@cfnathan Okay, it appears that file format is wrong. ```sh $ npx wrangler vectorize insert hey-hi-i

Sschkovich @cfnathan Okay, it appears that file format is wrong. ```sh $ npx wrangler vecto...

S

schkovichOP•4/12/24, 8:28 PM

@cfnathan validator says OK

Ccfnathan There's an example here. https://developers.cloudflare.com/vectorize/configurati...

S

schkovichOP•4/12/24, 8:42 PM

perfect! that's it. wrangler works as well as multipart request. however, the first example is still returning 400. you might have a bug there. i will review the code in quesion once again.

Sschkovich perfect! that's it. wrangler works as well as multipart request. however, the fi...

S

schkovichOP•4/12/24, 8:47 PM

curl is giving the same error.

curl --request POST   --url https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/vectorize/indexes/hey-hi-index/upsert   --header "Authorization: Bearer ${VECTORIZE_API_TOKEN}"   --header 'Content-Type: application/x-ndjson'   --data test_vector.ndjson
{
  "result": null,
  "success": false,
  "errors": [
    {
      "message": "unexpected - Internal server error"
    }
  ],
  "messages": []
}

curl --request POST   --url https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/vectorize/indexes/hey-hi-index/upsert   --header "Authorization: Bearer ${VECTORIZE_API_TOKEN}"   --header 'Content-Type: application/x-ndjson'   --data test_vector.ndjson
{
  "result": null,
  "success": false,
  "errors": [
    {
      "message": "unexpected - Internal server error"
    }
  ],
  "messages": []
}

curl --request POST   --url https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/vectorize/indexes/hey-hi-index/upsert   --header "Authorization: Bearer ${VECTORIZE_API_TOKEN}"   --header 'Content-Type: application/x-ndjson'   --data test_vector.ndjson
{
  "result": null,
  "success": false,
  "errors": [
    {
      "message": "unexpected - Internal server error"
    }
  ],
  "messages": []
}

curl --request POST   --url https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/vectorize/indexes/hey-hi-index/upsert   --header "Authorization: Bearer ${VECTORIZE_API_TOKEN}"   --header 'Content-Type: application/x-ndjson'   --data test_vector.ndjson
{
  "result": null,
  "success": false,
  "errors": [
    {
      "message": "unexpected - Internal server error"
    }
  ],
  "messages": []
}

W

Wang•4/17/24, 5:57 AM

Hi, Cloudflare team

W

Wang•4/17/24, 5:58 AM

I encountered a 502 error when accessing the Vectorize Query API using a Singapore IP, but it works fine with a China IP. How can I resolve this?

W

Wang•4/17/24, 5:58 AM

This is the API being used.
const url =

https://api.cloudflare.com/client/v4/accounts/${ACCOUNT_IDENTIFIER}/vectorize/indexes/${indexName}/query

https://api.cloudflare.com/client/v4/accounts/${ACCOUNT_IDENTIFIER}/vectorize/indexes/${indexName}/query

https://api.cloudflare.com/client/v4/accounts/${ACCOUNT_IDENTIFIER}/vectorize/indexes/${indexName}/query

https://api.cloudflare.com/client/v4/accounts/${ACCOUNT_IDENTIFIER}/vectorize/indexes/${indexName}/query;

N

notorious_tom•4/18/24, 9:41 PM

Does anyone know where I can find OpenAPI spec files for vectorize db?

Nnotorious_tom Does anyone know where I can find OpenAPI spec files for vectorize db?

D

DaniFoldi•4/19/24, 6:30 AM

https://developers.cloudflare.com/api/operations/vectorize-list-vectorize-indexes
if you go back to https://developers.cloudflare.com/api/ you can export the whole cloudflare openapi spec, if you need that

Z

zensin•4/19/24, 9:24 AM

All the examples show populating a

wrangler.toml

wrangler.toml

with:

[[vectorize]]
binding = "VECTOR_INDEX"
index_name = "vector-index"

[[vectorize]]
binding = "VECTOR_INDEX"
index_name = "vector-index"

[[vectorize]]
binding = "VECTOR_INDEX"
index_name = "vector-index"

[[vectorize]]
binding = "VECTOR_INDEX"
index_name = "vector-index"

and then they show using it in a worker script.

Do I have to declare the index in the toml file? What I would instead like to do is dynamically create indexes and let the client specify which one it wants to use (or create) in the request. That way each user can have their own index of whatever.

I know I can create indexes using the REST API. However, idk how to then dynamically load them by name in a worker to use them for search.

Ccfnathan Currently this isn't possible as you're correct, you need to bind to individual ...

S

Saqib•4/23/24, 5:05 PM

@cfnathan is there an ETA on when the limits will be increased — namespaces per index and vectors per index?

S

scotto•4/24/24, 12:04 AM

What is the best way to manage for example if a product has many vectors, for example one per image and we want to obtain the top 10 products without getting the same product multiple times

Sscotto What is the best way to manage for example if a product has many vectors, for ex...

P

pkpio•4/24/24, 9:16 AM

Try MMR search - I think what you are looking for is diversity in results

Ppkpio Try MMR search - I think what you are looking for is diversity in results

S

scotto•4/24/24, 11:35 AM

cloudflare vectorize supports inserting multiples vectors to the same id?

Sscotto cloudflare vectorize supports inserting multiples vectors to the same id?

P

pkpio•4/24/24, 1:21 PM

Don't know

Sscotto cloudflare vectorize supports inserting multiples vectors to the same id?

S

Saqib•4/24/24, 4:11 PM

I think it does not allow.

W

Wang•4/25/24, 11:45 AM

I suddenly realized that the functionality of my product is similar to AWS Bedrock's knowledge base management , and I don't have confidence in being able to compete with AWS. I want to know if it's possible for me to join Cloudflare and do the same thing?:blobhaj:

W

Wang•4/25/24, 11:47 AM

I use the technology stack of Cloudflare Pages for full-stack development, Cloudflare D1, Cloudflare AI, Cloudflare R2, as well as Vectorize for knowledge training and chatbot construction.

W

Wang•4/25/24, 11:47 AM

:dogekek:

S

scotto•4/25/24, 12:46 PM

i'm getting an empty 200 response from vectorize rest API, index has data

S

scotto•4/25/24, 12:46 PM

no errors just an empty response

S

scotto•4/25/24, 1:02 PM

how to open a support ticket here? i can send a video, i can reproduce the problem quite easily

Sscotto how to open a support ticket here? i can send a video, i can reproduce the probl...

I

Isaac McFadyen•4/25/24, 1:07 PM

?support

F

Flare•4/25/24, 1:07 PM

To contact Cloudflare Support about an issue, please visit the Support Portal and fill in the form on the portal. After submission, you will receive confirmation over email.

Some issues, such as Account or Billing related issues, cannot be solved by the community.
Any plan level (including Free plans) can open tickets for Account, Billing or Registrar ticket categories. Make sure to select the correct category to ensure it goes to the right place.
For more information on the methods by which you can contact Support for your plan level, see Contacting Cloudflare Support - Cloudflare Docs

Sscotto i'm getting an empty 200 response from vectorize rest API, index has data

I

Isaac McFadyen•4/25/24, 1:16 PM

Can you provide more info about the response you're getting? If it's a widespread issue we might be able to escalate here.

I

Isaac McFadyen•4/25/24, 1:16 PM

Are you getting an empty array in the response? An empty 200 body? Something else?

I

Isaac McFadyen•4/25/24, 1:16 PM

And what is your Vectorize index dimensions and type (i.e. cosine, etc)?

S

scotto•4/25/24, 7:38 PM

it's possible to see the amount of vectors inside a index?

Sscotto it's possible to see the amount of vectors inside a index?

T

thipperz•4/25/24, 8:06 PM

such basic stuff right

T

thipperz•4/25/24, 8:06 PM

i'm hoping to see a lot of things when Vectorize goes GA

B

Bram Adams•4/29/24, 3:38 PM

would really love any kind of way to introspect anything about the vector db. a ui similar to supabase where i could see the metadata at least would go a really long way!

S

Sweetbasil•4/29/24, 5:42 PM

Hi Cloudflare team
Is Vectorize database HIPPA compliant?

A

antonioballs•4/29/24, 11:55 PM

Any update on the unreliability of querying Vectorize via REST API, @cfnathan ? Discussed here: Can you provide more info about the. Can provide more info you need. Cheers.

Discord

Discord - A New Way to Chat with Friends & Communities

Discord is the easiest way to communicate over voice, video, and text. Chat, hang out, and stay close with your friends and communities.

B

Bonadio•5/1/24, 5:07 AM

Vectorize seems very slow. I have a simple RAG application that uses vectorize with an index of size 1536 with cosine, with a single document of 5 pages , I was timing the code and vectorize takes almost 2 seconds to respond.
Here are my timing
(log) Embedding time 378
(log) Vectorize time 1844
(log) Document time 171
(log) LLM time 1518

the code is this

        const vectorizeStartTime: any = new Date()
        const queryVec = await c.env.VECTORIZE_TESTE_1536.query(embQuery, { 
            topK: 3, 
            returnValues: false, 
            returnMetadata: true, 
            namespace: data.customerId.toString()+"_"+data.repoId.toString()
        });
        const vectorizeEndtime: any= new Date()
        console.log("Vectorize time", vectorizeEndtime - vectorizeStartTime)

        const vectorizeStartTime: any = new Date()
        const queryVec = await c.env.VECTORIZE_TESTE_1536.query(embQuery, { 
            topK: 3, 
            returnValues: false, 
            returnMetadata: true, 
            namespace: data.customerId.toString()+"_"+data.repoId.toString()
        });
        const vectorizeEndtime: any= new Date()
        console.log("Vectorize time", vectorizeEndtime - vectorizeStartTime)

        const vectorizeStartTime: any = new Date()
        const queryVec = await c.env.VECTORIZE_TESTE_1536.query(embQuery, { 
            topK: 3, 
            returnValues: false, 
            returnMetadata: true, 
            namespace: data.customerId.toString()+"_"+data.repoId.toString()
        });
        const vectorizeEndtime: any= new Date()
        console.log("Vectorize time", vectorizeEndtime - vectorizeStartTime)

        const vectorizeStartTime: any = new Date()
        const queryVec = await c.env.VECTORIZE_TESTE_1536.query(embQuery, { 
            topK: 3, 
            returnValues: false, 
            returnMetadata: true, 
            namespace: data.customerId.toString()+"_"+data.repoId.toString()
        });
        const vectorizeEndtime: any= new Date()
        console.log("Vectorize time", vectorizeEndtime - vectorizeStartTime)

Is this the expected speed?

B

Bonadio•5/1/24, 5:11 AM

If I run the same code using chromadb in my local machine it only takes 102 milliseconds to respond

N

nuno•5/2/24, 11:24 AM

Hi guys, is it possible to query a vector and filter by multiple namespaces?

Ccfnathan This is a symptom of how we have the beta deployed. As mentioned in the above th...

B

Bonadio•5/3/24, 1:23 AM

Hi @cfnathan, thanks for the feedback.

Ccfnathan This is a symptom of how we have the beta deployed. As mentioned in the above th...

S

scotto•5/3/24, 10:29 PM

any ETA for this new version?

N

notorious_tom•5/3/24, 11:55 PM

hey @George Portillo just wanted to confirm I'm seeing the same issue with code that was working before :\

J

Jens•5/6/24, 7:40 PM

The pageContent text is not stored and is only used for embedding to create the vectors, right?

So that I have to save the text separately and cannot simply get it back later from the vector db.

const store = new CloudflareVectorizeStore(embeddings, {
      index: env.VECTORIZE_INDEX,
});
await store.addDocuments(
  [
    {
      pageContent: "hello",
      metadata: {},
    },
    {
      pageContent: "world",
      metadata: {},
    },
    {
      pageContent: "hi",
      metadata: {},
    },
  ],
  { ids: ["id1", "id2", "id3"] }
);

const store = new CloudflareVectorizeStore(embeddings, {
      index: env.VECTORIZE_INDEX,
});
await store.addDocuments(
  [
    {
      pageContent: "hello",
      metadata: {},
    },
    {
      pageContent: "world",
      metadata: {},
    },
    {
      pageContent: "hi",
      metadata: {},
    },
  ],
  { ids: ["id1", "id2", "id3"] }
);

const store = new CloudflareVectorizeStore(embeddings, {
      index: env.VECTORIZE_INDEX,
});
await store.addDocuments(
  [
    {
      pageContent: "hello",
      metadata: {},
    },
    {
      pageContent: "world",
      metadata: {},
    },
    {
      pageContent: "hi",
      metadata: {},
    },
  ],
  { ids: ["id1", "id2", "id3"] }
);

const store = new CloudflareVectorizeStore(embeddings, {
      index: env.VECTORIZE_INDEX,
});
await store.addDocuments(
  [
    {
      pageContent: "hello",
      metadata: {},
    },
    {
      pageContent: "world",
      metadata: {},
    },
    {
      pageContent: "hi",
      metadata: {},
    },
  ],
  { ids: ["id1", "id2", "id3"] }
);

Ccfnathan This is a symptom of how we have the beta deployed. As mentioned in the above th...

J

Jens•5/6/24, 8:38 PM

Where is the datacenter?

Original message was deleted

J

Jens•5/7/24, 10:03 AM

Yes thanks, I thought it was probably in the USA. I am Europa and the performance wasn't great. Now I tried something else it was faster.

@cfnathan Okay, it appears that file format is wrong. ```sh $ npx wrangler vectorize insert hey-hi-i

Similar Threads

Similar Threads

Similar Threads