apunkt/rowboat
1
0
Fork 0
mirror of https://github.com/rowboatlabs/rowboat.git synced 2026-04-25 00:16:29 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

Rename env.copy to env.example, updated readme and notice

Browse source
This commit is contained in:
akhisud3195 2025-01-14 15:22:37 +05:30
parent 04e0cfdd07
commit 10fe4bfe76
3 changed files with 6 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

0
apps/agents/.env.copy → apps/agents/.env.example
View file

8
apps/agents/NOTICE.md
View file

@ -32,13 +32,13 @@ SOFTWARE.
```
# High-level changes
These are the high-level changes made to OpenAI Swarm to build in RowBoat's custom implementation.
Please note that this not an exhaustive list:
These are the high-level changes made to OpenAI Swarm to build in RowBoat's custom implementation:
- Added localized agent-level history
- Added parent-child agent relationships with parents' history containing children's history
- Added usage tracking of tokens per llm
- Added turn-level error handling
- Added converstaion turn limits
- Removed streaming support as RowBoat Agents does not support streaming currently
- Modified the `Agent` and `Response` classes to be more comprehensive
- Modified the `Agent` and `Response` classes to be more comprehensive
The above is not an exhaustive list.

4
apps/agents/README.md
View file

@ -5,7 +5,7 @@ Please visit https://www.rowboatlabs.com to learn more about RowBoat Labs
## Overview
- RowBoat Agents is a multi-agent framework which powers agentic workflows. The best way to configure these workflows is via the RowBoat Studio (UI), the source code for which is at [rowboatlabs/rowboat](https://github.com/rowboatlabs/rowboat/tree/dev/apps/rowboat)
- The Rowboat Agents framework has been built upon [OpenAI Swarm](https://github.com/openai/swarm), with modifications and improvements. Please see NOTICE.md in this directory, for attribution notes and more details. OpenAI Swarm is available under the MIT license as of the time of this writing.
- The Rowboat Agents framework has been built upon [OpenAI Swarm](https://github.com/openai/swarm), with modifications and improvements. Please see the `NOTICE.md` file in this directory, for attribution notes and more details. OpenAI Swarm is available under the MIT license as of the time of this writing.
- Multi-agent systems are typically implemented as graphs, where each agent is a node in the graph. At every turn of conversation, the graph is traversed based on the a) `state` which contains currently active agent and agent-level histories and b) the current set of `messages`.
- RowBoat Agents is a stateless implementation of such a graph-based system (specifically, a DAG or directed acyclic graph). The incoming request JSON (corresponding to a turn of conversation) is parsed to extract `messages`, `state` and the `workflow`.
- The `workflow` is a representation of the DAG containing agents, with each agent having a set of tools and connected children agents. See `tests/sample_requests/default_example.json` for an example of a complete request JSON from an upstream service.
@ -60,7 +60,7 @@ Install either using poetry or using pip
`pip install -r requirements.txt`
## Set up .env file
Copy `.env.copy` to `.env` and add your API keys
Copy `.env.example` to `.env` and add your API keys
## Run interactive test
`python -m tests.interactive --config default_config.json --sample_request default_example.json --load_messages`