II
KK
VV
ai-utils. I spend a lot of time troubleshooting it, it tracks token usage wrong (returns only the last ones), calls AI.run more often than necessary, etc. See #Is module @cloudflare/ai-utils stable? > I just wrote the function calling in my own code, works way better, and doesn't inflict double usage consumption. And I'd recommend you to do so, too, tbh
M
I
NKKAAI
SI
C
MM
B
Error: 8001: Invalid input when I try to call tools using @cf/meta/llama-4-scout-17b-16e-instruct. If I call the model without tools it works fines, but if add the tools array it throws the error. Here is my tools array:await AI.run( model, { messages: messages, tools: tools });B@cf/meta/llama-3.3-70b-instruct-fp8-fast instead of llama-4-scout the tool call works, but then the models responds incorrectly. Has there been a change in how tools are call between llama-3 and llama-4? Should I use Functions instead.B
BAiError: 3043: Internal server error on some calls -- has anyone successfully debugged those?Bresponse_format and as result I get response as JSON that can be easily parsed and then used to call my functions. It basically provides the same result, with the exception of allowing the model to select the tool, but one could easily set a prop in the JSON for function selection. It still sucks that tool calling appears to be broken.MBM
D
AMMMMM
A
@cf/bytedance/stable-diffusion-xl-lightning@cf/black-forest-labs/flux-1-schnellexpected destination type of 'string' or '[]byte' for responses with content-type 'image/png' that is not 'application/json'
AC
GAiError: 3040: Capacity temporarily exceeded, please try again.
JD1 TYPE ERROR: Type 'object' not supported for value '[object Object]'
B
BA"tool_calls":[]"tool_calls":[]response"type": "function"
A@cf/black-forest-labs/flux-1-schnell
JB@cf/qwen/qwen2.5-coder-32b-instructconst API_BASE_URL = "https://api.cloudflare.com/client/v4/accounts/{myID}/ai/run/"
const API_AUTH_TOKEN = "{myTOKEN}" //process.env.API_AUTH_TOKEN;
const model = "@cf/meta/llama-2-7b-chat-int8"
const headers = {
'Authorization':`Bearer ${API_AUTH_TOKEN}`,
//'Content-type':'application/type',
"Access-Control-Allow-Origin": "*",
"Access-Control-Allow-Methods": "GET,HEAD,POST,OPTIONS",
"Access-Control-Max-Age": "86400"
}
if (!API_BASE_URL || !API_AUTH_TOKEN) {
throw new Error('API credential is wrong or not configured from Github Action')
}
const inputs = [
{'role':'system', 'content':systemPrompt},
{'role':'user', 'content':userPrompt},
]
const payload = {
message: inputs
}
try {
console.log("Requesting to LLM...")
const response = await fetch(`${API_BASE_URL}${model}`, {
method: 'POST',
headers:headers,
body: JSON.stringify(payload),
mode: 'no-cors'
}
);
if (!response.ok) {
throw new Error (`Error request from LLM: ${response.status}`)
}
console.log("Requesting completed. Waiting for output...")
const output = await response.json(); // output
console.log(output)
}
catch (error) {
console.log("API Error", error);
throw error;
}resp, err := client.AI.Run(ctx, model, ai.AIRunParams{
AccountID: cloudflare.F(cfAccountID),
Body: ai.AIRunParamsBodyTextToImage{
Prompt: cloudflare.F(prompt),
},
})
if err != nil {
return err
}{
exception:
{
stack:
"AiError: 3040: Capacity temporarily exceeded, please try again. at Ai._parseError (cloudflare-internal:ai-api:102:24) at async Ai.run (cloudflare-internal:ai-api:82:19) at async Object.fetch (index.js:21:22)",
name:
"Error",
message:
"3040: Capacity temporarily exceeded, please try again.",
timestamp:
1747050909290,
},
message:
"3040: Capacity temporarily exceeded, please try again.",
$workers:
{
truncated:
false,
event:
{
request:
{
url:
"https://classify-ai.workers.dev/",
method:
"POST",
path:
"/"
}
},
outcome:
"exception",
scriptName:
"classify-ai",
eventType:
"fetch",
executionModel:
"stateless",
scriptVersion:
{
id:
"1678a794-81e9-48fd-8d8f-43f9d95d4235"
},
requestId:
"93e9b9b6a8b802ad"
},
$metadata:
{
id:
"01JV25JKKAQGM3BZG6KQDG9AA7",
requestId:
"93e9b9b6a8b802ad",
trigger:
"POST /",
service:
"classify-ai",
level:
"error",
error:
"3040: Capacity temporarily exceeded, please try again.",
message:
"3040: Capacity temporarily exceeded, please try again.",
account:
"f1c3db27dc01771c8c27ec175b404598",
type:
"cf-worker",
fingerprint:
"4bc40a10bc8b1073f4883173eeb61c8a",
origin:
"fetch",
messageTemplate:
"<NUM>: Capacity temporarily exceeded, please try again.",
errorTemplate:
"<NUM>: Capacity temporarily exceeded, please try again.",
}
}{{{{ ...the expected response... } } ] } } } \n' +
'\n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' \n' +
' ', import { runWithTools } from '@cloudflare/ai-utils';
const model = '@cf/meta/llama-3.3-70b-instruct-fp8-fast';
const response = await runWithTools(
env.AI,
model,
{
messages: chatmessages,
tools: function_tools,
max_tokens: 8192,
temperature: 0.6,
},
{ strictValidation: true, maxRecursiveToolRuns: 1, verbose: true, streamFinalResponse: true }
);ai-utilsAI.runError: 8001: Invalid input@cf/meta/llama-4-scout-17b-16e-instruct[
{
"name":"applyFilter",
"description":"Function that applies the filter...",
"parameters":{
"type":"object",
"properties":{
"query":{
"type":"object",
"description":"The query object..."
},
"filterDesc":{
"type":"string",
"description":"Description, for the user, of the filter..."
}
},
"required":["query","filterDesc"]
}
}
]await AI.run( model, { messages: messages, tools: tools });@cf/meta/llama-3.3-70b-instruct-fp8-fastllama-4-scoutFunctionsError: 5006: Error: oneOf at '/' not met, 0 matches: required properties at '/' are 'prompt', Type mismatch of '/messages/0/content', 'array' not in 'string', Type mismatch of '/messages/1/content', 'array' not in 'string', required properties at '/functions/0' are 'name,code'AiError: 3043: Internal server errorresponse_format