Add new integration for YandexGPT Embedding Model #14313
+625
−0
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
dosubot
bot
added
the
size:L
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
llama-index-integrations/embeddings/llama-index-embeddings-yandexgpt/README.md
Outdated
Show resolved
Hide resolved
...rations/embeddings/llama-index-embeddings-yandexgpt/llama_index/embeddings/yandexgpt/base.py
Outdated
Show resolved
Hide resolved
...rations/embeddings/llama-index-embeddings-yandexgpt/llama_index/embeddings/yandexgpt/util.py
Outdated
Show resolved
Hide resolved
nerdai
reviewed
Jun 25, 2024
There was a problem hiding this comment.
Thanks @KirillKukharev.
I pushed a commit to pass our lint checks. Left also a minor comment wrt pyproject.toml
llama-index-integrations/embeddings/llama-index-embeddings-yandexgpt/pyproject.toml
Outdated
Show resolved
Hide resolved
|
|
||
| def _get_query_embedding(self, text: str) -> List[float]: | ||
| """Get query embedding sync.""" | ||
| return self._embed(text, is_document=True) |
There was a problem hiding this comment.
Shouldn't this be is_document=False?
There was a problem hiding this comment.
(maybe I misunderstand this option though, but the query is not a document)
| """Get list of queries embeddings sync.""" | ||
| embeddings = [] | ||
| for text in texts: | ||
| embeddings.append(self._embed(text, is_document=True)) |
There was a problem hiding this comment.
same here?
Oh, I'm sorry, I didn't fully understand the difference between text and query. According to docs clarifai, embedding methods should be named vice versa. I have swapped the names of the embedding methods, please see if it's ok?
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
This pull request introduces a new class YandexGPTEmbedding for generating embeddings using the Yandex Cloud API.
Fixes # (issue)
New Package?
Version Bump?
Type of Change
How Has This Been Tested?
Suggested Checklist:
make format; make lintto appease the lint gods