GRPC Query failed AioRpcError of RPC terminated status UNAVAILABLE

Support
1

Description

Seeing this error pop up in our logs

2024-09-26T18:36:47.646Z
Error finding nearest neighbors: Query call with protocol GRPC search failed with message <AioRpcError of RPC that terminated with:
status = StatusCode.UNAVAILABLE
details = “recvmsg:Connection reset by peer”
debug_error_string = “UNKNOWN:Error received from peer {created_time:“2024-09-26T18:36:47.646280137+00:00”, grpc_status:14, grpc_message:“recvmsg:Connection reset by peer”}”

Server Setup Information

  • Weaviate Server Version: 1.26.4
  • Deployment Method: Weaviate Cloud
  • Multi Node? Number of Running Nodes: 1??
  • Client Language and Version: Python
  • Multitenancy?: No.

Any additional Information

Code where the error is populated:

def find_nearest_neighbors(item, settings):
vector_similarity = settings[“vector_similarity”]
matching_vectors = settings[“matching_vectors”]

try:
    description = item["description"]
    item_id = item["id"] if "id" in item else item["item_id"]
    embedding = get_embedding(description)
    collection = vector_client.collections.get("items")

    if embedding is None:
        raise ValueError("No embedding found for item")

    results = collection.query.near_vector(
        near_vector=embedding,
        certainty=vector_similarity,
        filters=Filter.by_property("item_id").not_equal(item_id),
        return_metadata=wvc.query.MetadataQuery(certainty=True),
        limit=matching_vectors
    )

    items_dict_list = [item.properties for item in results.objects]
    return items_dict_list

except Exception as e:
    print(f"Error finding nearest neighbors: {e}")
    return []
2

hi @AdamHeard !!

Welcome to our community :hugs:

Do you have any reading on resource usage?

How many of memory and cpu do you have available? How many objects have stored?

this error message indicates that the connection was closed from the server.

So I believe there may be requiring more resources.

If you have not fine tuned Weaviate for resource usage, check this documentation on how to do that:

3

Thanks for the response @DudaNogueira.

Per resources on the Fargate Instance:
CPU: 2 vCPU
Memory: 4 GB
Objects Stored: 1.6M

How much more resources do you feel it would require?

4

Hi!

This will vary according to the dimension length of your vectors.

Here we have an example for this calculation

Assuming your vectors has 1536 dimensions, this is the calculation you need to do, for storing 1 million objects:

2 * 1e6 * (1536 * 4)

As a rule of thumb, we always double the required memory (this is the 2x)

so you are looking to something around 12G of ram. This is not counting the maxconnections.

Let me know if this helps.

5

Снимок экрана от 2024-12-20 16-05-30
Снимок экрана от 2024-12-20 16-05-30848×708 35.8 KB

i need help

6

hi @dastankg !!

Welcome to our community!

Do you mind opening a new thread in the Support category?
And please, make sure to answer the required questions like versions, deployment methods, etc.

The issue with the screen shot seems to be that there isn’t any objects indexed.

Please, also provide any outstanding logs messages on the new thread you create.

THanks!

7

Have same

in LM Studio

But in console run - norm

image
image1129×611 60.8 KB

Why u dont like LM STudio )))) ?

8

hi @VlaUg !

We do like all things AI, LM Studio included :wink:

Could it be that the vectorization is timing out? How long goes it took to generate those vectors?

If that’s the case, you may need to change MODULES_CLIENT_TIMEOUT env variable accordingly.

9

Very very very fast
( rtx 3060 12 GB , main llm like clode 3.5 (7 GB ) , embended llm like 300-600 mb )