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

i wrote an extremely lenient parser in

i wrote an extremely lenient parser in typescript (published to npm) specifically to handle bad JSON output from LLMs: https://github.com/acusti/uikit/tree/main/packages/parsing
import { parseAsJSON } from '@acusti/parsing';
const parsedResult = parseAsJSON(resultFromLLM);
import { parseAsJSON } from '@acusti/parsing';
const parsedResult = parseAsJSON(resultFromLLM);
...

Has anyone gotten Vercel AI Package

Has anyone gotten Vercel AI Package working with streamText and Cloudflare AI models? I am getting the following error and it's only when I am streaming (generateText works fine). I will note I am using a modified baseURL in an OpenAI provider to make CF AI work with Vercel AI package. "Error message: [ { "code": "invalid_union",...

Flux also returns a 500 error for me and

Flux also returns a 500 error for me and other users in this discord, any idea why?

hey did you ever get openai compat

hey did you ever get openai compat endpoint working? I'm egtting an error

which model can out-perform GPt4? I mean

which model can out-perform GPt4? I mean will the big model be supported later?

Getting no responses from whisper ai :/

Getting no responses from whisper ai :/
No description

The docs describe `stable-diffusion-xl-

The docs describe stable-diffusion-xl-base-1.0 as:
Diffusion-based text-to-image generative model by Stability AI. Generates and modify images based on text prompts.
I'm trying to use it to modify an image (inpainting with an image & mask) but am getting the following error: InferenceUpstreamError: ERROR 3030: Model input is not valid: input tensor ``image`` is not present in the model....

text to image not working

Just trying out text-to-image generation - seems the num_steps parameter is required - If I don't provide it I get the error: Uncaught Error: unexpected type "int32" with value "undefined". This is contrary to the docs: https://developers.cloudflare.com/workers-ai/models/text-to-image/

I am trying to call workers ai using

I am trying to call workers ai using langchain in a worker, I have the code setup but get Cloudflare LLM call failed with status code 404. Maybe my environment variables are not setup right? But I cannot tell because console.log's apparently do not show when running wrangler dev... Am I missing something obvious here? ``` import type { D1Database } from '@cloudflare/workers-types'; import { Hono } from 'hono';...

Cloudflare Workers AI meta llama 2 7b

Cloudflare Workers AI meta/llama-2-7b-chat-int8 model is not working properly, the response to the question is the formatted question it self. Posting the request and response in the thread to avoid long message....

Where does the docs say `inputs` The

Where does the docs say inputs? The only places I found said prompt: "" or messages: []

Llama Token Counter - a Hugging Face Spa...

Hi, using llama2 from a cloudflare worker using the ai.run binding, and finding that the responses I get back get cut off after < 300 tokens. Is there a way to set the token limit for a response to something higher than whatever it's set to? A silly example, to illustrate, where I ask for a recipe for potatoes au gratin with bubble gum syrup, gets cut off midway through the instructions... ```...