[Bug] dataprep-pgvector-server langchain - different vector dimensions 1024 and 768

[erojaso]

Priority

Undecided

OS type

Ubuntu

Hardware type

CPU-other (Please let us know in description)

Installation method

• [X] Pull docker images from hub.docker.com
• [ ] Build docker images from source

Deploy method

• [ ] Docker compose
• [X] Docker
• [X] Kubernetes
• [ ] Helm

Running nodes

Single Node

What's the version?

docker pull opea/dataprep-pgvector:latest docker pull opea/retriever-pgvector:latest

Description

After enabling my services as containers in Kubernetes, I have performed some data ingestion tests for PosgresSQL with the Langchain framework

When performing the tests for the retriever-pgvector I encounter the error: sqlalchemy.exc.DataError: (psycopg2.errors.DataException) different vector dimensions 1024 and 768

Although I use the default model "BAAI/bge-base-en-v1.5", the vector in DB has a different size.

Reproduce steps

With this code I was able to check the error

from langchain_huggingface import HuggingFaceEmbeddings
import random
import requests
import json
import asyncio

# Generate the embedding
async def get_embedding(text):
    embeddings = HuggingFaceEmbeddings(model_name="BAAI/bge-base-en-v1.5")
    embedding = await embeddings.aembed_query(text)
    return embedding

text = "What is the revenue of Nike in 2023?"
embedding_pre = asyncio.run(get_embedding(text))

embedding = embedding_pre + [0.0] * (1024 - len(embedding_pre))
print(len(embedding))
print(type(embedding))
print(embedding[0:10])

# Define the URL and the payload
url = "http://localhost:7000/v1/retrieval"
payload = {
    "text": "What is the revenue of Nike in 2023?",
    "embedding": embedding
}

# Send the POST request
headers = {'Content-Type': 'application/json'}
response = requests.post(url, data=json.dumps(payload), headers=headers)

# Print the response
print(response.text)

Raw log

PS C:\> kubectl logs -l app=retriever-pgvector-server -n gaas -f
    cursor.execute(statement, parameters)
sqlalchemy.exc.DataError: (psycopg2.errors.DataException) different vector dimensions 1024 and 768

[SQL: SELECT langchain_pg_embedding.collection_id AS langchain_pg_embedding_collection_id, langchain_pg_embedding.embedding AS langchain_pg_embedding_embedding, langchain_pg_embedding.document AS langchain_pg_embedding_document, langchain_pg_embedding.cmetadata AS langchain_pg_embedding_cmetadata, langchain_pg_embedding.custom_id AS langchain_pg_embedding_custom_id, langchain_pg_embedding.uuid AS langchain_pg_embedding_uuid, langchain_pg_embedding.embedding <=> %(embedding_1)s AS distance
FROM langchain_pg_embedding JOIN langchain_pg_collection ON langchain_pg_embedding.collection_id = langchain_pg_collection.uuid
WHERE langchain_pg_embedding.collection_id = %(collection_id_1)s::UUID ORDER BY distance ASC
 LIMIT %(param_1)s]
[parameters: {'embedding_1': '[0.011756504885852337,-0.0120476633310318,-0.00515980226919055,-0.00771339749917388,0.04292724281549454,0.011159130372107029,0.06352052837610245,0.01 ... (15909 characters truncated) ... 7,-0.025849001482129097,0.05056244507431984,-0.00946701318025589,-0.02234337292611599,0.013910794630646706,0.023309819400310516,-0.05879069119691849]', 'collection_id_1': UUID('e5f56093-bf77-4f95-8c2d-81ff968cca56'), 'param_1': 4}]
(Background on this error at: https://sqlalche.me/e/20/9h9h)
INFO:     127.0.0.1:49758 - "POST /v1/retrieval HTTP/1.1" 200 OK
INFO:     127.0.0.1:38832 - "POST /v1/retrieval HTTP/1.1" 500 Internal Server Error
ERROR:    Exception in ASGI application
Traceback (most recent call last):
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/engine/base.py", line 1967, in _exec_single_context
    self.dialect.do_execute(
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/engine/default.py", line 941, in do_execute
    cursor.execute(statement, parameters)
psycopg2.errors.DataException: different vector dimensions 1024 and 768

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/home/user/.local/lib/python3.11/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi
    result = await app(  # type: ignore[func-returns-value]
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
    return await self.app(scope, receive, send)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/fastapi/applications.py", line 1054, in __call__
    await super().__call__(scope, receive, send)
  File "/home/user/.local/lib/python3.11/site-packages/starlette/applications.py", line 113, in __call__
    await self.middleware_stack(scope, receive, send)
  File "/home/user/.local/lib/python3.11/site-packages/starlette/middleware/errors.py", line 187, in __call__
    raise exc
  File "/home/user/.local/lib/python3.11/site-packages/starlette/middleware/errors.py", line 165, in __call__
    await self.app(scope, receive, _send)
  File "/home/user/.local/lib/python3.11/site-packages/prometheus_fastapi_instrumentator/middleware.py", line 174, in __call__
    raise exc
  File "/home/user/.local/lib/python3.11/site-packages/prometheus_fastapi_instrumentator/middleware.py", line 172, in __call__
    await self.app(scope, receive, send_wrapper)
  File "/home/user/.local/lib/python3.11/site-packages/starlette/middleware/cors.py", line 85, in __call__
    await self.app(scope, receive, send)
  File "/home/user/.local/lib/python3.11/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
    await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
  File "/home/user/.local/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
    raise exc
  File "/home/user/.local/lib/python3.11/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
    await app(scope, receive, sender)
  File "/home/user/.local/lib/python3.11/site-packages/starlette/routing.py", line 715, in __call__
    await self.middleware_stack(scope, receive, send)
  File "/home/user/.local/lib/python3.11/site-packages/starlette/routing.py", line 735, in app
    await route.handle(scope, receive, send)
  File "/home/user/.local/lib/python3.11/site-packages/starlette/routing.py", line 288, in handle
    await self.app(scope, receive, send)
  File "/home/user/.local/lib/python3.11/site-packages/starlette/routing.py", line 76, in app
    await wrap_app_handling_exceptions(app, request)(scope, receive, send)
  File "/home/user/.local/lib/python3.11/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
    raise exc
  File "/home/user/.local/lib/python3.11/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
    await app(scope, receive, sender)
  File "/home/user/.local/lib/python3.11/site-packages/starlette/routing.py", line 73, in app
    response = await f(request)
               ^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/fastapi/routing.py", line 301, in app
    raw_response = await run_endpoint_function(
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/fastapi/routing.py", line 212, in run_endpoint_function
    return await dependant.call(**values)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/comps/retrievers/pgvector/langchain/retriever_pgvector.py", line 41, in retrieve
    search_res = await vector_db.asimilarity_search_by_vector(embedding=input.embedding)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/langchain_core/vectorstores/base.py", line 685, in asimilarity_search_by_vector
    return await run_in_executor(
           ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/langchain_core/runnables/config.py", line 588, in run_in_executor
    return await asyncio.get_running_loop().run_in_executor(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/usr/local/lib/python3.11/concurrent/futures/thread.py", line 58, in run
    result = self.fn(*self.args, **self.kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/langchain_core/runnables/config.py", line 579, in wrapper
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/langchain_community/vectorstores/pgvector.py", line 990, in similarity_search_by_vector
    docs_and_scores = self.similarity_search_with_score_by_vector(
                      ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/langchain_community/vectorstores/pgvector.py", line 632, in similarity_search_with_score_by_vector
    results = self._query_collection(embedding=embedding, k=k, filter=filter)
              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/langchain_community/vectorstores/pgvector.py", line 968, in _query_collection
    .all()
     ^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/orm/query.py", line 2673, in all
    return self._iter().all()  # type: ignore
           ^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/orm/query.py", line 2827, in _iter
    result: Union[ScalarResult[_T], Result[_T]] = self.session.execute(
                                                  ^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/orm/session.py", line 2362, in execute
    return self._execute_internal(
           ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/orm/session.py", line 2247, in _execute_internal
    result: Result[Any] = compile_state_cls.orm_execute_statement(
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/orm/context.py", line 305, in orm_execute_statement
    result = conn.execute(
             ^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/engine/base.py", line 1418, in execute
    return meth(
           ^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/sql/elements.py", line 515, in _execute_on_connection
    return connection._execute_clauseelement(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/engine/base.py", line 1640, in _execute_clauseelement
    ret = self._execute_context(
          ^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/engine/base.py", line 1846, in _execute_context
    return self._exec_single_context(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/engine/base.py", line 1986, in _exec_single_context
    self._handle_dbapi_exception(
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/engine/base.py", line 2355, in _handle_dbapi_exception
    raise sqlalchemy_exception.with_traceback(exc_info[2]) from e
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/engine/base.py", line 1967, in _exec_single_context
    self.dialect.do_execute(
  File "/home/user/.local/lib/python3.11/site-packages/sqlalchemy/engine/default.py", line 941, in do_execute
    cursor.execute(statement, parameters)
sqlalchemy.exc.DataError: (psycopg2.errors.DataException) different vector dimensions 1024 and 768

[SQL: SELECT langchain_pg_embedding.collection_id AS langchain_pg_embedding_collection_id, langchain_pg_embedding.embedding AS langchain_pg_embedding_embedding, langchain_pg_embedding.document AS langchain_pg_embedding_document, langchain_pg_embedding.cmetadata AS langchain_pg_embedding_cmetadata, langchain_pg_embedding.custom_id AS langchain_pg_embedding_custom_id, langchain_pg_embedding.uuid AS langchain_pg_embedding_uuid, langchain_pg_embedding.embedding <=> %(embedding_1)s AS distance
FROM langchain_pg_embedding JOIN langchain_pg_collection ON langchain_pg_embedding.collection_id = langchain_pg_collection.uuid
WHERE langchain_pg_embedding.collection_id = %(collection_id_1)s::UUID ORDER BY distance ASC
 LIMIT %(param_1)s]
[parameters: {'embedding_1': '[0.011756504885852337,-0.0120476633310318,-0.00515980226919055,-0.00771339749917388,0.04292724281549454,0.011159130372107029,0.06352052837610245,0.01 ... (15909 characters truncated) ... 7,-0.025849001482129097,0.05056244507431984,-0.00946701318025589,-0.02234337292611599,0.013910794630646706,0.023309819400310516,-0.05879069119691849]', 'collection_id_1': UUID('e5f56093-bf77-4f95-8c2d-81ff968cca56'), 'param_1': 4}]
(Background on this error at: https://sqlalche.me/e/20/9h9h)

[Spycsh]

Hi @erojaso , why do you explicitly convert the 768 vec to 1024 by embedding = embedding_pre + [0.0] * (1024 - len(embedding_pre))? Please remove this conversion and the code should work.

[Spycsh]

Please make sure your dataprep and retriever both access the same TEI Endpoint/Local model. If you have a bge-base (dim:768) for one and a bge-large(dim: 1024) for the other, you are likely to have these dimension mismatch issues.