mirror of
https://github.com/OpenHands/OpenHands.git
synced 2025-12-26 05:48:36 +08:00
simplify readme (#366)
* simplify readme * Update config.toml.template * Update vite.config.ts (#372) * Update vite.config.ts * Update frontend/vite.config.ts --------- Co-authored-by: Robert Brennan <accounts@rbren.io> * remove old langchains infra * remove refs to OPENAI_API_KEY * simplify opendevin readme --------- Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>
This commit is contained in:
Robert Brennan
GitHub
parent
11ed011b11
commit
6bd566d780
33
README.md
33
README.md
@ -23,26 +23,18 @@ OpenDevin is still a work in progress. But you can run the alpha version to see
|
||||
* [NodeJS](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) >= 14.8
|
||||
|
||||
### Installation
|
||||
First, make sure Docker is running:
|
||||
```bash
|
||||
docker ps # this should exit successfully
|
||||
```
|
||||
|
||||
Then pull our latest image [here](https://github.com/opendevin/OpenDevin/pkgs/container/sandbox)
|
||||
First, pull our latest sandbox image [here](https://github.com/opendevin/OpenDevin/pkgs/container/sandbox)
|
||||
```bash
|
||||
docker pull ghcr.io/opendevin/sandbox
|
||||
```
|
||||
|
||||
Then copy `config.toml.template` to `config.toml`. Add an API key to `config.toml`.
|
||||
(See below for how to use different models.)
|
||||
Then copy `config.toml.template` to `config.toml`. Add an OpenAI API key to `config.toml`,
|
||||
or see below for how to use different models.
|
||||
```toml
|
||||
OPENAI_API_KEY="..."
|
||||
WORKSPACE_DIR="..."
|
||||
LLM_API_KEY="sk-..."
|
||||
```
|
||||
|
||||
Next, start the backend.
|
||||
We manage python packages and the virtual environment with `pipenv`.
|
||||
Make sure you have python >= 3.10.
|
||||
Next, start the backend:
|
||||
```bash
|
||||
python -m pip install pipenv
|
||||
python -m pipenv install -v
|
||||
@ -56,6 +48,7 @@ cd frontend
|
||||
npm install
|
||||
npm start
|
||||
```
|
||||
You'll see OpenDevin running at localhost:3001
|
||||
|
||||
### Picking a Model
|
||||
We use LiteLLM, so you can run OpenDevin with any foundation model, including OpenAI, Claude, and Gemini.
|
||||
@ -79,20 +72,6 @@ And you can customize which embeddings are used for the vector database storage:
|
||||
LLM_EMBEDDING_MODEL="llama2" # can be "llama2", "openai", "azureopenai", or "local"
|
||||
```
|
||||
|
||||
### Running the app
|
||||
You should be able to run the backend now
|
||||
```bash
|
||||
uvicorn opendevin.server.listen:app --port 3000
|
||||
```
|
||||
Then in a second terminal:
|
||||
```bash
|
||||
cd frontend
|
||||
npm install
|
||||
npm run start -- --port 3001
|
||||
```
|
||||
|
||||
You'll see OpenDevin running at localhost:3001
|
||||
|
||||
### Running on the Command Line
|
||||
You can run OpenDevin from your command line:
|
||||
```bash
|
||||
|
||||
@ -1,20 +0,0 @@
|
||||
from python:3.12-bookworm
|
||||
|
||||
ENV OPENAI_API_KEY=""
|
||||
ENV OPENAI_MODEL="gpt-4-0125-preview"
|
||||
|
||||
RUN git config --global user.email "devin@opendevin.com"
|
||||
RUN git config --global user.name "Devin Abierto"
|
||||
|
||||
RUN apt-get update
|
||||
RUN apt-get install -y git sudo curl
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
COPY requirements.txt ./requirements.txt
|
||||
RUN python -m pip install -r requirements.txt
|
||||
|
||||
WORKDIR /workspace
|
||||
|
||||
CMD ["python", "/app/opendevin/main.py", "/workspace"]
|
||||
|
||||
@ -1,19 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -eo pipefail
|
||||
|
||||
rm -rf `pwd`/workspace
|
||||
mkdir -p `pwd`/workspace
|
||||
|
||||
pushd agenthub/langchains_agent
|
||||
docker build -t control-loop .
|
||||
popd
|
||||
docker run \
|
||||
-e DEBUG=$DEBUG \
|
||||
-e OPENAI_API_KEY=$OPENAI_API_KEY \
|
||||
-u `id -u`:`id -g` \
|
||||
-v `pwd`/workspace:/workspace \
|
||||
-v `pwd`:/app:ro \
|
||||
-e PYTHONPATH=/app \
|
||||
control-loop \
|
||||
python /app/opendevin/main.py -d /workspace -t "${1}"
|
||||
|
||||
@ -1,4 +1,4 @@
|
||||
# This is a template. Run `cp config.toml.template config.toml` to use it.
|
||||
|
||||
OPENAI_API_KEY="<YOUR OPENAI API KEY>"
|
||||
LLM_API_KEY="<YOUR OPENAI API KEY>"
|
||||
WORKSPACE_DIR="./workspace"
|
||||
|
||||
@ -7,7 +7,6 @@ export default defineConfig({
|
||||
base: "",
|
||||
plugins: [react(), viteTsconfigPaths()],
|
||||
server: {
|
||||
// this sets a default port to 3000
|
||||
port: 3001,
|
||||
},
|
||||
});
|
||||
|
||||
@ -2,9 +2,16 @@
|
||||
|
||||
This is a Python package that contains all the shared abstraction (e.g., Agent) and components (e.g., sandbox, web browser, search API, selenium).
|
||||
|
||||
## Sandbox component
|
||||
See the [main README](../README.md) for instructions on how to run OpenDevin from the command line.
|
||||
|
||||
Run the docker-based sandbox interactive:
|
||||
## Sandbox Image
|
||||
```bash
|
||||
docker build -f opendevin/sandbox/Dockerfile -t opendevin/sandbox:v0.1 .
|
||||
```
|
||||
|
||||
## Sandbox Runner
|
||||
|
||||
Run the docker-based interactive sandbox:
|
||||
|
||||
```bash
|
||||
mkdir workspace
|
||||
@ -17,31 +24,3 @@ Example screenshot:
|
||||
|
||||
<img width="868" alt="image" src="https://github.com/OpenDevin/OpenDevin/assets/38853559/8dedcdee-437a-4469-870f-be29ca2b7c32">
|
||||
|
||||
|
||||
## How to run
|
||||
|
||||
1. Build the sandbox image local. If you want to use specific image tags, please also fix the variable in code, in code default image tag is `latest`.
|
||||
```bash
|
||||
docker build -f opendevin/sandbox/Dockerfile -t opendevin/sandbox:v0.1 .
|
||||
```
|
||||
|
||||
Or you can pull the latest image [here](https://github.com/opendevin/OpenDevin/pkgs/container/sandbox):
|
||||
```bash
|
||||
docker pull ghcr.io/opendevin/sandbox
|
||||
```
|
||||
|
||||
2. Set the `OPENAI_API_KEY`, please find more details [here](https://help.openai.com/en/articles/5112595-best-practices-for-api-key-safety). Also, choose the model you want. Default is `gpt-4-0125-preview`
|
||||
```bash
|
||||
export OPENAI_API_KEY=xxxxxxx
|
||||
```
|
||||
|
||||
3. Install the requirement package.
|
||||
```bash
|
||||
pip install -r requirements.txt
|
||||
```
|
||||
If you still meet problem like `ModuleNotFoundError: No module named 'agenthub'`, try to add the `opendevin` root path into `PATH` env.
|
||||
|
||||
4. Run following cmd to start.
|
||||
```bash
|
||||
PYTHONPATH=`pwd` python ./opendevin/main.py -d ./workspace -t "write a bash script that prints hello world"
|
||||
```
|
||||
|
||||
@ -7,7 +7,7 @@ This is a WebSocket server that executes tasks using an agent.
|
||||
Create a `.env` file with the contents
|
||||
|
||||
```sh
|
||||
OPENAI_API_KEY=<YOUR OPENAI API KEY>
|
||||
LLM_API_KEY=<YOUR OPENAI API KEY>
|
||||
```
|
||||
|
||||
Install requirements:
|
||||
@ -36,7 +36,7 @@ websocat ws://127.0.0.1:3000/ws
|
||||
## Supported Environment Variables
|
||||
|
||||
```sh
|
||||
OPENAI_API_KEY=sk-... # Your OpenAI API Key
|
||||
LLM_API_KEY=sk-... # Your OpenAI API Key
|
||||
LLM_MODEL=gpt-4-0125-preview # Default model for the agent to use
|
||||
WORKSPACE_DIR=/path/to/your/workspace # Default path to model's workspace
|
||||
```
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user