* WIP agentic tool call streaming - OpenAI - Anthropic - Azure OpenAI * WIP rest of providers EXCLUDES Bedrock and GenericOpenAI * patch untooled complete/streaming to use chatCallback provider from provider class and not assume OpenAI client struct example: Ollama * modify ollama to function with its own overrides normalize completion/stream outputs across providers/untooled * dev build * fix message sanization for anthropic agent streaming * wip fix anthropic agentic streaming sanitization * patch gemini, webgenui, generic aibitat providers + disable providers unable to test * refactor anthropic aibitat provider for empty message and tool call formatting * Add frontend missing prop check update Azure for streaming support update Gemini to streamting support on gemini-* models generic OpenAI disable streaming verify localAI support verify NVIDIA Nim support * DPAIS, remove temp from call, support streaming' * remove 0 temp to remove possibility of bad temp error/500s/400s * Patch condition where model is non-streamable and no tools are present or called resulting in the provider `handleFunctionCallChat` being called - which returns a string. This would then fail in Untooled.complete since response would be a string and not the expected `response.choices?.[0]?.message` Modified this line to handle both conditions for stream/non-streaming and tool presence or lack thereof * Allow generic Openai to be streamable since using untooled it should work fine honor disabled streaming for provider where that concern may apply for regular chats * rename function and more gemini-specific function to gemini provider * add comments for readability .complete on azure should be non-streaming as this is the sync response * migrate CometAPI, but disable as we cannot test --------- Co-authored-by: shatfield4 <seanhatfield5@gmail.com>
114 lines
3.0 KiB
JavaScript
114 lines
3.0 KiB
JavaScript
const { AzureOpenAI } = require("openai");
|
|
const Provider = require("./ai-provider.js");
|
|
const { RetryError } = require("../error.js");
|
|
|
|
/**
|
|
* The agent provider for the Azure OpenAI API.
|
|
*/
|
|
class AzureOpenAiProvider extends Provider {
|
|
model;
|
|
|
|
constructor(config = { model: null }) {
|
|
const client = new AzureOpenAI({
|
|
apiKey: process.env.AZURE_OPENAI_KEY,
|
|
endpoint: process.env.AZURE_OPENAI_ENDPOINT,
|
|
apiVersion: "2024-12-01-preview",
|
|
});
|
|
super(client);
|
|
this.model = config.model ?? process.env.OPEN_MODEL_PREF;
|
|
this.verbose = true;
|
|
}
|
|
|
|
get supportsAgentStreaming() {
|
|
return true;
|
|
}
|
|
|
|
/**
|
|
* Create a completion based on the received messages.
|
|
*
|
|
* @param messages A list of messages to send to the OpenAI API.
|
|
* @param functions
|
|
* @returns The completion.
|
|
*/
|
|
async complete(messages, functions = []) {
|
|
try {
|
|
const response = await this.client.chat.completions.create({
|
|
model: this.model,
|
|
stream: false,
|
|
messages,
|
|
...(Array.isArray(functions) && functions?.length > 0
|
|
? { functions }
|
|
: {}),
|
|
});
|
|
|
|
// Right now, we only support one completion,
|
|
// so we just take the first one in the list
|
|
const completion = response.choices[0].message;
|
|
const cost = this.getCost(response.usage);
|
|
// treat function calls
|
|
if (completion.function_call) {
|
|
let functionArgs = {};
|
|
try {
|
|
functionArgs = JSON.parse(completion.function_call.arguments);
|
|
} catch (error) {
|
|
// call the complete function again in case it gets a json error
|
|
return this.complete(
|
|
[
|
|
...messages,
|
|
{
|
|
role: "function",
|
|
name: completion.function_call.name,
|
|
function_call: completion.function_call,
|
|
content: error?.message,
|
|
},
|
|
],
|
|
functions
|
|
);
|
|
}
|
|
|
|
// console.log(completion, { functionArgs })
|
|
return {
|
|
textResponse: null,
|
|
functionCall: {
|
|
name: completion.function_call.name,
|
|
arguments: functionArgs,
|
|
},
|
|
cost,
|
|
};
|
|
}
|
|
|
|
return {
|
|
textResponse: completion.content,
|
|
cost,
|
|
};
|
|
} catch (error) {
|
|
// If invalid Auth error we need to abort because no amount of waiting
|
|
// will make auth better.
|
|
if (error instanceof AzureOpenAI.AuthenticationError) throw error;
|
|
|
|
if (
|
|
error instanceof AzureOpenAI.RateLimitError ||
|
|
error instanceof AzureOpenAI.InternalServerError ||
|
|
error instanceof AzureOpenAI.APIError // Also will catch AuthenticationError!!!
|
|
) {
|
|
throw new RetryError(error.message);
|
|
}
|
|
|
|
throw error;
|
|
}
|
|
}
|
|
|
|
/**
|
|
* Get the cost of the completion.
|
|
* Stubbed since Azure OpenAI has no public cost basis.
|
|
*
|
|
* @param _usage The completion to get the cost for.
|
|
* @returns The cost of the completion.
|
|
*/
|
|
getCost(_usage) {
|
|
return 0;
|
|
}
|
|
}
|
|
|
|
module.exports = AzureOpenAiProvider;
|