Wrong input: Not existing vector name

[kientv]

I created collection name by this code:

qdrantClient.create_collection(
collection_name=collection_name,
vectors_config=VectorParams(
distance=rest.Distance.COSINE,
size=1536,
),
)

But error as below when upsert:

File "/home/chat-langchain/main.py", line 80, in ingress
ingest_docs(llm, collection_name, source_type, url, max_depth)
File "/home/chat-langchain/ingest.py", line 135, in ingest_docs
indexing_stats = index(
^^^^^^
File "/home/chat-langchain/_index.py", line 154, in index
vector_store.add_documents(docs_to_index, ids=uids)
File "/home/chat-langchain/venv/lib/python3.11/site-packages/langchain_core/vectorstores.py", line 122, in add_documents
return self.add_texts(texts, metadatas, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/chat-langchain/venv/lib/python3.11/site-packages/langchain/vectorstores/qdrant.py", line 181, in add_texts
self.client.upsert(
File "/home/chat-langchain/venv/lib/python3.11/site-packages/qdrant_client/qdrant_client.py", line 987, in upsert
return self._client.upsert(
^^^^^^^^^^^^^^^^^^^^
File "/home/chat-langchain/venv/lib/python3.11/site-packages/qdrant_client/qdrant_remote.py", line 1300, in upsert
http_result = self.openapi_client.points_api.upsert_points(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/chat-langchain/venv/lib/python3.11/site-packages/qdrant_client/http/api/points_api.py", line 1439, in upsert_points
return self._build_for_upsert_points(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/chat-langchain/venv/lib/python3.11/site-packages/qdrant_client/http/api/points_api.py", line 738, in build_for_upsert_points
return self.api_client.request(
^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/chat-langchain/venv/lib/python3.11/site-packages/qdrant_client/http/api_client.py", line 74, in request
return self.send(request, type)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/chat-langchain/venv/lib/python3.11/site-packages/qdrant_client/http/api_client.py", line 97, in send
raise UnexpectedResponse.for_response(response)
qdrant_client.http.exceptions.UnexpectedResponse: Unexpected Response: 400 (Bad Request)
Raw response content:
b'{"status":{"error":"Wrong input: Not existing vector name error: "},"time":0.064342823}'

Do you know how to fix it.

Thanks in advanced.

[timvisee]

Are you sure that you're inserting in this very same collection? Things look about right.

It errors because it cannot insert a vector with name "", but the collection you're creating does have that name ("" the default for an unnamed vector).

[kientv]

Are you sure that you're inserting in this very same collection? Things look about right.

It errors because it cannot insert a vector with name "", but the collection you're creating does have that name ("" the default for an unnamed vector).

I'm using same vector name:

debug_error_string = "UNKNOWN:Error received from peer {grpc_message:"Wrong input: Not existing vector name error: custom_vector", grpc_status:3, created_time:"2023-12-12T17:26:11.522274035+07:00"}"

My code like this:

 vectorstore = Qdrant(
        client=qdrantClient,
        collection_name=collection_name,
        embeddings=vertex_embedding,
        metadata_payload_key="tags",
        content_payload_key="content",
        vector_name="custom_vector",
    )

qdrantClient.create_collection(
    collection_name=collection_name,
    vectors_config=VectorParams(
        distance=rest.Distance.COSINE,
        size=768,
    ),
)

[timvisee]

Based on the above it looks like you're:

• creating a collection with no named vectors
• are upserting vectors with the name custom-vector

The schema during creation and the vectors you upsert must match. Qdrant will not create new vector names dynamically.

In this example you can see how you'd create a collection with named vectors. In your case you likely just want one named vector (custom-vector): https://qdrant.tech/documentation/concepts/collections/#collection-with-multiple-vectors

After doing that I assume the above issue will be resolved.

[kientv]

Thank you for your support, Now it work with this code:

 qdrantClient.create_collection(
    collection_name=collection_name,
    vectors_config= {
        "custom_vector": rest.VectorParams(
            distance=rest.Distance.COSINE,
            size=768,
        ),
    }
)