diff --git a/.vscode/settings.json b/.vscode/settings.json index 307bbe6c719..e6b76c9e9de 100644 --- a/.vscode/settings.json +++ b/.vscode/settings.json @@ -41,6 +41,7 @@ "opendocument", "openrouter", "pagerender", + "ppio", "Qdrant", "royalblue", "SearchApi", diff --git a/README.md b/README.md index f5782936ce4..ae82df2cfff 100644 --- a/README.md +++ b/README.md @@ -99,6 +99,7 @@ AnythingLLM divides your documents into objects called `workspaces`. A Workspace - [Apipie](https://apipie.ai/) - [xAI](https://x.ai/) - [Novita AI (chat models)](https://novita.ai/model-api/product/llm-api?utm_source=github_anything-llm&utm_medium=github_readme&utm_campaign=link) +- [PPIO](https://ppinfra.com?utm_source=github_anything-llm) **Embedder models:** diff --git a/docker/.env.example b/docker/.env.example index d3cc68e1240..40acac84b68 100644 --- a/docker/.env.example +++ b/docker/.env.example @@ -126,6 +126,10 @@ GID='1000' # DEEPSEEK_API_KEY='your-deepseek-api-key-here' # DEEPSEEK_MODEL_PREF='deepseek-chat' +# LLM_PROVIDER='ppio' +# PPIO_API_KEY='your-ppio-api-key-here' +# PPIO_MODEL_PREF=deepseek/deepseek-v3/community + ########################################### ######## Embedding API SElECTION ########## ########################################### diff --git a/frontend/src/components/LLMSelection/PPIOLLMOptions/index.jsx b/frontend/src/components/LLMSelection/PPIOLLMOptions/index.jsx new file mode 100644 index 00000000000..99b617f1707 --- /dev/null +++ b/frontend/src/components/LLMSelection/PPIOLLMOptions/index.jsx @@ -0,0 +1,100 @@ +import System from "@/models/system"; +import { useState, useEffect } from "react"; + +export default function PPIOLLMOptions({ settings }) { + return ( +
+
+
+ + +
+ {!settings?.credentialsOnly && ( + + )} +
+
+ ); +} + +function PPIOModelSelection({ settings }) { + const [groupedModels, setGroupedModels] = useState({}); + const [loading, setLoading] = useState(true); + + useEffect(() => { + async function fetchModels() { + setLoading(true); + const { models } = await System.customModels("ppio"); + if (models?.length > 0) { + const modelsByOrganization = models.reduce((acc, model) => { + acc[model.organization] = acc[model.organization] || []; + acc[model.organization].push(model); + return acc; + }, {}); + setGroupedModels(modelsByOrganization); + } + setLoading(false); + } + fetchModels(); + }, []); + + if (loading || Object.keys(groupedModels).length === 0) { + return ( +
+ + +
+ ); + } + + return ( +
+ + +
+ ); +} diff --git a/frontend/src/hooks/useGetProvidersModels.js b/frontend/src/hooks/useGetProvidersModels.js index 8c1b998cec5..2019a19dfca 100644 --- a/frontend/src/hooks/useGetProvidersModels.js +++ b/frontend/src/hooks/useGetProvidersModels.js @@ -79,6 +79,7 @@ const groupedProviders = [ "openai", "novita", "openrouter", + "ppio", ]; export default function useGetProviderModels(provider = null) { const [defaultModels, setDefaultModels] = useState([]); diff --git a/frontend/src/media/llmprovider/ppio.png b/frontend/src/media/llmprovider/ppio.png new file mode 100644 index 00000000000..37b131a5440 Binary files /dev/null and b/frontend/src/media/llmprovider/ppio.png differ diff --git a/frontend/src/pages/GeneralSettings/LLMPreference/index.jsx b/frontend/src/pages/GeneralSettings/LLMPreference/index.jsx index 96ec360fd77..8f137805533 100644 --- a/frontend/src/pages/GeneralSettings/LLMPreference/index.jsx +++ b/frontend/src/pages/GeneralSettings/LLMPreference/index.jsx @@ -30,6 +30,7 @@ import DeepSeekLogo from "@/media/llmprovider/deepseek.png"; import APIPieLogo from "@/media/llmprovider/apipie.png"; import XAILogo from "@/media/llmprovider/xai.png"; import NvidiaNimLogo from "@/media/llmprovider/nvidia-nim.png"; +import PPIOLogo from "@/media/llmprovider/ppio.png"; import PreLoader from "@/components/Preloader"; import OpenAiOptions from "@/components/LLMSelection/OpenAiOptions"; @@ -57,6 +58,7 @@ import DeepSeekOptions from "@/components/LLMSelection/DeepSeekOptions"; import ApiPieLLMOptions from "@/components/LLMSelection/ApiPieOptions"; import XAILLMOptions from "@/components/LLMSelection/XAiLLMOptions"; import NvidiaNimOptions from "@/components/LLMSelection/NvidiaNimOptions"; +import PPIOLLMOptions from "@/components/LLMSelection/PPIOLLMOptions"; import LLMItem from "@/components/LLMSelection/LLMItem"; import { CaretUpDown, MagnifyingGlass, X } from "@phosphor-icons/react"; @@ -246,6 +248,15 @@ export const AVAILABLE_LLM_PROVIDERS = [ description: "Run DeepSeek's powerful LLMs.", requiredConfig: ["DeepSeekApiKey"], }, + { + name: "PPIO", + value: "ppio", + logo: PPIOLogo, + options: (settings) => , + description: + "Run stable and cost-efficient open-source LLM APIs, such as DeepSeek, Llama, Qwen etc.", + requiredConfig: ["PPIOApiKey"], + }, { name: "AWS Bedrock", value: "bedrock", diff --git a/frontend/src/pages/OnboardingFlow/Steps/DataHandling/index.jsx b/frontend/src/pages/OnboardingFlow/Steps/DataHandling/index.jsx index cab4d667788..76372e83956 100644 --- a/frontend/src/pages/OnboardingFlow/Steps/DataHandling/index.jsx +++ b/frontend/src/pages/OnboardingFlow/Steps/DataHandling/index.jsx @@ -25,7 +25,6 @@ import AWSBedrockLogo from "@/media/llmprovider/bedrock.png"; import DeepSeekLogo from "@/media/llmprovider/deepseek.png"; import APIPieLogo from "@/media/llmprovider/apipie.png"; import XAILogo from "@/media/llmprovider/xai.png"; - import CohereLogo from "@/media/llmprovider/cohere.png"; import ZillizLogo from "@/media/vectordbs/zilliz.png"; import AstraDBLogo from "@/media/vectordbs/astraDB.png"; @@ -36,6 +35,7 @@ import WeaviateLogo from "@/media/vectordbs/weaviate.png"; import QDrantLogo from "@/media/vectordbs/qdrant.png"; import MilvusLogo from "@/media/vectordbs/milvus.png"; import VoyageAiLogo from "@/media/embeddingprovider/voyageai.png"; +import PPIOLogo from "@/media/llmprovider/ppio.png"; import React, { useState, useEffect } from "react"; import paths from "@/utils/paths"; @@ -226,6 +226,14 @@ export const LLM_SELECTION_PRIVACY = { ], logo: XAILogo, }, + ppio: { + name: "PPIO", + description: [ + "Your chats will not be used for training", + "Your prompts and document text used in response creation are visible to PPIO", + ], + logo: PPIOLogo, + }, }; export const VECTOR_DB_PRIVACY = { diff --git a/frontend/src/pages/OnboardingFlow/Steps/LLMPreference/index.jsx b/frontend/src/pages/OnboardingFlow/Steps/LLMPreference/index.jsx index 9ea733b95e5..16f15675723 100644 --- a/frontend/src/pages/OnboardingFlow/Steps/LLMPreference/index.jsx +++ b/frontend/src/pages/OnboardingFlow/Steps/LLMPreference/index.jsx @@ -25,6 +25,8 @@ import NovitaLogo from "@/media/llmprovider/novita.png"; import XAILogo from "@/media/llmprovider/xai.png"; import NvidiaNimLogo from "@/media/llmprovider/nvidia-nim.png"; import CohereLogo from "@/media/llmprovider/cohere.png"; +import PPIOLogo from "@/media/llmprovider/ppio.png"; + import OpenAiOptions from "@/components/LLMSelection/OpenAiOptions"; import GenericOpenAiOptions from "@/components/LLMSelection/GenericOpenAiOptions"; import AzureAiOptions from "@/components/LLMSelection/AzureAiOptions"; @@ -50,6 +52,7 @@ import ApiPieLLMOptions from "@/components/LLMSelection/ApiPieOptions"; import NovitaLLMOptions from "@/components/LLMSelection/NovitaLLMOptions"; import XAILLMOptions from "@/components/LLMSelection/XAiLLMOptions"; import NvidiaNimOptions from "@/components/LLMSelection/NvidiaNimOptions"; +import PPIOLLMOptions from "@/components/LLMSelection/PPIOLLMOptions"; import LLMItem from "@/components/LLMSelection/LLMItem"; import System from "@/models/system"; @@ -213,6 +216,14 @@ const LLMS = [ options: (settings) => , description: "Run DeepSeek's powerful LLMs.", }, + { + name: "PPIO", + value: "ppio", + logo: PPIOLogo, + options: (settings) => , + description: + "Run stable and cost-efficient open-source LLM APIs, such as DeepSeek, Llama, Qwen etc.", + }, { name: "APIpie", value: "apipie", diff --git a/frontend/src/pages/WorkspaceSettings/AgentConfig/AgentLLMSelection/index.jsx b/frontend/src/pages/WorkspaceSettings/AgentConfig/AgentLLMSelection/index.jsx index ca936a8318e..10d986830ab 100644 --- a/frontend/src/pages/WorkspaceSettings/AgentConfig/AgentLLMSelection/index.jsx +++ b/frontend/src/pages/WorkspaceSettings/AgentConfig/AgentLLMSelection/index.jsx @@ -25,6 +25,7 @@ const ENABLED_PROVIDERS = [ "bedrock", "fireworksai", "deepseek", + "ppio", "litellm", "apipie", "xai", diff --git a/locales/README.fa-IR.md b/locales/README.fa-IR.md index dcb71f9d1d5..33305af968e 100644 --- a/locales/README.fa-IR.md +++ b/locales/README.fa-IR.md @@ -103,6 +103,7 @@ AnythingLLM اسناد شما را به اشیایی به نام `workspaces` ت - [Apipie](https://apipie.ai/) - [xAI](https://x.ai/) - [Novita AI (chat models)](https://novita.ai/model-api/product/llm-api?utm_source=github_anything-llm&utm_medium=github_readme&utm_campaign=link) +- [PPIO](https://ppinfra.com?utm_source=github_anything-llm)
diff --git a/locales/README.ja-JP.md b/locales/README.ja-JP.md index 9ba566eb911..5c7ca1e8787 100644 --- a/locales/README.ja-JP.md +++ b/locales/README.ja-JP.md @@ -90,6 +90,7 @@ AnythingLLMのいくつかのクールな機能 - [Groq](https://groq.com/) - [Cohere](https://cohere.com/) - [KoboldCPP](https://github.com/LostRuins/koboldcpp) +- [PPIO](https://ppinfra.com?utm_source=github_anything-llm) **埋め込みモデル：** diff --git a/locales/README.tr-TR.md b/locales/README.tr-TR.md index 026bc7d4211..4bd9fe337d2 100644 --- a/locales/README.tr-TR.md +++ b/locales/README.tr-TR.md @@ -100,6 +100,7 @@ AnythingLLM, belgelerinizi **"çalışma alanları" (workspaces)** adı verilen - [Apipie](https://apipie.ai/) - [xAI](https://x.ai/) - [Novita AI (chat models)](https://novita.ai/model-api/product/llm-api?utm_source=github_anything-llm&utm_medium=github_readme&utm_campaign=link) +- [PPIO](https://ppinfra.com?utm_source=github_anything-llm) **Embedder modelleri:** diff --git a/locales/README.zh-CN.md b/locales/README.zh-CN.md index 095116fc020..f6ecdc086d5 100644 --- a/locales/README.zh-CN.md +++ b/locales/README.zh-CN.md @@ -86,6 +86,7 @@ AnythingLLM的一些酷炫特性 - [Groq](https://groq.com/) - [Cohere](https://cohere.com/) - [KoboldCPP](https://github.com/LostRuins/koboldcpp) +- [PPIO (聊天模型)](https://ppinfra.com?utm_source=github_anything-llm) **支持的嵌入模型：** diff --git a/server/.env.example b/server/.env.example index 1975ada8bba..f5fa69a34f4 100644 --- a/server/.env.example +++ b/server/.env.example @@ -116,6 +116,10 @@ SIG_SALT='salt' # Please generate random string at least 32 chars long. # NVIDIA_NIM_LLM_BASE_PATH='http://127.0.0.1:8000' # NVIDIA_NIM_LLM_MODEL_PREF='meta/llama-3.2-3b-instruct' +# LLM_PROVIDER='ppio' +# PPIO_API_KEY='your-ppio-api-key-here' +# PPIO_MODEL_PREF='deepseek/deepseek-v3/community' + ########################################### ######## Embedding API SElECTION ########## ########################################### diff --git a/server/models/systemSettings.js b/server/models/systemSettings.js index 58087f7b78a..bd811af1ca3 100644 --- a/server/models/systemSettings.js +++ b/server/models/systemSettings.js @@ -560,6 +560,10 @@ const SystemSettings = { NvidiaNimLLMBasePath: process.env.NVIDIA_NIM_LLM_BASE_PATH, NvidiaNimLLMModelPref: process.env.NVIDIA_NIM_LLM_MODEL_PREF, NvidiaNimLLMTokenLimit: process.env.NVIDIA_NIM_LLM_MODEL_TOKEN_LIMIT, + + // PPIO API keys + PPIOApiKey: !!process.env.PPIO_API_KEY, + PPIOModelPref: process.env.PPIO_MODEL_PREF, }; }, diff --git a/server/storage/models/.gitignore b/server/storage/models/.gitignore index 12436b21f38..f5c78ac877c 100644 --- a/server/storage/models/.gitignore +++ b/server/storage/models/.gitignore @@ -8,4 +8,4 @@ mixedbread-ai* gemini togetherAi tesseract -ppio \ No newline at end of file +ppio diff --git a/server/utils/AiProviders/ppio/index.js b/server/utils/AiProviders/ppio/index.js new file mode 100644 index 00000000000..677cd4cd04f --- /dev/null +++ b/server/utils/AiProviders/ppio/index.js @@ -0,0 +1,266 @@ +const { NativeEmbedder } = require("../../EmbeddingEngines/native"); +const { + handleDefaultStreamResponseV2, +} = require("../../helpers/chat/responses"); +const fs = require("fs"); +const path = require("path"); +const { safeJsonParse } = require("../../http"); +const { + LLMPerformanceMonitor, +} = require("../../helpers/chat/LLMPerformanceMonitor"); +const cacheFolder = path.resolve( + process.env.STORAGE_DIR + ? path.resolve(process.env.STORAGE_DIR, "models", "ppio") + : path.resolve(__dirname, `../../../storage/models/ppio`) +); + +class PPIOLLM { + constructor(embedder = null, modelPreference = null) { + if (!process.env.PPIO_API_KEY) throw new Error("No PPIO API key was set."); + + const { OpenAI: OpenAIApi } = require("openai"); + this.basePath = "https://api.ppinfra.com/v3/openai/"; + this.openai = new OpenAIApi({ + baseURL: this.basePath, + apiKey: process.env.PPIO_API_KEY ?? null, + defaultHeaders: { + "HTTP-Referer": "https://anythingllm.com", + "X-API-Source": "anythingllm", + }, + }); + this.model = + modelPreference || + process.env.PPIO_MODEL_PREF || + "qwen/qwen2.5-32b-instruct"; + this.limits = { + history: this.promptWindowLimit() * 0.15, + system: this.promptWindowLimit() * 0.15, + user: this.promptWindowLimit() * 0.7, + }; + + this.embedder = embedder ?? new NativeEmbedder(); + this.defaultTemp = 0.7; + + if (!fs.existsSync(cacheFolder)) + fs.mkdirSync(cacheFolder, { recursive: true }); + this.cacheModelPath = path.resolve(cacheFolder, "models.json"); + this.cacheAtPath = path.resolve(cacheFolder, ".cached_at"); + + this.log(`Loaded with model: ${this.model}`); + } + + log(text, ...args) { + console.log(`\x1b[36m[${this.constructor.name}]\x1b[0m ${text}`, ...args); + } + + async #syncModels() { + if (fs.existsSync(this.cacheModelPath) && !this.#cacheIsStale()) + return false; + + this.log("Model cache is not present or stale. Fetching from PPIO API."); + await fetchPPIOModels(); + return; + } + + #cacheIsStale() { + const MAX_STALE = 6.048e8; // 1 Week in MS + if (!fs.existsSync(this.cacheAtPath)) return true; + const now = Number(new Date()); + const timestampMs = Number(fs.readFileSync(this.cacheAtPath)); + return now - timestampMs > MAX_STALE; + } + + #appendContext(contextTexts = []) { + if (!contextTexts || !contextTexts.length) return ""; + return ( + "\nContext:\n" + + contextTexts + .map((text, i) => { + return `[CONTEXT ${i}]:\n${text}\n[END CONTEXT ${i}]\n\n`; + }) + .join("") + ); + } + + models() { + if (!fs.existsSync(this.cacheModelPath)) return {}; + return safeJsonParse( + fs.readFileSync(this.cacheModelPath, { encoding: "utf-8" }), + {} + ); + } + + streamingEnabled() { + return "streamGetChatCompletion" in this; + } + + promptWindowLimit() { + const model = this.models()[this.model]; + if (!model) return 4096; // Default to 4096 if we cannot find the model + return model?.maxLength || 4096; + } + + async isValidChatCompletionModel(model = "") { + await this.#syncModels(); + const availableModels = this.models(); + return Object.prototype.hasOwnProperty.call(availableModels, model); + } + + /** + * Generates appropriate content array for a message + attachments. + * @param {{userPrompt:string, attachments: import("../../helpers").Attachment[]}} + * @returns {string|object[]} + */ + #generateContent({ userPrompt, attachments = [] }) { + if (!attachments.length) { + return userPrompt; + } + + const content = [{ type: "text", text: userPrompt }]; + for (let attachment of attachments) { + content.push({ + type: "image_url", + image_url: { + url: attachment.contentString, + detail: "auto", + }, + }); + } + return content.flat(); + } + + constructPrompt({ + systemPrompt = "", + contextTexts = [], + chatHistory = [], + userPrompt = "", + // attachments = [], - not supported + }) { + const prompt = { + role: "system", + content: `${systemPrompt}${this.#appendContext(contextTexts)}`, + }; + return [prompt, ...chatHistory, { role: "user", content: userPrompt }]; + } + + async getChatCompletion(messages = null, { temperature = 0.7 }) { + if (!(await this.isValidChatCompletionModel(this.model))) + throw new Error( + `PPIO chat: ${this.model} is not valid for chat completion!` + ); + + const result = await LLMPerformanceMonitor.measureAsyncFunction( + this.openai.chat.completions + .create({ + model: this.model, + messages, + temperature, + }) + .catch((e) => { + throw new Error(e.message); + }) + ); + + if ( + !Object.prototype.hasOwnProperty.call(result.output, "choices") || + result.output.choices.length === 0 + ) + return null; + + return { + textResponse: result.output.choices[0].message.content, + metrics: { + prompt_tokens: result.output.usage.prompt_tokens || 0, + completion_tokens: result.output.usage.completion_tokens || 0, + total_tokens: result.output.usage.total_tokens || 0, + outputTps: result.output.usage.completion_tokens / result.duration, + duration: result.duration, + }, + }; + } + + async streamGetChatCompletion(messages = null, { temperature = 0.7 }) { + if (!(await this.isValidChatCompletionModel(this.model))) + throw new Error( + `PPIO chat: ${this.model} is not valid for chat completion!` + ); + + const measuredStreamRequest = await LLMPerformanceMonitor.measureStream( + this.openai.chat.completions.create({ + model: this.model, + stream: true, + messages, + temperature, + }), + messages + ); + return measuredStreamRequest; + } + + handleStream(response, stream, responseProps) { + return handleDefaultStreamResponseV2(response, stream, responseProps); + } + + async embedTextInput(textInput) { + return await this.embedder.embedTextInput(textInput); + } + async embedChunks(textChunks = []) { + return await this.embedder.embedChunks(textChunks); + } + + async compressMessages(promptArgs = {}, rawHistory = []) { + const { messageArrayCompressor } = require("../../helpers/chat"); + const messageArray = this.constructPrompt(promptArgs); + return await messageArrayCompressor(this, messageArray, rawHistory); + } +} + +async function fetchPPIOModels() { + return await fetch(`https://api.ppinfra.com/v3/openai/models`, { + method: "GET", + headers: { + "Content-Type": "application/json", + Authorization: `Bearer ${process.env.PPIO_API_KEY}`, + }, + }) + .then((res) => res.json()) + .then(({ data = [] }) => { + const models = {}; + data.forEach((model) => { + const organization = model.id?.split("/")?.[0] || "PPIO"; + models[model.id] = { + id: model.id, + name: model.display_name || model.title || model.id, + organization, + maxLength: model.context_size || 4096, + }; + }); + + if (!fs.existsSync(cacheFolder)) + fs.mkdirSync(cacheFolder, { recursive: true }); + fs.writeFileSync( + path.resolve(cacheFolder, "models.json"), + JSON.stringify(models), + { + encoding: "utf-8", + } + ); + fs.writeFileSync( + path.resolve(cacheFolder, ".cached_at"), + String(Number(new Date())), + { + encoding: "utf-8", + } + ); + return models; + }) + .catch((e) => { + console.error(e); + return {}; + }); +} + +module.exports = { + PPIOLLM, + fetchPPIOModels, +}; diff --git a/server/utils/agents/aibitat/index.js b/server/utils/agents/aibitat/index.js index f5af2e907a3..83bc736ea60 100644 --- a/server/utils/agents/aibitat/index.js +++ b/server/utils/agents/aibitat/index.js @@ -795,7 +795,8 @@ ${this.getHistory({ to: route.to }) return new Providers.XAIProvider({ model: config.model }); case "novita": return new Providers.NovitaProvider({ model: config.model }); - + case "ppio": + return new Providers.PPIOProvider({ model: config.model }); default: throw new Error( `Unknown provider: ${config.provider}. Please use a valid provider.` diff --git a/server/utils/agents/aibitat/providers/ai-provider.js b/server/utils/agents/aibitat/providers/ai-provider.js index bd7920611be..1d7a37fac19 100644 --- a/server/utils/agents/aibitat/providers/ai-provider.js +++ b/server/utils/agents/aibitat/providers/ai-provider.js @@ -163,6 +163,14 @@ class Provider { apiKey: process.env.NOVITA_LLM_API_KEY ?? null, ...config, }); + case "ppio": + return new ChatOpenAI({ + configuration: { + baseURL: "https://api.ppinfra.com/v3/openai", + }, + apiKey: process.env.PPIO_API_KEY ?? null, + ...config, + }); // OSS Model Runners // case "anythingllm_ollama": diff --git a/server/utils/agents/aibitat/providers/index.js b/server/utils/agents/aibitat/providers/index.js index e5c01123c63..3b24ed20431 100644 --- a/server/utils/agents/aibitat/providers/index.js +++ b/server/utils/agents/aibitat/providers/index.js @@ -20,6 +20,7 @@ const ApiPieProvider = require("./apipie.js"); const XAIProvider = require("./xai.js"); const NovitaProvider = require("./novita.js"); const NvidiaNimProvider = require("./nvidiaNim.js"); +const PPIOProvider = require("./ppio.js"); module.exports = { OpenAIProvider, @@ -44,4 +45,5 @@ module.exports = { XAIProvider, NovitaProvider, NvidiaNimProvider, + PPIOProvider, }; diff --git a/server/utils/agents/aibitat/providers/ppio.js b/server/utils/agents/aibitat/providers/ppio.js new file mode 100644 index 00000000000..2baf895b2d2 --- /dev/null +++ b/server/utils/agents/aibitat/providers/ppio.js @@ -0,0 +1,115 @@ +const OpenAI = require("openai"); +const Provider = require("./ai-provider.js"); +const InheritMultiple = require("./helpers/classes.js"); +const UnTooled = require("./helpers/untooled.js"); + +/** + * The agent provider for the PPIO AI provider. + */ +class PPIOProvider extends InheritMultiple([Provider, UnTooled]) { + model; + + constructor(config = {}) { + const { model = "qwen/qwen2.5-32b-instruct" } = config; + super(); + const client = new OpenAI({ + baseURL: "https://api.ppinfra.com/v3/openai", + apiKey: process.env.PPIO_API_KEY, + maxRetries: 3, + defaultHeaders: { + "HTTP-Referer": "https://anythingllm.com", + "X-API-Source": "anythingllm", + }, + }); + + this._client = client; + this.model = model; + this.verbose = true; + } + + get client() { + return this._client; + } + + async #handleFunctionCallChat({ messages = [] }) { + return await this.client.chat.completions + .create({ + model: this.model, + temperature: 0, + messages, + }) + .then((result) => { + if (!Object.prototype.hasOwnProperty.call(result, "choices")) + throw new Error("PPIO chat: No results!"); + if (result.choices.length === 0) + throw new Error("PPIO chat: No results length!"); + return result.choices[0].message.content; + }) + .catch((_) => { + return null; + }); + } + + /** + * Create a completion based on the received messages. + * + * @param messages A list of messages to send to the API. + * @param functions + * @returns The completion. + */ + async complete(messages, functions = null) { + let completion; + if (functions.length > 0) { + const { toolCall, text } = await this.functionCall( + messages, + functions, + this.#handleFunctionCallChat.bind(this) + ); + + if (toolCall !== null) { + this.providerLog(`Valid tool call found - running ${toolCall.name}.`); + this.deduplicator.trackRun(toolCall.name, toolCall.arguments); + return { + result: null, + functionCall: { + name: toolCall.name, + arguments: toolCall.arguments, + }, + cost: 0, + }; + } + completion = { content: text }; + } + + if (!completion?.content) { + this.providerLog("Will assume chat completion without tool call inputs."); + const response = await this.client.chat.completions.create({ + model: this.model, + messages: this.cleanMsgs(messages), + }); + completion = response.choices[0].message; + } + + // The UnTooled class inherited Deduplicator is mostly useful to prevent the agent + // from calling the exact same function over and over in a loop within a single chat exchange + // _but_ we should enable it to call previously used tools in a new chat interaction. + this.deduplicator.reset("runs"); + return { + result: completion.content, + cost: 0, + }; + } + + /** + * Get the cost of the completion. + * + * @param _usage The completion to get the cost for. + * @returns The cost of the completion. + * Stubbed since PPIO has no cost basis. + */ + getCost() { + return 0; + } +} + +module.exports = PPIOProvider; diff --git a/server/utils/agents/index.js b/server/utils/agents/index.js index 531b2866a1a..c06751c6d47 100644 --- a/server/utils/agents/index.js +++ b/server/utils/agents/index.js @@ -184,6 +184,10 @@ class AgentHandler { "NVIDIA NIM base path must be provided to use agents." ); break; + case "ppio": + if (!process.env.PPIO_API_KEY) + throw new Error("PPIO API Key must be provided to use agents."); + break; default: throw new Error( @@ -249,6 +253,8 @@ class AgentHandler { return process.env.NOVITA_LLM_MODEL_PREF ?? "deepseek/deepseek-r1"; case "nvidia-nim": return process.env.NVIDIA_NIM_LLM_MODEL_PREF ?? null; + case "ppio": + return process.env.PPIO_MODEL_PREF ?? "qwen/qwen2.5-32b-instruct"; default: return null; } diff --git a/server/utils/helpers/customModels.js b/server/utils/helpers/customModels.js index 32cb977d56b..f0da28bf8ed 100644 --- a/server/utils/helpers/customModels.js +++ b/server/utils/helpers/customModels.js @@ -7,6 +7,7 @@ const { ElevenLabsTTS } = require("../TextToSpeech/elevenLabs"); const { fetchNovitaModels } = require("../AiProviders/novita"); const { parseLMStudioBasePath } = require("../AiProviders/lmStudio"); const { parseNvidiaNimBasePath } = require("../AiProviders/nvidiaNim"); +const { fetchPPIOModels } = require("../AiProviders/ppio"); const { GeminiLLM } = require("../AiProviders/gemini"); const SUPPORT_CUSTOM_MODELS = [ @@ -29,6 +30,7 @@ const SUPPORT_CUSTOM_MODELS = [ "novita", "xai", "gemini", + "ppio", ]; async function getCustomModels(provider = "", apiKey = null, basePath = null) { @@ -74,6 +76,8 @@ async function getCustomModels(provider = "", apiKey = null, basePath = null) { return await getNvidiaNimModels(basePath); case "gemini": return await getGeminiModels(apiKey); + case "ppio": + return await getPPIOModels(apiKey); default: return { models: [], error: "Invalid provider for custom models" }; } @@ -571,6 +575,19 @@ async function getGeminiModels(_apiKey = null) { return { models, error: null }; } +async function getPPIOModels() { + const ppioModels = await fetchPPIOModels(); + if (!Object.keys(ppioModels).length === 0) return { models: [], error: null }; + const models = Object.values(ppioModels).map((model) => { + return { + id: model.id, + organization: model.organization, + name: model.name, + }; + }); + return { models, error: null }; +} + module.exports = { getCustomModels, }; diff --git a/server/utils/helpers/index.js b/server/utils/helpers/index.js index 842d48e4e82..6fc7f00e01a 100644 --- a/server/utils/helpers/index.js +++ b/server/utils/helpers/index.js @@ -197,6 +197,9 @@ function getLLMProvider({ provider = null, model = null } = {}) { case "nvidia-nim": const { NvidiaNimLLM } = require("../AiProviders/nvidiaNim"); return new NvidiaNimLLM(embedder, model); + case "ppio": + const { PPIOLLM } = require("../AiProviders/ppio"); + return new PPIOLLM(embedder, model); default: throw new Error( `ENV: No valid LLM_PROVIDER value found in environment! Using ${process.env.LLM_PROVIDER}` @@ -338,6 +341,9 @@ function getLLMProviderClass({ provider = null } = {}) { case "nvidia-nim": const { NvidiaNimLLM } = require("../AiProviders/nvidiaNim"); return NvidiaNimLLM; + case "ppio": + const { PPIOLLM } = require("../AiProviders/ppio"); + return PPIOLLM; default: return null; } diff --git a/server/utils/helpers/updateENV.js b/server/utils/helpers/updateENV.js index 41216c96b36..ab76cb15fcf 100644 --- a/server/utils/helpers/updateENV.js +++ b/server/utils/helpers/updateENV.js @@ -615,6 +615,16 @@ const KEY_MAPPING = { }, ], }, + + // PPIO Options + PPIOApiKey: { + envKey: "PPIO_API_KEY", + checks: [isNotEmpty], + }, + PPIOModelPref: { + envKey: "PPIO_MODEL_PREF", + checks: [isNotEmpty], + }, }; function isNotEmpty(input = "") { @@ -721,6 +731,7 @@ function supportedLLM(input = "") { "apipie", "xai", "nvidia-nim", + "ppio", ].includes(input); return validSelection ? null : `${input} is not a valid LLM provider.`; }