Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active
TypeScript aianthropicartifactsawsazurechatgptchatgpt-cloneclaudeclonedeepseekgeminigooglegpt-5librechatmcpo1openairesponses-apivisionwebui
fix(openai/completions): use old method for instruct/davinci/text gen models (#1166)
Danny Avila9ca84edb9aa1
diff --git a/api/app/clients/OpenAIClient.js b/api/app/clients/OpenAIClient.jsindex 124d05e68f..c7c973e482 100644--- a/api/app/clients/OpenAIClient.js+++ b/api/app/clients/OpenAIClient.js@@ -367,7 +367,7 @@ If your reverse proxy is compatible to OpenAI specs in every other way, it may slet streamResult = null;this.modelOptions.user = this.user;const invalidBaseUrl = this.completionsUrl && extractBaseURL(this.completionsUrl) === null;- const useOldMethod = !!(this.azure || invalidBaseUrl);+ const useOldMethod = !!(this.azure || invalidBaseUrl || !this.isChatCompletion);if (typeof opts.onProgress === 'function' && useOldMethod) {await this.getCompletion(payload,@@ -702,9 +702,10 @@ ${convo}if (typeof onProgress === 'function') {modelOptions.stream = true;}- if (this.isChatGptModel) {+ if (this.isChatCompletion) {modelOptions.messages = payload;} else {+ // TODO: unreachable code. Need to implement completions call for non-chat modelsmodelOptions.prompt = payload;}