Skip to content

invalid_embedder #82

@AhmedMostafa08

Description

@AhmedMostafa08

Description
when trying to use vector index as vector store and use it as retriever when I use the retriever in a rag chain i get the following error :
meilisearch.errors.MeilisearchApiError: MeilisearchApiError. Error code: invalid_embedder. Error message: Cannot find embedder with name default.. Hint: It might not be working because you're not up to date with the Meilisearch version that search call requires. Error documentation: https://docs.meilisearch.com/errors#invalid_embedder Error type: invalid_request
Expected behavior
to return a response
Current behavior
the mentioned error occurs
here's the code for how I created the vector index :
client=meilisearch.Client('url','api key ')
embeddings = OpenAIEmbeddings()
vectorstore = Meilisearch(
embedding=embeddings,
client=client,
embedders=embedders,
index_name='vector_index')

and here's the embedding and embedder code
embeddings = OpenAIEmbeddings()
embedders = {
"default": {
"source": "userProvided",
"dimensions": 1536,
}
}
embedder_name = "default"
It was working fine till earlier today

Meilisearch version: 1.8.0

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions