ConnectAI-E/feishu-openai
Feishu Openai
This project is an AI assistant integration that connects OpenAI models to the Feishu team communication platform. It functions as a multi-model gateway that routes requests to GPT-4, GPT-4V, DALL-E-3, and Whisper models, enabling voice conversations, image generation, and multi-topic dialogues within team chats.
The assistant operates through a bridge layer that translates Feishu chat events into internal commands, supporting plugin-based persona switching to alter response behavior and tone for different use cases. It distributes API requests across multiple authentication tokens for load balancing, forwards requests through a configurable reverse proxy, and formats replies as structured cards with images, buttons, and text using Feishu's interactive message API.
Conversation management preserves context across threads with auto-expiring inactive sessions, while voice input is transcribed via Whisper API and responses can be synthesized for audible replies. The system also supports text-to-image generation and reverse image search for visual queries, with token balance checking to help monitor usage costs.
Features
- Feishu and Lark Integrations - Connects OpenAI models to Feishu for voice conversations, image generation, and multi-topic discussions within team chats.
- Context-Aware Conversation Managers - Maintains separate conversation histories per thread and user, automatically expiring inactive sessions.
- Dialogue Context Management - Maintains separate conversation threads in private and group chats for coherent, topic-specific discussions.
- Messaging Platform Bridges - Provides a bridge layer that translates Feishu chat events into internal commands for AI model interaction.
- Model Gateways - Routes requests to GPT-4, GPT-4V, DALL-E-3, and Whisper models with load balancing and proxy support.
- Multi-Model Orchestration - Routes requests to GPT-4, GPT-4V, DALL-E-3, and Whisper models based on detected input type and task.
- Conversation Thread Contexts - Preserves dialogue history across threads with auto-expiring inactive sessions for coherent multi-topic conversations.
- Conversational Voice AI - Processes spoken input and responds audibly to enable hands-free interaction within the platform.
- Conversational Voice Pipelines - Transcribes audio messages via Whisper API and synthesizes spoken responses for voice conversations.
- Persona Configurations - Applies pre-built role and scenario configurations to instantly change the assistant's behavior and tone.
- Text-to-Image Generators - Creates images based on textual descriptions and supports reverse image search for visual queries.
- Bots - Creates images from text descriptions and supports reverse image search for visual queries within Feishu.
- Voice Assistants - Processes spoken input and responds audibly for hands-free interaction within the Feishu platform.
- Cards - Sends responses as formatted cards with images, buttons, and structured text for richer information delivery.
- Token Load Balancers - Distributes API requests across multiple authentication tokens to handle high-frequency production calls reliably.
- AI Persona Plugins - Loads role and scenario configurations as interchangeable plugins that modify response behavior and tone.
- JSON-Based Card Rendering - Formats replies as structured cards with images, buttons, and text using Feishu's interactive message API.
Star history
How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
