launched vectorize to prod today it works great

.

.r20OP•9/23/25, 5:16 AM

its pretty easy to use

..r20 launched vectorize to prod today it works great

F

fortytwo•9/23/25, 5:16 AM

so are you just manually chunking, using cloudflare to generate vectors, inserting them, then searching and using one of cloudflare's llm models for the overall query?

F

fortytwo•9/23/25, 5:16 AM

I.e. all still cloudflare stuff, just not autorag to automatically do some things?

.

.r20OP•9/23/25, 5:17 AM

manually chunking, going to openai for vector embeddings, inserting them, and using open router models for agentic capabilities

.

.r20OP•9/23/25, 5:17 AM

i don’t use workers ai

F

fortytwo•9/23/25, 5:18 AM

Ok got it, so only using vector db to hold the vectors generated elsewhere, then search it but pass the found data to a model elsewhere for the actual query? I'm hitting cloudflare errors when trying to hit the rag/handle queries and just wondering if it's just autorag that has issues or if I need to move the whole impl to use other services, basically

.

.r20OP•9/23/25, 5:19 AM

yea that’s what i use vectorize for, what errors are you getting?

.

.r20OP•9/23/25, 5:19 AM

for me all the errors stopped when i went off of autorag

F

fortytwo•9/23/25, 5:19 AM

Stuff like

Workers AI: 9003: unknown internal error

Workers AI: 9003: unknown internal error

Workers AI: 9003: unknown internal error

Workers AI: 9003: unknown internal error for example

.

.r20OP•9/23/25, 5:20 AM

wait isn’t that a dns error?

.

.r20OP•9/23/25, 5:21 AM

maybe one of the devs or someone else more experienced with that error can help you with that

.

.r20OP•9/23/25, 5:21 AM

not entirely sure about that one

F

fortytwo•9/23/25, 5:22 AM

I've seen some others too, trying to dig them up now

.

.r20OP•9/23/25, 5:22 AM

maybe stay off of workers ai if u can’t solve it

.

.r20OP•9/23/25, 5:22 AM

openrouter has some free rate limited models

F

fortytwo•9/23/25, 5:23 AM

I've also seen timeouts:

Workers AI: WORKERS AI: Operation timed out after 40000 ms

Workers AI: WORKERS AI: Operation timed out after 40000 ms

Workers AI: WORKERS AI: Operation timed out after 40000 ms

Workers AI: WORKERS AI: Operation timed out after 40000 ms

.

.r20OP•9/23/25, 5:23 AM

yeah that one is a workers ai issue that i think the devs are aware of

F

fortytwo•9/23/25, 5:48 AM

@.r20 do you use ai gateway to access the other stuff or just go straight to them?

.

.r20OP•9/23/25, 5:50 AM

ai gateway

F

fortytwo•9/23/25, 5:51 AM

cool. thanks for the info

P

pietrolc.com•9/23/25, 1:08 PM

Hi, is there a way to retrieve the amount of used tokens for each given AI model call?
Many thanks in advance

K

khoi•9/23/25, 9:33 PM

Has anyone used Smart Turn V2 for voice activity detection via Workers AI?

Seems like Smart Turn is optimized for full audio clips -- does Cloudflare automatically do that for us over the websocket? Or...

Notes on input format

Smart Turn takes 16kHz PCM audio as input. Up to 8 seconds of audio is supported, and we recommend providing the full audio of the user's current turn.

The model is designed to be used in conjunction with a lightweight VAD model such as Silero. Once the VAD model detects silence, run Smart Turn on the entire recording of the user's turn, truncating from the beginning to shorten the audio to around 8 seconds if necessary.

If additional speech is detected from the user before Smart Turn has finished executing, re-run Smart Turn on the entire turn recording, including the new audio, rather than just the new segment. Smart Turn works best when given sufficient context, and is not designed to run on very short audio segments.

Note that audio from previous turns does not need to be included.

A

ALECKS•9/24/25, 8:19 PM

~~Is there a way to disable the Agent sdk logging of state changes? It seems to output messages like this on every state change:~~

AALECKS ~~ Is there a way to disable the Agent sdk logging of state changes? It seems t...

S

samjs•9/24/25, 8:25 PM

Hey @ALECKS , there's a dedicated channel #agents for agents SDK that will have more info for you

H

Hew•9/25/25, 6:04 PM

So in the August blog post announcing the gpt-oss models, it's mentioned that chat/completions endpoint support is "coming soon". It's been almost two months now. Any update on what "soon" means?

K

khoi•9/25/25, 9:47 PM

Has anyone used the Nova-3 Deepgram STT model with endpointing and interim results on? For me, it doesn't seem like the endpointing does anything?

J

Jeffrey•9/27/25, 12:15 AM

Anyone using the playwright-mcp worker and happen to know what the correct endpoint is to retrieve screenshots/pdfs? The repo shows image responses in their example, but I've never gotten an actual response back with the screenshot or pdf, just a /tmp/ path that returns nothing when visiting the url directly...

https://github.com/cloudflare/playwright-mcp/tree/main

GitHub

GitHub - cloudflare/playwright-mcp: Playwright MCP fork that works ...

Playwright MCP fork that works with Cloudflare Browser Rendering - cloudflare/playwright-mcp

P

pietrolc.com•9/27/25, 3:55 PM

Is checking for nsfw worth or are ai workers always checking for that?

Ppietrolc.com Is checking for nsfw worth or are ai workers always checking for that?

T

toadilywasted•9/28/25, 1:26 AM

They usually block it already but likely depends on your use case

C

CodingCoop | Co-Founder Nullshot•9/28/25, 4:43 AM

I’m looking for access to Claude and other models before I build against something like open router.

Anyone I can connect to? Happy to pay and we are a startup - I’d joining the startup programs help, please advise.

I already sent a request into the beta form and didn’t get anything

CCodingCoop | Co-Founder Nullshot I’m looking for access to Claude and other models before I build against somethi...

I

Isaac McFadyen•9/28/25, 10:02 AM

Workers AI is Cloudflare-run models only, which does not include Claude.

C

CodingCoop | Co-Founder Nullshot•9/28/25, 1:00 PM

Am I getting confused with gateway?

C

CodingCoop | Co-Founder Nullshot•9/28/25, 1:04 PM

Sorry I did https://blog.cloudflare.com/ai-gateway-aug-2025-refresh/

The Cloudflare Blog

AI Gateway now gives you access to your favorite AI models, dynamic...

AI Gateway simplifies AI app development with unified billing, secure key storage, and dynamic routing. Gain observability and control over costs, API keys, and traffic, connecting to major AI providers through a single endpoint.

Z

zsueo•9/28/25, 5:47 PM

out of curiosity does workers-ai use durable objects with web-gpu internally? or is it an entirely custom cloudflare product?

Zzsueo out of curiosity does workers-ai use durable objects with web-gpu internally? or...

I

Isaac McFadyen•9/28/25, 5:50 PM

A mix of custom and off-the-shelf engines, no WebGPU. It's been blogged about here: https://blog.cloudflare.com/how-cloudflare-runs-more-ai-models-on-fewer-gpus/

I

Isaac McFadyen•9/28/25, 5:51 PM

See specifically this section: https://blog.cloudflare.com/how-cloudflare-runs-more-ai-models-on-fewer-gpus/#how-omni-runs-multiple-models-for-workers-ai

AI models can run in a variety of inference engines or backends: vLLM, Python, and now our very own inference engine, Infire.

Z

zsueo•9/28/25, 5:53 PM

ah cool thanks!

A

Ashkan•9/29/25, 4:31 PM

I encountered this error:

error executing callback "..." Error: Attempting to read .name on ScheduleJobAgent before it was set. The name can be set by explicitly calling .setName(name) on the stub, or by using routePartyKitRequest(). This is a known issue and will be fixed soon. Follow https://github.com/cloudflare/workerd/issues/2240 for more updates.

error executing callback "..." Error: Attempting to read .name on ScheduleJobAgent before it was set. The name can be set by explicitly calling .setName(name) on the stub, or by using routePartyKitRequest(). This is a known issue and will be fixed soon. Follow https://github.com/cloudflare/workerd/issues/2240 for more updates.

error executing callback "..." Error: Attempting to read .name on ScheduleJobAgent before it was set. The name can be set by explicitly calling .setName(name) on the stub, or by using routePartyKitRequest(). This is a known issue and will be fixed soon. Follow https://github.com/cloudflare/workerd/issues/2240 for more updates.

error executing callback "..." Error: Attempting to read .name on ScheduleJobAgent before it was set. The name can be set by explicitly calling .setName(name) on the stub, or by using routePartyKitRequest(). This is a known issue and will be fixed soon. Follow https://github.com/cloudflare/workerd/issues/2240 for more updates.

I put setName everywhere in the codebase to fix it but no success. do u have any idea to temporary resolve it until major updates come?

AAshkan Hello, when I want to poll batch request I encounter this error: `Error: 3030: 1...

K

Kevin•9/29/25, 5:06 PM

Hey can you share an example payload you’re sending for polling the batch request

KKevin Hey can you share an example payload you’re sending for polling the batch reques...

A

Ashkan•9/29/25, 10:17 PM

I've had that error almost days ago(I can't remember the payload) but the problem was related to JSON format of the

payload

payload

and I could resolve the error. although the error resolved and no more exceptions were thrown but when I was checking status of the batch job it was showing

invalid parameters

invalid parameters

invalid parameters

invalid parameters. so I decided to suspend my works around the batch processing until stable version of that is announced.

AAshkan I've had that error almost days ago(I can't remember the payload) but the proble...

A

Ashkan•9/29/25, 10:22 PM

this is the part of the code I was using for batch process:

const response = args.env.AI.run(
                    '@cf/openai/gpt-oss-120b' as any,
                    {
                        requests: [input],
                    },
                    { queueRequest: true, gateway: { id: GATEWAY_ID } }
                );

const response = args.env.AI.run(
                    '@cf/openai/gpt-oss-120b' as any,
                    {
                        requests: [input],
                    },
                    { queueRequest: true, gateway: { id: GATEWAY_ID } }
                );

const response = args.env.AI.run(
                    '@cf/openai/gpt-oss-120b' as any,
                    {
                        requests: [input],
                    },
                    { queueRequest: true, gateway: { id: GATEWAY_ID } }
                );

const response = args.env.AI.run(
                    '@cf/openai/gpt-oss-120b' as any,
                    {
                        requests: [input],
                    },
                    { queueRequest: true, gateway: { id: GATEWAY_ID } }
                );

A

Ashkan•9/29/25, 10:24 PM

it should be noted

input

input

of type

Array

Array

Array

Array worked but I wasn't able to run it when

input

input

was of type

string

string

(openai compatible JSON format)

D

displayname•9/29/25, 10:44 PM

Hey, could we please get some eyes on workers-and-pages-helpOpenAI Completions compatibility for gpt-oss models?
Sorry I didn't know where to open the thread

A

ajgeiss0702•9/30/25, 1:23 AM

just got an error i havent seen before with

gpt-oss-20b

gpt-oss-20b

gpt-oss-20b

gpt-oss-20b

AiError: AiError: EngineCore encountered an issue. See stack trace (above) for the root cause. (50d9f590-dc24-4cf3-92b4-313011575443)

AiError: AiError: EngineCore encountered an issue. See stack trace (above) for the root cause. (50d9f590-dc24-4cf3-92b4-313011575443)

AiError: AiError: EngineCore encountered an issue. See stack trace (above) for the root cause. (50d9f590-dc24-4cf3-92b4-313011575443)

AiError: AiError: EngineCore encountered an issue. See stack trace (above) for the root cause. (50d9f590-dc24-4cf3-92b4-313011575443)

account id:

f55b85c8a963663b11036975203c63c0

f55b85c8a963663b11036975203c63c0

f55b85c8a963663b11036975203c63c0

f55b85c8a963663b11036975203c63c0
(there is no stack trace above)

Z

Zetax•10/1/25, 6:29 AM

I wish the types would work for this

Wanted to try out a model and the response type for it is completely broken.

Bildschirmfoto_2025-10-01_um_08.28.55.png

J

James•10/2/25, 6:34 PM

Workers AI types need a lot of love, yeah.
- https://github.com/cloudflare/workerd/issues/2181
- https://github.com/cloudflare/workerd/issues/2418
- https://github.com/cloudflare/workerd/issues/5080

N

Nova Sven Cat•10/3/25, 7:14 PM

I'm using workers AI with the free plan and it still works even when I reached the quota, what is happening?

N

Nova Sven Cat•10/3/25, 8:00 PM

Daily usage (resets at 00:00 UTC) - Neurons used today: 32.48k/10k

N

Nova Sven Cat•10/3/25, 8:28 PM

You have exceeded the Neuron limit of 10,000 for this today. Upgrade your plan

NNova Sven Cat > You have exceeded the Neuron limit of 10,000 for this today. Upgrade your plan

Z

Zetax•10/3/25, 9:58 PM

why would you report that though

launched vectorize to prod today it works great

Similar Threads

Similar Threads

Similar Threads