email protected]>
Signed-off-by: Gilbert Kwan <[email protected]>
Signed-off-by: Siaa Gor <[email protected]>
…to the Mongodb Database using the Api calls defined in EmbeddingService.java. Also added an api in EmbeddingService.java to retrieve all embeddings. 1. user visits localhost:8080 the chat service -> All the files under knowledge_base are added to Mongodb 2. OpenApi ui, users are able to call the get method to see all embeddings from the database. Signed-off-by: Siaa Gor <[email protected]>
…d coding the custom retrival augmentator - example query on localhost:9080 : Create Java class that uses the MicroProfile Health API to check/montior CPU usage is below 95%: and comparing to mp-health-3.txt. Also increase character length size for segments to keep simple Signed-off-by: Siaa Gor <[email protected]>
Hugging Face models do not support streaming chat anyways
* Fix packaging, toolchat.js, readme, pom Signed-off-by: Andrew Sasmito <[email protected]> * Add Google Gemini support, remove HF Signed-off-by: Andrew Sasmito <[email protected]> * Remove HF from the tests, add Gemini Signed-off-by: Andrew Sasmito <[email protected]> * Update readme Signed-off-by: Andrew Sasmito <[email protected]> * Remove gemini Signed-off-by: Andrew Sasmito <[email protected]> * Remove gemini from readme Signed-off-by: Andrew Sasmito <[email protected]> * Remove gemini from pom Signed-off-by: Andrew Sasmito <[email protected]> * dev content review Signed-off-by: Gilbert Kwan <[email protected]> --------- Signed-off-by: Andrew Sasmito <[email protected]> Signed-off-by: Gilbert Kwan <[email protected]> Co-authored-by: Andrew Sasmito <[email protected]> Co-authored-by: Gilbert Kwan <[email protected]>
Signed-off-by: Siaa Gor <[email protected]>
Signed-off-by: Siaa Gor <[email protected]>
Signed-off-by: Siaa Gor <[email protected]>
Signed-off-by: Siaa Gor <[email protected]>
Signed-off-by: Siaa Gor <[email protected]>
With GitHub Models and gpt-4o-mini, the first token is sometimes an empty string. The unit test breaks since the empty string denotes the end of the message, thus checking if an empty string contains a year.
* Fix packaging, toolchat.js, readme, pom Signed-off-by: Andrew Sasmito <[email protected]> * Add Google Gemini support, remove HF Signed-off-by: Andrew Sasmito <[email protected]> * Remove HF from the tests, add Gemini Signed-off-by: Andrew Sasmito <[email protected]> * Update readme Signed-off-by: Andrew Sasmito <[email protected]> * Remove gemini Signed-off-by: Andrew Sasmito <[email protected]> * Remove gemini from readme Signed-off-by: Andrew Sasmito <[email protected]> * Remove gemini from pom Signed-off-by: Andrew Sasmito <[email protected]> * Add ejb keyword Signed-off-by: Andrew Sasmito <[email protected]> * dev content review Signed-off-by: Gilbert Kwan <[email protected]> --------- Signed-off-by: Andrew Sasmito <[email protected]> Signed-off-by: Gilbert Kwan <[email protected]> Co-authored-by: Andrew Sasmito <[email protected]> Co-authored-by: Gilbert Kwan <[email protected]>
create a new branch from gkwan-ibm-rag to fix the following:
|
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.
address #21