-
Notifications
You must be signed in to change notification settings - Fork 91
feat: add Vercel AI Gateway provider #779
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
mojoxr
wants to merge
3
commits into
Merit-Systems:master
Choose a base branch
from
mojoxr:fix/vercel-ai-gateway-provider
base: master
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
259 changes: 259 additions & 0 deletions
259
packages/app/server/src/providers/VercelAIGatewayProvider.ts
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,259 @@ | ||
| import { LlmTransactionMetadata, Transaction } from '../types'; | ||
| import { getCostPerToken } from '../services/AccountingService'; | ||
| import { BaseProvider } from './BaseProvider'; | ||
| import { ProviderType } from './ProviderType'; | ||
| import { parseSSEGPTFormat } from './GPTProvider'; | ||
| import logger from '../logger'; | ||
| import { env } from '../env'; | ||
|
|
||
| interface AIGatewayUsage { | ||
| inputTokens?: number; | ||
| outputTokens?: number; | ||
| totalTokens?: number; | ||
| } | ||
|
|
||
| interface OpenAICompatibleUsage { | ||
| prompt_tokens?: number; | ||
| completion_tokens?: number; | ||
| total_tokens?: number; | ||
| } | ||
|
|
||
| interface AIGatewayResponseBody { | ||
| id?: string; | ||
| response?: { | ||
| id?: string; | ||
| }; | ||
| usage?: AIGatewayUsage | OpenAICompatibleUsage; | ||
| } | ||
|
|
||
| interface AIGatewayStreamPart { | ||
| type?: string; | ||
| id?: string; | ||
| response?: { | ||
| id?: string; | ||
| }; | ||
| usage?: AIGatewayUsage; | ||
| } | ||
|
|
||
| const ECHO_VERCEL_MODEL_PREFIX = 'vercel/'; | ||
|
|
||
| function toVercelModelId(model: string): string { | ||
| return model.startsWith(ECHO_VERCEL_MODEL_PREFIX) | ||
| ? model.slice(ECHO_VERCEL_MODEL_PREFIX.length) | ||
| : model; | ||
| } | ||
|
|
||
| function isAIGatewayUsage( | ||
| usage: AIGatewayUsage | OpenAICompatibleUsage | undefined | ||
| ): usage is AIGatewayUsage { | ||
| return ( | ||
| usage !== undefined && | ||
| ('inputTokens' in usage || | ||
| 'outputTokens' in usage || | ||
| 'totalTokens' in usage) | ||
| ); | ||
| } | ||
|
|
||
| function parseSSEJsonObjects(data: string): unknown[] { | ||
| const chunks: unknown[] = []; | ||
|
|
||
| for (const event of data.split('\n\n')) { | ||
| const dataLines = event | ||
| .split('\n') | ||
| .filter(line => line.startsWith('data: ')) | ||
| .map(line => line.slice(6)); | ||
|
|
||
| if (dataLines.length === 0) { | ||
| continue; | ||
| } | ||
|
|
||
| const payload = dataLines.join('\n').trim(); | ||
| if (!payload || payload === '[DONE]') { | ||
| continue; | ||
| } | ||
|
|
||
| try { | ||
| chunks.push(JSON.parse(payload)); | ||
| } catch (error) { | ||
| logger.error(`Error parsing Vercel AI Gateway SSE chunk: ${error}`); | ||
| } | ||
| } | ||
|
|
||
| return chunks; | ||
| } | ||
|
|
||
| export class VercelAIGatewayProvider extends BaseProvider { | ||
| private readonly VERCEL_AI_GATEWAY_OPENAI_BASE_URL = | ||
| 'https://ai-gateway.vercel.sh/v1'; | ||
| private readonly VERCEL_AI_GATEWAY_AI_SDK_BASE_URL = | ||
| 'https://ai-gateway.vercel.sh/v1/ai'; | ||
|
|
||
| getType(): ProviderType { | ||
| return ProviderType.VERCEL_AI_GATEWAY; | ||
| } | ||
|
|
||
| getBaseUrl(reqPath?: string): string { | ||
| if ( | ||
| reqPath?.includes('/language-model') || | ||
| reqPath?.includes('/embedding-model') || | ||
| reqPath?.endsWith('/config') | ||
| ) { | ||
| return this.VERCEL_AI_GATEWAY_AI_SDK_BASE_URL; | ||
| } | ||
|
|
||
| return this.VERCEL_AI_GATEWAY_OPENAI_BASE_URL; | ||
| } | ||
|
|
||
| override formatUpstreamUrl(req: { path: string; url: string }): string { | ||
| const query = req.url.includes('?') | ||
| ? req.url.substring(req.url.indexOf('?')) | ||
| : ''; | ||
|
|
||
| if (req.path.endsWith('/language-model')) { | ||
| return `${this.VERCEL_AI_GATEWAY_AI_SDK_BASE_URL}/language-model${query}`; | ||
| } | ||
| if (req.path.endsWith('/embedding-model')) { | ||
| return `${this.VERCEL_AI_GATEWAY_AI_SDK_BASE_URL}/embedding-model${query}`; | ||
| } | ||
| if (req.path.endsWith('/config')) { | ||
| return `${this.VERCEL_AI_GATEWAY_AI_SDK_BASE_URL}/config${query}`; | ||
| } | ||
|
|
||
| return `${this.getBaseUrl(req.path)}${req.path}${query}`; | ||
| } | ||
|
|
||
| getApiKey(): string | undefined { | ||
| return env.AI_GATEWAY_API_KEY; | ||
| } | ||
|
|
||
| override async formatAuthHeaders( | ||
| headers: Record<string, string> | ||
| ): Promise<Record<string, string>> { | ||
| const formattedHeaders = await super.formatAuthHeaders(headers); | ||
|
|
||
| delete formattedHeaders['AI-Language-Model-Id']; | ||
| delete formattedHeaders['ai-language-model-id']; | ||
| formattedHeaders['ai-language-model-id'] = toVercelModelId(this.getModel()); | ||
|
|
||
| return formattedHeaders; | ||
| } | ||
|
|
||
| override ensureStreamUsage( | ||
| reqBody: Record<string, unknown>, | ||
| reqPath: string | ||
| ): Record<string, unknown> { | ||
| if (reqPath.includes('/language-model')) { | ||
| return reqBody; | ||
| } | ||
|
|
||
| return super.ensureStreamUsage(reqBody, reqPath); | ||
| } | ||
|
|
||
| override transformRequestBody( | ||
| reqBody: Record<string, unknown> | ||
| ): Record<string, unknown> { | ||
| if (typeof reqBody.model === 'string') { | ||
| return { | ||
| ...reqBody, | ||
| model: toVercelModelId(reqBody.model), | ||
| }; | ||
| } | ||
|
|
||
| return reqBody; | ||
| } | ||
|
|
||
| override supportsStream(): boolean { | ||
| return true; | ||
| } | ||
|
|
||
| private getUsageFromAIResponse(usage: AIGatewayUsage | undefined): { | ||
| promptTokens: number; | ||
| completionTokens: number; | ||
| totalTokens: number; | ||
| } { | ||
| const promptTokens = usage?.inputTokens ?? 0; | ||
| const completionTokens = usage?.outputTokens ?? 0; | ||
| const totalTokens = usage?.totalTokens ?? promptTokens + completionTokens; | ||
|
|
||
| return { promptTokens, completionTokens, totalTokens }; | ||
| } | ||
|
|
||
| async handleBody(data: string): Promise<Transaction> { | ||
| try { | ||
| let prompt_tokens = 0; | ||
| let completion_tokens = 0; | ||
| let total_tokens = 0; | ||
| let providerId = 'null'; | ||
|
|
||
| if (this.getIsStream()) { | ||
| const chunks = parseSSEJsonObjects(data); | ||
|
|
||
| for (const chunk of chunks) { | ||
| const streamPart = chunk as AIGatewayStreamPart; | ||
|
|
||
| if (streamPart.type === 'finish' && streamPart.usage) { | ||
| const usage = this.getUsageFromAIResponse(streamPart.usage); | ||
| prompt_tokens += usage.promptTokens; | ||
| completion_tokens += usage.completionTokens; | ||
| total_tokens += usage.totalTokens; | ||
| } | ||
|
|
||
| providerId = streamPart.response?.id ?? streamPart.id ?? providerId; | ||
| } | ||
|
|
||
| if (total_tokens === 0) { | ||
| for (const chunk of parseSSEGPTFormat(data)) { | ||
| if (chunk.usage !== null) { | ||
| prompt_tokens += chunk.usage.prompt_tokens; | ||
| completion_tokens += chunk.usage.completion_tokens; | ||
| total_tokens += chunk.usage.total_tokens; | ||
| } | ||
| providerId = chunk.id || providerId; | ||
| } | ||
| } | ||
| } else { | ||
| const parsed = JSON.parse(data) as AIGatewayResponseBody; | ||
|
|
||
| if (isAIGatewayUsage(parsed.usage)) { | ||
| const usage = this.getUsageFromAIResponse(parsed.usage); | ||
| prompt_tokens += usage.promptTokens; | ||
| completion_tokens += usage.completionTokens; | ||
| total_tokens += usage.totalTokens; | ||
| providerId = parsed.response?.id ?? parsed.id ?? 'null'; | ||
| } else if (parsed.usage) { | ||
| prompt_tokens += parsed.usage.prompt_tokens ?? 0; | ||
| completion_tokens += parsed.usage.completion_tokens ?? 0; | ||
| total_tokens += | ||
| parsed.usage.total_tokens ?? prompt_tokens + completion_tokens; | ||
| providerId = parsed.id || 'null'; | ||
| } else { | ||
| providerId = parsed.response?.id ?? parsed.id ?? 'null'; | ||
| } | ||
| } | ||
|
|
||
| const cost = getCostPerToken( | ||
| this.getModel(), | ||
| prompt_tokens, | ||
| completion_tokens | ||
| ); | ||
|
|
||
| const metadata: LlmTransactionMetadata = { | ||
| providerId, | ||
| provider: this.getType(), | ||
| model: this.getModel(), | ||
| inputTokens: prompt_tokens, | ||
| outputTokens: completion_tokens, | ||
| totalTokens: total_tokens, | ||
| }; | ||
|
|
||
| return { | ||
| rawTransactionCost: cost, | ||
| metadata, | ||
| status: 'success', | ||
| }; | ||
| } catch (error) { | ||
| logger.error(`Error processing data: ${error}`); | ||
| throw error; | ||
| } | ||
| } | ||
| } | ||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.