mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-14 16:16:48 +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.
36 lines
1.6 KiB
YAML
36 lines
1.6 KiB
YAML
# Configuration for Premade Agents
|
|
# This file contains template agents that will be seeded into the database
|
|
|
|
agents:
|
|
# Basic Agent Template
|
|
- name: "Agent Name" # Required: Unique name for the agent
|
|
description: "What this agent does" # Required: Brief description of the agent's purpose
|
|
image: "URL_TO_IMAGE" # Optional: URL to agent's avatar/image
|
|
agent_type: "classic" # Required: Type of agent (e.g., classic, react, etc.)
|
|
prompt_id: "default" # Optional: Reference to prompt template
|
|
prompt: # Optional: Define new prompt
|
|
name: "New Prompt"
|
|
content: "You are new agent with cool new prompt."
|
|
chunks: "0" # Optional: Chunking strategy for documents
|
|
retriever: "" # Optional: Retriever type for document search
|
|
|
|
# Source Configuration (where the agent gets its knowledge)
|
|
source: # Optional: Select a source to link with agent
|
|
name: "Source Display Name" # Human-readable name for the source
|
|
url: "https://example.com/data-source" # URL or path to knowledge source
|
|
loader: "url" # Type of loader (url, pdf, txt, etc.)
|
|
|
|
# Tools Configuration (what capabilities the agent has)
|
|
tools: # Optional: Remove if agent doesn't need tools
|
|
- name: "tool_name" # Must match a supported tool name
|
|
display_name: "Tool Display Name" # Optional: Human-readable name for the tool
|
|
config:
|
|
# Tool-specific configuration
|
|
# Example for DuckDuckGo:
|
|
# token: "${DDG_API_KEY}" # ${} denotes environment variable
|
|
|
|
# Add more tools as needed
|
|
# - name: "another_tool"
|
|
# config:
|
|
# param1: "value1"
|
|
# param2: "${ENV_VAR}" |