Cloudflare Developers

CD

Cloudflare Developers

Welcome to the official Cloudflare Developers server. Here you can ask for help and stay updated with the latest news

Join

workers-help

pages-help

general-help

durable-objects

workers-discussions

pages-discussions

wrangler

coding-help

kv

🦀rust-on-workers

miniflare

stream

general-discussions

functions

zaraz

⚡instant-logs

email-routing

r2

pubsub-beta

analytics-engine

d1-database

queues

workers-for-platforms

workerd

web3

🤖turnstile

radar

web-research

logs-engine

cloudflare-go

terraform-provider-cloudflare

workers-ai

browser-rendering-api

analytics

next-on-pages

cloudflare-ai

build-caching-beta

hyperdrive

vectorize

ai-gateway

python-workers-beta

vitest-integration-beta

workers-observability

workflows-beta

d
d
View on Discord
2/27/2024

Howdy y'all, I'm trying your API for the

Howdy y'all, I'm trying your API for the Worker AI stuff by following the example but keep getting errors: ```bash curl -X POST \ https://api.cloudflare.com/client/v4/accounts/MYACCTID/ai/run/@cf/meta/llama-2-7b-chat-int8 \ -H "Authorization: Bearer MYTOKEN" \ -d '{"messages":[{"role":"system","content":"You are a friendly assistant that helps write stories"},{"role":"user","content":"Write a short story about a llama that goes on a journey to find an orange cloud "}]}'...
Cedrick
Cedrick
View on Discord
12/5/2023

```

``` curl --location 'https://api.cloudflare.com/client/v4/accounts/{my-account}/ai/run/@cf/mistral/mistral-7b-instruct-v0.1' \ --header 'Authorization: Bearer {mytoken}' \ --header 'Content-Type: application/json' \ --data '{ ...
Ben-xD
Ben-xD
View on Discord
10/29/2023

I increased the detail:

I increased the detail:
"Convert the users next message content into a duration in seconds. Provide the user only 1 number, with no other words, units or formatting. For example, if the user says '5 minutes', you should return '300'. If the user says 'the time it takes for the average person to run 100m', you should return '20'."
But even ChatGPT 3.5 turbo isn't very good at this. Running it a few times: 31536000s 30000000s...
Erisa
Erisa
View on Discord
10/4/2023

From my understanding you should be able

From my understanding you should be able to stream the response body returned by ai.run?
Nick
Nick
View on Discord
10/4/2023

Hi I m trying out the LLM worker and I m

Hi! I'm trying out the LLM worker and I'm wondering if it's possible to return the response as a stream? similar to https://developers.cloudflare.com/workers/examples/openai-sdk-streaming/ ?
Falco
Falco
View on Discord
10/3/2023

So when running BGE models for

So when running BGE models for embeddings you must prepend your docs with Represent this sentence for searching relevant passages:. From what I can see this is uncessesary in the WorkersAI API right? So the API does that for me automatically? In both batch and single inputs?
Łukasz
Łukasz
View on Discord
10/2/2023

Full code straight from the tutorial

Full code, straight from the tutorial: ``` import { Ai } from '@cloudflare/ai' export default {...
Previous