You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Clément Tamines a6cbb755a7 community[patch]: fix semantic answer bug in AzureSearch vector store (#18938) ... - **Description:** The `semantic_hybrid_search_with_score_and_rerank` method of `AzureSearch` contains a hardcoded field name "metadata" for the document metadata in the Azure AI Search Index. Adding such a field is optional when creating an Azure AI Search Index, as other snippets from `AzureSearch` test for the existence of this field before trying to access it. Furthermore, the metadata field name shouldn't be hardcoded as "metadata" and use the `FIELDS_METADATA` variable that defines this field name instead. In the current implementation, any index without a metadata field named "metadata" will yield an error if a semantic answer is returned by the search in `semantic_hybrid_search_with_score_and_rerank`. - **Issue:** https://github.com/langchain-ai/langchain/issues/18731 - **Prior fix to this bug:** This bug was fixed in this PR https://github.com/langchain-ai/langchain/pull/15642 by adding a check for the existence of the metadata field named `FIELDS_METADATA` and retrieving a value for the key called "key" in that metadata if it exists. If the field named `FIELDS_METADATA` was not present, an empty string was returned. This fix was removed in this PR https://github.com/langchain-ai/langchain/pull/15659 (see ed1ffca911#). @lz-chen: could you confirm this wasn't intentional? - **New fix to this bug:** I believe there was an oversight in the logic of the fix from [#1564](https://github.com/langchain-ai/langchain/pull/15642) which I explain below. The `semantic_hybrid_search_with_score_and_rerank` method creates a dictionary `semantic_answers_dict` with semantic answers returned by the search as follows. 5c2f7e6b2b/libs/community/langchain_community/vectorstores/azuresearch.py (L574-L581) The keys in this dictionary are the unique document ids in the index, if I understand the [documentation of semantic answers](https://learn.microsoft.com/en-us/azure/search/semantic-answers) in Azure AI Search correctly. When the method transforms a search result into a `Document` object, an "answer" key is added to the document's metadata. The value for this "answer" key should be the semantic answer returned by the search from this document, if such an answer is returned. The match between a `Document` object and the semantic answers returned by the search should be done through the unique document id, which is used as a key for the `semantic_answers_dict` dictionary. This id is defined in the search result's field named `FIELDS_ID`. I added a check to avoid any error in case no field named `FIELDS_ID` exists in a search result (which shouldn't happen in theory). A benefit of this approach is that this fix should work whether or not the Azure AI Search Index contains a metadata field. @levalencia could you confirm my analysis and test the fix? @raunakshrivastava7 do you agree with the fix? Thanks for the help!		4 months ago
..
adapters	docs: added `community` modules descriptions (#17827)	5 months ago
agent_toolkits	community: Add PolygonAggregates tool (#18882)	5 months ago
callbacks	community[patch] : [Fiddler] ensure dataset is not added if model is present (#19293)	4 months ago
chat_loaders	community[patch]: speed up import times in the community package (#18928)	5 months ago
chat_message_histories	community[patch]: speed up import times in the community package (#18928)	5 months ago
chat_models	community[minor]: Prem AI langchain integration (#19113)	4 months ago
docstore	community[patch]: speed up import times in the community package (#18928)	5 months ago
document_compressors	community[patch]: speed up import times in the community package (#18928)	5 months ago
document_loaders	community[patch]: expanding version in confluence loader (#19324)	4 months ago
document_transformers	community[patch]: flattening imports 3 (#18939)	5 months ago
embeddings	community[minor]: Prem AI langchain integration (#19113)	4 months ago
example_selectors	docs: added `community` modules descriptions (#17827)	5 months ago
graphs	community[patch]: flattening imports 3 (#18939)	5 months ago
indexes	community: Add document manager and mongo document manager (#17320)	5 months ago
llms	community[patch]: YandexGPT Use recent yandexcloud sdk version (#19341)	4 months ago
output_parsers	langchain[patch], community[minor]: move `output_parsers.ernie_functions` (#16057)	7 months ago
retrievers	community[patch]: Fixing incorrect base URLs for Azure Cognitive Search Retriever (#19352)	4 months ago
storage	community[patch]: flattening imports 3 (#18939)	5 months ago
tools	Josha91 fix docstring (#19249)	5 months ago
utilities	community[patch]: flattening imports 3 (#18939)	5 months ago
utils	core[patch]: Convert SimSIMD back to NumPy (#19473)	4 months ago
vectorstores	community[patch]: fix semantic answer bug in AzureSearch vector store (#18938)	4 months ago
__init__.py	community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)	8 months ago
cache.py	community: Use langchain-astradb for AstraDB caches (#18419)	5 months ago
py.typed	community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)	8 months ago