LLM/DocsGPT
1
0
Fork 0
mirror of https://github.com/arc53/DocsGPT.git synced 2026-01-20 05:50:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: agent templates and seeding premade agents (#1910)

Browse Source 
* feat: agent templates and seeding premade agents

* fix: ensure ObjectId is used for source reference in agent configuration

* fix: improve source handling in DatabaseSeeder and update tool config processing

* feat: add prompt handling in DatabaseSeeder for agent configuration

* Docs premade agents

* link to prescraped docs

* feat: add template agent retrieval and adopt agent functionality

* feat: simplify agent descriptions in premade_agents.yaml  added docs

---------

Co-authored-by: Pavel <pabin@yandex.ru>
Co-authored-by: Alex <a@tushynski.me>
This commit is contained in:
Siddhant Rai
2025-10-07 15:30:14 +05:30
committed by GitHub
parent 8b8e616557
commit da6317a242
21 changed files with 1053 additions and 574 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
docs/pages/Agents/basics.mdx
View File

@@ -107,3 +107,13 @@ Once an agent is created, you can:
* Modify any of its configuration settings (name, description, source, prompt, tools, type).
* **Generate a Public Link:** From the edit screen, you can create a shareable public link that allows others to import and use your agent.
* **Get a Webhook URL:** You can also obtain a Webhook URL for the agent. This allows external applications or services to trigger the agent and receive responses programmatically, enabling powerful integrations and automations.
## Seeding Premade Agents from YAML
You can bootstrap a fresh DocsGPT deployment with a curated set of agents by seeding them directly into MongoDB.
1. **Customize the configuration** – edit `application/seed/config/premade_agents.yaml` (or copy from `application/seed/config/agents_template.yaml`) to describe the agents you want to provision. Each entry lets you define prompts, tools, and optional data sources.
2. **Ensure dependencies are running** – MongoDB must be reachable using the credentials in `.env`, and a Celery worker should be available if any agent sources need to be ingested via `ingest_remote`.
3. **Execute the seeder** – run `python -m application.seed.commands init`. Add `--force` when you need to reseed an existing environment.
The seeder keeps templates under the `system` user so they appear in the UI for anyone to clone or customize. Environment variable placeholders such as `${MY_TOKEN}` inside tool configs are resolved during the seeding process.