Updated search_datasets tool using gemini search + the default #947
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
Remove outdated features and installation instructions from README and add a link to mkdocs website.
|
MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅ |
|
Ah I just filled the form that was required :) |
SubhadityaMukherjee
changed the title
|
recheck |
1 similar comment
|
recheck |
|
@joaquinvanschoren can you check if this works now and if it can be merged? If so, I can proceed with the other parts of the project as we discussed |
|
@SubhadityaMukherjee just for my understanding: does the gemini search hinge on using gemini api as backend llm? or can any llm backend be used? |
|
Hey I wanted to initially start with gemini, and if it proved to be useful, then add options for anything else. The perks of using gemini itself was that you wouldnt necessarily run into search limits :) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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Outdated suggestions cannot be applied.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.
Redefined the search_datasts tool while using gemini to also do a "google search" using gemini and not just look at the dataset index when doing a search.
This can be tested using "eclair-client --tool search-datasets --query "tree cover datasets" --use-gemini" after running eclair-server and gemini-cli (following the current documentation)
Also updated the required packages so we can use 'uv' as the venv/package manager.