langchain

3fc0ea51 - community : [bugfix] Use document ids as keys in AzureSearch vectorstore (#25486)

community : [bugfix] Use document ids as keys in AzureSearch vectorstore (#25486) # Description [Vector store base class](https://github.com/langchain-ai/langchain/blob/4cdaca67dc51dba887289f56c6fead3c1a52f97d/libs/core/langchain_core/vectorstores/base.py#L65) currently expects `ids` to be passed in and that is what it passes along to the AzureSearch vector store when attempting to `add_texts()`. However AzureSearch expects `keys` to be passed in. When they are not present, AzureSearch `add_embeddings()` makes up new uuids. This is a problem when trying to run indexing. [Indexing code expects](https://github.com/langchain-ai/langchain/blob/b297af5482ae7c6d26779513d637ec657a1cd552/libs/core/langchain_core/indexing/api.py#L371) the documents to be uploaded using provided ids. Currently AzureSearch ignores `ids` passed from `indexing` and makes up new ones. Later when `indexer` attempts to delete removed file, it uses the `id` it had stored when uploading the document, however it was uploaded under different `id`. **Twitter handle: @martintriska1**