yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-09-23 07:03:45 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix lg (#3725)

Browse Source
This commit is contained in:
Agnieszka Marzec 2022-12-16 09:43:22 +01:00 committed by GitHub
parent 54bf7ad343
commit a23f425877
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
haystack/nodes/retriever/multimodal/retriever.py
View File

@ -45,11 +45,11 @@ class MultiModalRetriever(DenseRetriever):
:param document_embedding_models: Dictionary matching a local path or remote name of document encoder :param document_embedding_models: Dictionary matching a local path or remote name of document encoder
checkpoint with the content type it should handle ("text", "table", "image", and so on). checkpoint with the content type it should handle ("text", "table", "image", and so on).
The format equals the one used by Hugging Face transformers' modelhub models. The format equals the one used by Hugging Face transformers' modelhub models.
:param query_type: The content type of the query ("text", "image" and so on) :param query_type: The content type of the query ("text", "image" and so on).
:param query_feature_extraction_params: The parameters to pass to the feature extractor of the query. :param query_feature_extraction_params: The parameters to pass to the feature extractor of the query.
:param document_feature_extraction_params: The parameters to pass to the feature extractor of the documents. :param document_feature_extraction_params: The parameters to pass to the feature extractor of the documents.
:param top_k: How many documents to return per query. :param top_k: How many documents to return per query.
:param batch_size: Number of questions or documents to encode at once. In case of multiple GPUs, this will be :param batch_size: Number of questions or documents to encode at once. For multiple GPUs, this is
the total batch size. the total batch size.
:param embed_meta_fields: Concatenate the provided meta fields to a (text) pair that is then used to create :param embed_meta_fields: Concatenate the provided meta fields to a (text) pair that is then used to create
the embedding. This is likely to improve performance if your titles contain meaningful information the embedding. This is likely to improve performance if your titles contain meaningful information