hi guys is there a way I can add like 80KB worth of text as instructions to the AI -- KV, D1 maybe?

Ccosmos hi guys is there a way I can add like 80KB worth of text as instructions to the ...

F

fry69•11/6/24, 7:56 AM

In a constant variable If those instructions change only on build time at worst? Otherwise D1, KV, R2 depending on your needs.

A

Ali_hat•11/6/24, 9:48 PM

Hey guys, we're using the Workers AI REST API (

llama-3.1-70b-instruct

llama-3.1-70b-instruct

llama-3.1-70b-instruct

llama-3.1-70b-instruct) and, for some reason, I'm currently unable to see in Cloudflare dashboard how much we've been consuming. Any ideas?

B

boommachine•11/8/24, 5:34 AM

how to generate custom sized images instead of square shaped using flux in cloudfare ai?

M

maahin•11/8/24, 6:46 AM

How to check models accuracy which has been provided by cloudflare as in analytics it provides me request and errors of api call

Ccosmos hi guys is there a way I can add like 80KB worth of text as instructions to the ...

M

maahin•11/8/24, 6:47 AM

You can pass it as chunks

B

Brandon Studio•11/11/24, 2:15 AM

Would Workers AI allow cross-origin request?

0

0x7d8•11/11/24, 5:43 PM

do workers stay online after a request is made to handle further requests or do they get shutdown instantly?

00x7d8 do workers stay online after a request is made to handle further requests or do ...

F

fry69•11/11/24, 5:45 PM

Usually workers exit when they have done their work

I

Isaac McFadyen•11/11/24, 6:42 PM

^ they can stay online for a little bit but different users will likely hit different servers (meaning they won't hit the same Worker) and Workers are not guaranteed to stay online at all.

A

Advany•11/12/24, 8:20 AM

Can we please get... Qwen2.5-Coder-32B-Instruct on cloudflare AI?

S

Sean•11/12/24, 9:29 AM

Can anyone make LoRA adapters work? I'm constantly getting

{"errors":[{"message":"AiError: AiError: Unknown internal error","code":3028}],"success":false,"result":{},"messages":[]}

{"errors":[{"message":"AiError: AiError: Unknown internal error","code":3028}],"success":false,"result":{},"messages":[]}

{"errors":[{"message":"AiError: AiError: Unknown internal error","code":3028}],"success":false,"result":{},"messages":[]}

{"errors":[{"message":"AiError: AiError: Unknown internal error","code":3028}],"success":false,"result":{},"messages":[]}

. The example from the docs doesn't work either https://developers.cloudflare.com/workers-ai/fine-tunes/public-loras/ . Tried the cURL command using my token, same error. Saw a few messages related to this before, but seems like there aren't any solution yet.

Cloudflare Docs

Public LoRA adapters | Cloudflare Workers AI docs

Cloudflare offers a few public LoRA adapters that are immediately ready for use.

�

😈 Donkey 💫•11/13/24, 6:04 AM

the ony one supports function: @hf/nousresearch/hermes-2-pro-mistral-7b so terrible?
it even retrieves kind of tool_calls which is not in pre-defined list

const tool_response = await env.AI.run(
    "@hf/nousresearch/hermes-2-pro-mistral-7b",
    {
        messages: [
            { role: "user", content: query },
        ],
        temperature: 0.2,
        tools: [
            {
                type: "function",
                function: {
                    name: "get-weather",
                    description: "Gets weather information of a particular city",
                    parameters: {
                        type: "object",
                        properties: {
                            city: {
                                type: "string",
                                description: "The city name",
                            },
                            country: {
                                type: "string",
                                description: "The country name",
                            }
                        },
                        required: ["city"],
                    }
                }
            },
            {
                type: "function",
                function: {
                    name: "search-google",
                    description: "Gets general data from Google",
                    parameters: {
                        type: "object",
                        properties: {
                            keyword: {
                                type: "string",
                                description: "The keywords for searching",
                            },
                        },
                        required: ["keyword"],
                    }
                }
            },
        ],
    }
);

const selected_tool = tool_response?.tool_calls?.[0];
console.log({ selected_tool });

const tool_response = await env.AI.run(
    "@hf/nousresearch/hermes-2-pro-mistral-7b",
    {
        messages: [
            { role: "user", content: query },
        ],
        temperature: 0.2,
        tools: [
            {
                type: "function",
                function: {
                    name: "get-weather",
                    description: "Gets weather information of a particular city",
                    parameters: {
                        type: "object",
                        properties: {
                            city: {
                                type: "string",
                                description: "The city name",
                            },
                            country: {
                                type: "string",
                                description: "The country name",
                            }
                        },
                        required: ["city"],
                    }
                }
            },
            {
                type: "function",
                function: {
                    name: "search-google",
                    description: "Gets general data from Google",
                    parameters: {
                        type: "object",
                        properties: {
                            keyword: {
                                type: "string",
                                description: "The keywords for searching",
                            },
                        },
                        required: ["keyword"],
                    }
                }
            },
        ],
    }
);

const selected_tool = tool_response?.tool_calls?.[0];
console.log({ selected_tool });

const tool_response = await env.AI.run(
    "@hf/nousresearch/hermes-2-pro-mistral-7b",
    {
        messages: [
            { role: "user", content: query },
        ],
        temperature: 0.2,
        tools: [
            {
                type: "function",
                function: {
                    name: "get-weather",
                    description: "Gets weather information of a particular city",
                    parameters: {
                        type: "object",
                        properties: {
                            city: {
                                type: "string",
                                description: "The city name",
                            },
                            country: {
                                type: "string",
                                description: "The country name",
                            }
                        },
                        required: ["city"],
                    }
                }
            },
            {
                type: "function",
                function: {
                    name: "search-google",
                    description: "Gets general data from Google",
                    parameters: {
                        type: "object",
                        properties: {
                            keyword: {
                                type: "string",
                                description: "The keywords for searching",
                            },
                        },
                        required: ["keyword"],
                    }
                }
            },
        ],
    }
);

const selected_tool = tool_response?.tool_calls?.[0];
console.log({ selected_tool });

const tool_response = await env.AI.run(
    "@hf/nousresearch/hermes-2-pro-mistral-7b",
    {
        messages: [
            { role: "user", content: query },
        ],
        temperature: 0.2,
        tools: [
            {
                type: "function",
                function: {
                    name: "get-weather",
                    description: "Gets weather information of a particular city",
                    parameters: {
                        type: "object",
                        properties: {
                            city: {
                                type: "string",
                                description: "The city name",
                            },
                            country: {
                                type: "string",
                                description: "The country name",
                            }
                        },
                        required: ["city"],
                    }
                }
            },
            {
                type: "function",
                function: {
                    name: "search-google",
                    description: "Gets general data from Google",
                    parameters: {
                        type: "object",
                        properties: {
                            keyword: {
                                type: "string",
                                description: "The keywords for searching",
                            },
                        },
                        required: ["keyword"],
                    }
                }
            },
        ],
    }
);

const selected_tool = tool_response?.tool_calls?.[0];
console.log({ selected_tool });

�

😈 Donkey 💫•11/13/24, 6:04 AM

  selected_tool: {
    arguments: { from_currency: 'USD', to_currency: 'CNY' },
    name: 'get-currency-exchange-rate'
  }

  selected_tool: {
    arguments: { from_currency: 'USD', to_currency: 'CNY' },
    name: 'get-currency-exchange-rate'
  }

  selected_tool: {
    arguments: { from_currency: 'USD', to_currency: 'CNY' },
    name: 'get-currency-exchange-rate'
  }

  selected_tool: {
    arguments: { from_currency: 'USD', to_currency: 'CNY' },
    name: 'get-currency-exchange-rate'
  }

C

catnaut.•11/13/24, 11:40 AM

News for multilingual embedding model ?

Ppkd but no solution

S

Sean•11/14/24, 4:42 PM

Tried custom lora on gemma-2b too, same error

F

Fernando Dilland•11/16/24, 4:09 PM

Cloudflare Workers AI + WordPress, I'm sharing this WordPress plugin I've created to use the CF REST API and enable webchat. Feedback, suggestions, and improvements are welcome! :MeowHeartCloudflare:

https://github.com/fernandodilland/workers-ai-chat

GitHub

GitHub - fernandodilland/workers-ai-chat: Uses Cloudflare Workers A...

Uses Cloudflare Workers AI in a web chat embedded via shortcode. - fernandodilland/workers-ai-chat

LLogan Grasby This is long overdue some attention and we have some big updates coming soon! I ...

A

ajgeiss0702•11/17/24, 7:13 PM

any news on this?

Ppkd except getting hired at cf, fixing the bug and quitting

S

Sean•11/18/24, 6:26 AM

Seems like there's no solution found online, but I'm sure there're working hard on that. Let's wait patiently.

LLogan Grasby This is long overdue some attention and we have some big updates coming soon! I ...

A

Advany•11/18/24, 10:37 AM

can't wait on the updates

seems like you guys are working on a lot of updates to AI

LLogan Grasby Updates like @cf/openai/whisper-large-v3 with inputs: ``` { "task": "translat...

I

Isaac McFadyen•11/19/24, 2:48 AM

this is quite awesome, but also interesting timing given Whisper V3 Turbo just got released with quality matching

large-v2

large-v2

large-v2

large-v2 while speeds are on par with

base

base

base

base :lul:

I

Isaac McFadyen•11/19/24, 2:48 AM

https://huggingface.co/openai/whisper-large-v3-turbo

I

Isaac McFadyen•11/19/24, 2:52 AM

If you're targeting translation though that makes sense, I think Turbo is only for direct transcription

LLogan Grasby Updates like @cf/openai/whisper-large-v3 with inputs: ``` { "task": "translat...

C

Chaika•11/19/24, 3:03 AM

hmm guessing it's still cooking? It throws

        "message": "5006: must be string, 'audio' must be array, must match exactly one schema in oneOf"

"message": "5006: must be string, 'audio' must be array, must match exactly one schema in oneOf"

        "message": "5006: must be string, 'audio' must be array, must match exactly one schema in oneOf"

"message": "5006: must be string, 'audio' must be array, must match exactly one schema in oneOf" despite you saying it's a base64 string lol

LLogan Grasby It's actually whisper-large-v3-turbo and will be called that when released 🙂

I

Isaac McFadyen•11/19/24, 3:07 AM

Oh awesome

LLogan Grasby Try again in a few mins. It's unreleased and may not work as expected so be warn...

C

Chaika•11/19/24, 4:19 AM

oo cool, working now!

K

kyle•11/19/24, 9:46 PM

are beta models still free to use? even image models? I think they used to be that way

K

kyle•11/19/24, 11:43 PM

I'm also running into the issue where flex-1-schnell has an overactive nsfw filter.

"cyberpunk cat"

"cyberpunk cat"

"cyberpunk cat"

"cyberpunk cat" is marked nsfw

J

James•11/20/24, 1:29 AM

Just a heads up, but @cf/google/gemma-7b-it-lora is returning mostly blank responses for me regardless of prompt.

K

kyle•11/20/24, 4:34 AM

would love for

flex-1-schnell

flex-1-schnell

flex-1-schnell

flex-1-schnell to have height/width options

K

kyle•11/20/24, 4:35 AM

the model on Replicate, has a megapixel param

L

leesus•11/20/24, 3:09 PM

Is there any plan to support prompts for Whisper (/ are they supported currently just not documented)?

LLogan Grasby The unreleased version above supports "initial_prompt", and "prefix". Until the ...

A

Advany•11/20/24, 5:28 PM

I love how you guys can leak stuff unofficially haha! Cloudflare has a great culture man!

LLogan Grasby Trust me not everyone like my leaks but the people need models

A

Advany•11/20/24, 7:16 PM

with a company the size of cloudflare... no one likes everything. You are doing good work by leaking haha

T

TK•11/21/24, 10:49 PM

Hello, appears that @cf/meta/m2m100-1.2b is down or consistently returning 429s anyway, failing a bunch of workers I have

TTK Hello, appears that @cf/meta/m2m100-1.2b is down or consistently returning 429s ...

�

😈 Donkey 💫•11/22/24, 4:40 PM

this GA model is a night mare, unstable and truncate input unexpectedly

hi guys is there a way I can add like 80KB worth of text as instructions to the AI -- KV, D1 maybe?

Similar Threads