API endpoints
Langdock provides different APIs to connect models to your processes or use assistants programmatically.
How to create API keys
Admins can create and manage API keys in the API section of the settings.
If you’re not an admin, reach out to your Langdock admin to request an API key.
API overview
Completion API
The completion API lets you use AI models in other tools or your own workflows. This API provides direct model access without tools or attachments, giving you maximum flexibility for custom implementations. Find the documentation here
Assistant API
You can use any assistant through the API. An admin needs to share the assistant with your API key first (we’ll walk you through this process).
Once the assistant is connected to your API key, follow this guide to use it programmatically.
Knowledge folder API
The knowledge folder API lets you programmatically manage knowledge folders attached to assistants. This means you can automate document uploads, updates, and deletions without using the UI. Check out this guide for implementation details.
Embedding API
The embedding API creates embeddings for text using OpenAI’s embedding models. These vector representations are essential for semantic search, text similarity, and RAG applications. Find the documentation here.