improvements to FastEmbed integration #558
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
github-actions
bot
added
type:documentation
anakin87
commented
Mar 7, 2024
Comment on lines
-161
to
+167
| source_pkgs = ["src", "tests"] | ||
| source = ["haystack_integrations"] | ||
| branch = true | ||
| parallel = true | ||
|
|
||
|
|
||
| [tool.coverage.paths] | ||
| fastembed_haystack = ["src/haystack_integrations", "*/fastembed-haystack/src"] | ||
| tests = ["tests", "*/fastembed-haystack/tests"] | ||
| parallel = false | ||
|
|
||
| [tool.coverage.report] | ||
| omit = ["*/tests/*", "*/__init__.py"] | ||
| show_missing=true |
anakin87
commented
Mar 7, 2024
| @@ -35,7 +35,6 @@ def __init__( | |||
| threads: Optional[int] = None, | |||
| prefix: str = "", | |||
| suffix: str = "", | |||
| batch_size: int = 256, | |||
There was a problem hiding this comment.
the text embedder only accepts a single string,
so batch_size was misleading
anakin87
commented
Mar 7, 2024
Comment on lines
+44
to
+51
| def embed(self, data: List[str], progress_bar=True, **kwargs) -> List[List[float]]: | ||
| # the embed method returns a Iterable[np.ndarray], so we convert it to a list of lists | ||
| embeddings = [np_array.tolist() for np_array in self.model.embed(data, **kwargs)] | ||
| embeddings = [] | ||
| embeddings_iterable = self.model.embed(data, **kwargs) | ||
| for np_array in tqdm( | ||
| embeddings_iterable, disable=not progress_bar, desc="Calculating embeddings", total=len(data) | ||
| ): | ||
| embeddings.append(np_array.tolist()) |
There was a problem hiding this comment.
since the original library does not provide this feature,
we create the progress bar using tqdm in the embedding backend.
silvanocerza
approved these changes
Mar 7, 2024
|
sorry I had to come to the office to handle packaging, only now I saw this |
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.
While looking at #554 and at the cookbook, I found several opportunities to improve this integration.
Fixes #554