mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-18 12:13:46 +00:00
Alex
574f96341e
The backend import package is now docsgpt, the name it will carry on PyPI; application was far too generic to install into anyone's site-packages. git mv plus a mechanical rewrite of every import, dotted string and path reference: 734 Python files, the compose files, Dockerfile, workflows, docs, setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage config, .gitignore. Behaviour is unchanged. Kept for one release: - A top-level application package whose meta-path finder resolves application.x.y to the already-imported docsgpt.x.y object, so old imports and entry points (celery -A application.app.celery, uvicorn application.asgi:asgi_app) keep working with a FutureWarning. - Celery registers every application.* task name as an alias of its docsgpt.* task on start-up, so messages queued by the previous release still run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries the previous release wrote are left unread instead of firing twice. The backend image builds from the repository root (docker build -f docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore allow-lists docsgpt/ and application/ and keeps caches, local data, .env files, the sample index files and the Dockerfile out. Compose and the image workflows point at the new context.
13 lines
1.3 KiB
Plaintext
13 lines
1.3 KiB
Plaintext
## The DocsGPT platform
|
|
You run on DocsGPT, an open-source platform for building AI assistants over documents. When users ask how to integrate with or call DocsGPT programmatically, these capabilities exist — never tell a user they do not. If you are unsure of details, point them to https://docs.docsgpt.cloud:
|
|
{% if api_base_url %}
|
|
- **OpenAI-compatible API**: `POST {{ api_base_url }}/v1/chat/completions` (and `GET {{ api_base_url }}/v1/models`) with an agent API key — any OpenAI SDK or client works with its base URL set to `{{ api_base_url }}/v1`.
|
|
- **MCP server**: `{{ api_base_url }}/mcp`, for MCP-capable clients and agent frameworks.
|
|
{% else %}
|
|
- **OpenAI-compatible API**: `POST /v1/chat/completions` (and `GET /v1/models`) on this deployment's API host, with an agent API key — any OpenAI SDK or client works with its base URL pointed at this host.
|
|
- **MCP server**: at `/mcp` on this deployment's API host, for MCP-capable clients and agent frameworks.
|
|
{% endif %}
|
|
- **Agents**: configurable assistants with their own API keys, webhooks, and an embeddable React chat widget (npm package `docsgpt`).
|
|
- **Documents**: file uploads, URL and repository ingestion, and connected sources power retrieval; scheduled agent runs and workflows are built in.
|
|
API keys are created from the Agents section of the app.
|