Hi, guys, I have a problem and I have a lot of doubts about how I can solve it, and I'm thinking abo

Hi, guys, I have a problem and I have a lot of doubts about how I can solve it, and I'm thinking about using supervised learning. Here's the problem: I have a price comparison tool and I need to be validating, buying, identifying products that are identical but with different characteristics, for example, GOD OF WAR = GOD OF WAR 2018 = GOD OF WAR ™, this is one of the examples I've been facing. Can you give me an idea of a tool or something that can help me with this, I'm studying it but I'm extremely lost on how I can do this.

ac•10/16/24, 7:19 PM

Hi, I'm having an issue where CF AI has completely stopped working from my local environment (yesterday it was working fine). Not getting any errors or anything, just the AI is obviously not running and not returning anything. Has anything changed with how Cloudflare handles this?

Aac Hi, I'm having an issue where CF AI has completely stopped working from my local...

ac•10/16/24, 7:37 PM

To add to this, it is explicility llama-3-8b-instruct. Changing it to a different model (3.1-8b) fixed it. This seems to only happen from my local environment -- production calls to 3-8b seem to still be working fine.

Raylight•10/17/24, 7:34 AM

Any chance of higher free allocations (i.e. tokens/steps/units per day) on the Workers Paid plan? Like.. something that's more in line with the spirit of the rest of the Workers platform where the limits are (more than) generous enough to build a simple prototype or follow a tutorial.

Looking at the table (https://developers.cloudflare.com/workers-ai/platform/pricing/#free-allocation), taking image generation as example, you'd easily hit 250 steps just to fix a simple bug or help someone out.

[[FDG] H4kuna Hi, guys, I have a problem and I have a lot of doubts about how I can solve it, ...

Keebs•10/17/24, 4:09 PM

identify the main title, offer alternative options to drill down to the user, probably best solution

Keebs•10/17/24, 4:09 PM

its like "apple iphone" :D

ajgeiss0702•10/19/24, 7:47 PM

any idea when the dashboard will be updated to show the new unit of billing?
Also is there any way to get that now?

shoo•10/20/24, 8:42 PM

guys - are beta models still free? (i remember they used to be)
I couldn't find that in documentation anymore

0xPh4s3•10/21/24, 11:19 AM

Hey guys, I would like to ask whether the LLM in cf worker AI is full precision or quantized, such as LLaMA3.1:70b

fry69•10/21/24, 11:25 AM

?crossposting

Flare•10/21/24, 11:25 AM

Please do not post your question in multiple channels/post it multiple times per the rules at ⁠#

welcome-and-rules. It creates confusion for people trying to help you and doesn't get your issue or question solved any faster.

Sshoo guys - are beta models still free? (i remember they used to be) I couldn't find ...

Erisa•10/21/24, 11:41 AM

yes

0xPh4s3•10/21/24, 11:44 AM

sry

0xPh4s3•10/21/24, 11:45 AM

:MeowHeartCloudflare:

crazyjack12•10/21/24, 8:26 PM

Any updates on the use any model beta

�

😈 Donkey 💫•10/22/24, 11:39 AM

i believe @cf/meta/llama-3.1-8b-instruct-fast in problem, in several days, it usually returns empty answer

Phanindra Reddy•10/22/24, 4:14 PM

hey guys i am to use llama 3.2 but it is getting an error in workers, how can i use it

Ben-xD•10/22/24, 8:11 PM

is there a way to check the context length of models hosted on cf?

ExploringBildr•10/23/24, 9:58 AM

Hello, I'm trying to set up Worker AI. I got this {"response":"Content-Type invalid"}
Any thoughts?

EExploringBildr Hello, I'm trying to set up Worker AI. I got this {"response":"Content-Type inva...

fry69•10/23/24, 10:11 AM

Check if your AI request works with

curl

curl

and when it does implement it inside the worker. Example request that works for me ->

curl -X POST \
  https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/run/@cf/meta/llama-3-8b-instruct \
  -H "Authorization: Bearer ${CLOUDFLARE_API_TOKEN}" \
  -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 "
    }
  ]
}' \
  | jq

curl -X POST \
  https://api.cloudflare.com/client/v4/accounts/${CLOUDFLARE_ACCOUNT_ID}/ai/run/@cf/meta/llama-3-8b-instruct \
  -H "Authorization: Bearer ${CLOUDFLARE_API_TOKEN}" \
  -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 "
    }
  ]
}' \
  | jq

ExploringBildr•10/23/24, 10:30 AM

OK. I got it working

ExploringBildr•10/23/24, 10:30 AM

Where do I add stream: true, max_tokens: 2048,

EExploringBildr Where do I add stream: true, max_tokens: 2048,

fry69•10/23/24, 10:35 AM

On the same level as messagesmessages, in doubt ask any chatbot website to format this correctly for you.

InventorAI•10/23/24, 2:05 PM

Hi I am using https://developers.cloudflare.com/workers-ai/models/llama-2-7b-chat-int8/

can anyone please suggest me how can I calculate Input and Output token for price calculation

Cloudflare Docs

llama-2-7b-chat-int8 | Cloudflare Workers AI docs

Quantized (int8) generative text model with 7 billion parameters from Meta

IInventorAI Hi I am using https://developers.cloudflare.com/workers-ai/models/llama-2-7b-cha...

fry69•10/23/24, 2:07 PM

See here -> https://developers.cloudflare.com/workers-ai/platform/pricing/#pricing-structure

Cloudflare Docs

Pricing | Cloudflare Workers AI docs

Workers AI is included in both the Free and Paid Workers plans and is priced based on model task, model size, and units.

Ffry69 See here -> https://developers.cloudflare.com/workers-ai/platform/pricing/#prici...

InventorAI•10/23/24, 2:10 PM

Please suggest me programeticaly how can calculate the price when any API call perform

IInventorAI Please suggest me programeticaly how can calculate the price when any API call p...

fry69•10/23/24, 2:13 PM

That would require tokenization which is different for every LLM. If you only need one model it might work, but if you plan to switch between models and even providers, you might need to reach out for something like -> https://www.helicone.ai/

Ffry69 That would require tokenization which is different for every LLM. If you only ne...

InventorAI•10/24/24, 7:18 AM

Hi right now I am working on https://developers.cloudflare.com/workers-ai/models/llama-2-7b-chat-int8/
This is from cloudflare, so I want to calculation of token for this CF model

Cloudflare Docs

llama-2-7b-chat-int8 | Cloudflare Workers AI docs

Quantized (int8) generative text model with 7 billion parameters from Meta

IInventorAI Hi right now I am working on https://developers.cloudflare.com/workers-ai/models...

fry69•10/24/24, 7:25 AM

Well, google for a LLama 2 tokenizer then, e.g. -> https://github.com/belladoreai/llama-tokenizer-js (or use the official Python Sentencepiece tokenizer like this -> https://github.com/meta-llama/llama/blob/main/llama/tokenizer.py)

GitHub

GitHub - belladoreai/llama-tokenizer-js: JS tokenizer for LLaMA 1 a...

JS tokenizer for LLaMA 1 and 2. Contribute to belladoreai/llama-tokenizer-js development by creating an account on GitHub.

Ffry69 Well, google for a LLama 2 tokenizer then, e.g. -> https://github.com/belladorea...

InventorAI•10/24/24, 7:30 AM

Is Cloudflare not providing anything related to this?

IInventorAI Is Cloudflare not providing anything related to this?

fry69•10/24/24, 7:39 AM

Nope. Cloudflare AI does not even return the token amount in the response or anywhere else as far as I can see.

�

😈 Donkey 💫•10/24/24, 11:12 AM

flux is weird, usually happens

kcbrewron•10/24/24, 2:41 PM

Good morning, periodically when I run batches of updates to content using vectorize,I receive an error AiError: 3001: Unknown interal error. How can I get more insights on what's going on?

Could this be too many requests on the AI requests?
For embedding

fry69•10/24/24, 2:42 PM

?crossposting

Flare•10/24/24, 2:42 PM

Please do not post your question in multiple channels/post it multiple times per the rules at ⁠#

welcome-and-rules. It creates confusion for people trying to help you and doesn't get your issue or question solved any faster.

ExploringBildr•10/25/24, 11:09 AM

Hello, the response I'm getting isn't in an accurate json format. Anyone knows how to fix it?

EExploringBildr Hello, the response I'm getting isn't in an accurate json format. Anyone knows h...

fry69•10/25/24, 11:12 AM

What you get from the API is guaranteed to be valid JSON, but if you ask a LLM to reply with JSON (inside the responseresponse property), it may not work. LLMs are trained to generate text not JSON.

fry69•10/25/24, 11:14 AM

(some very recent advanced LLMs have learned a few JSON tricks, but their responses suffer in quality if you use those)

Ffry69 What you get from the API is guaranteed to be valid JSON, but if you ask a LLM t...

ExploringBildr•10/25/24, 11:15 AM

Thanks. Then, I need help to make my API call return a json. Now, it's returning a string?

EExploringBildr Thanks. Then, I need help to make my API call return a json. Now, it's returning...

fry69•10/25/24, 11:16 AM

A string is valid JSON, you have to parse it.

ExploringBildr•10/25/24, 11:16 AM

I tried to parse, but because of all the " and , it's not working for me.

ExploringBildr•10/25/24, 11:18 AM

I need to have a way to make the API call return a json without the unneccesary escape characters

EExploringBildr I need to have a way to make the API call return a json without the unneccesary ...

fry69•10/25/24, 11:18 AM

I do not see those escape chars when I use the API, see e.g. -> workers-ai

fry69•10/25/24, 11:19 AM

If jqjq is happy so should any JSON parser

Original message was deleted

ExploringBildr•10/25/24, 5:22 PM

Workers AI REST API

Original message was deleted

ExploringBildr•10/25/24, 5:32 PM

curl -X POST \
https://api.cloudflare.com/client/v4/accounts/[....]/run/@cf/mistral/mistral-7b-instruct-v0.1 \
-H "Authorization: Bearer [....]" \
-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 "}]}'

ExploringBildr•10/26/24, 4:29 AM

It's solved now

blindChicken•10/26/24, 8:26 PM

I'm trying to use Cloudflare worker-AI with langchain to embed some text. Specifically I'm trying to use the OpenAIEmbeddingsOpenAIEmbeddings library to send text to my AI-worker. What I noticed is that the embed_documentsembed_documents method doesn't send the text to the endpoint provided but rather sends an array of tokens. On the other hand the CF embedding models/methods expects strings as inputs. Anyone know how to resolve this? Is there specific Langchain library for Cloudflare, or is there a way to input tokens into the CF models?

celeste_y•10/28/24, 2:44 AM

In my application, I need to create embeddings for articles and queries in both Chinese and English. However, the embedding models supported by Worker-AI are English-only models. I am thinking about calling out to an external inference API which supports multi-lingual embedding, then insert into/ query the embedding with Cloudfare Vectorize. Before doing that, I want to check and see if there is a more cloudfare native way to support multi-lingual embedding as I would like to keep my whole workflow on Cloudfare if possible. Thank you!

surgery18•10/28/24, 1:28 PM

Any chance of getting suno/bark and other AI TTS models added to available models we can use in workers AI?

Hi, guys, I have a problem and I have a lot of doubts about how I can solve it, and I'm thinking abo

Similar Threads

Similar Threads

Similar Threads