Open-source, secure environment with real-world tools for enterprise-grade agents.
Python agentaiai-agentai-agentscode-interpretercopilotdevelopmentdevtoolsgptgpt-4javascriptllmnextjsopenaipythonreactsoftwaretypescript
Improve readme and contrib guide
Tomas Valenta09a9d28b3bd4
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.mdindex d0fb5c2e8..c52459529 100644--- a/CONTRIBUTING.md+++ b/CONTRIBUTING.md@@ -1,14 +1,14 @@# Contributing-If you want to contribute open a PR, issue, or start a discussion on our [Discord](https://discord.gg/dSBY3ms2Qr).+If you want to contribute, open a PR, issue, or start a discussion on our [Discord](https://discord.gg/dSBY3ms2Qr).# π€ Adding a new model providerIf you want to add a new model provider (like OpenAI or HuggingFace) complete the following steps and create a PR.-When you add a provider you can also add a specific models (like OpenAI's GPT-4) under that provider.+When you add a provider you can also add a specific model (like OpenAI's GPT-4) under that provider.Here is an [example code for adding a new provider](./NEW_PROVIDER_EXAMPLE.md).-## 1. Add provider to **frontend**+## 1. Add the provider to **frontend**- Add provider name to `ModelProvider` enum in [state/model.ts](state/model.ts)- Add provider and models template to `modelTemplates` object in [state/model.ts](state/model.ts)- `creds` and `args` defined in the `modelTemplates` are accessible on backend in `get_model` under their exact names in `config["args"]` object.@@ -17,12 +17,12 @@ Here is an [example code for adding a new provider](./NEW_PROVIDER_EXAMPLE.md).## 2. Add provider to **backend** ([api-service/models/base.py](api-service/models/base.py))- Add provider name to `ModelProvider` enum-- Add provider integration (implementing LangChain's `BaseLanguageModel`) to `get_model` function. You can use an existing integration from LangChain or crate a new integration from scratch.+- Add provider integration (implementing LangChain's `BaseLanguageModel`) to `get_model` function. You can use an existing integration from LangChain or create a new integration from scratch.The new provider integrations should be placed in `api-service/models/providers/`.## Provider integrations-We use [LangChain](https://github.com/hwchase17/langchain) under the hood so if you are adding a new integration you have to implement the `BaseLanguageModel` class. That basically means just implementing the `_acall` which is an async method that calls the model with prompt and returns the output.+We use [LangChain](https://github.com/hwchase17/langchain) under the hood, so if you are adding a new integration you have to implement the `BaseLanguageModel` class. That means just implementing the `_acall` async method that calls the model with a prompt and returns the output.### **Using [LangChain](https://python.langchain.com/en/latest/modules/models/llms/integrations.html) integration**You can often use existing LangChain integrations to add new model providers to e2b with just a few modifications.@@ -67,53 +67,4 @@ class NewModelProviderWithStreaming(LLM):```## 3. Test-Test if the provider works by starting the app, selecting the provider and model in the "Model" sidebar menu and trying to "Run" it.--Add a screenshot of the results to the PR if you can.---# π» Development setup-For developing with hot reloading and contributing to the project you may want to run the app locally without Docker Compose (`npm start` command). Here are the steps for how to do it.--You will need:-- OpenAI API key (support for more and custom models coming soon)-- Docker-- Node.js *16+*-- Python *3.10+*-- Poetry *1.3.2+*-- Free ports 3000, 49155, 49160, 54321, 54322--## 1. Install dependencies-```-npm run install:all-```--## 2. Start local Supabase-```-npm run db:start-```--> Local Supabase runs in the background - to stop it you have to run `npm run db:stop`.--## 3. Add env vars-Create `.env` file by copying the [`.env.example`](.env.example)-```-cp .env.example .env-```-and fill in the following variables:-- `SUPABASE_SERVICE_ROLE_KEY` - Supabase service role key you got in the previous step as `service_role key: eyJh......`-- `NEXT_PUBLIC_SUPABASE_ANON_KEY` - Supabase anonymous key you got in the previous step as `anon key: eyJh......`--## 4. Start the app-```-npm run dev-```-Then open the page on [http://localhost:3000](http://localhost:3000) and sign in with the testing credentials:--**Email**---**Password**-+Test if the provider works by starting the app, selecting the provider and model in the "Model" sidebar menu and trying to "Run" it. Then add a screenshot of agent steps to the PR.diff --git a/README.md b/README.mdindex 91daefdbe..250b0e60a 100644--- a/README.md+++ b/README.md@@ -34,28 +34,71 @@ e2b currently supports building only REST servers in Node.js. Specifically using# π Get startedWe're working on the cloud-hosted version. In the meantime, the fastest way try out e2b is to run it locally via Docker.+## π³ Start e2b with DockerYou will need:- [OpenAI API key](https://platform.openai.com/account/api-keys) (support for more and custom models coming soon)- Docker- Node.js *16+*- Free ports 3000 (Next.js app), 54321 (Supabase API Gateway), 54322 (Supabase Database)-> The first start of the Dockerized app is slower because it downloads and builds all the necessary containers. On a 2CPU 4GB RAM machine it takes cca. 6 minutes and doesn't require any interaction. The subsequent starts are way faster.--## Start the app+To start e2b run:```npm start```-Then open the page on [http://localhost:3000](http://localhost:3000).-> `npm start` starts local Supabase in the background - to stop it you have to run `npm run stop`.+Then open page on [http://localhost:3000](http://localhost:3000).-> If you want to run non-containerize version of e2b use the [development setup here](CONTRIBUTING.md#π»-development-setup). This is useful if you want to leverage hot reloading and develop the project.+`npm start` starts local Supabase in the background - to stop it you have to run `npm run stop`.-# Features+## π» Or start in development setup+For developing with hot reloading and contributing to the project you may want to run the app locally without Docker (`npm start` command). Here are the steps for how to do it.-## π Bring your own X+You will need:+- OpenAI API key (support for more and custom models coming soon)+- Docker (For starting the Supabase DB locally)+- Node.js *16+*+- Python *3.10+*+- Poetry *1.3.2+*+- Free ports 3000, 49155, 49160, 54321, 54322+### 1. Install dependencies+```+npm run install:all+```++### 2. Start local Supabase+```+npm run db:start+```++Local Supabase runs in the background - to stop it you have to run `npm run db:stop`.++### 3. Add env vars+Create `.env` file by copying the [`.env.example`](.env.example)+```+cp .env.example .env+```+and fill in the following variables:+- `SUPABASE_SERVICE_ROLE_KEY` - Supabase service role key you got in the previous step as `service_role key: eyJh......`+- `NEXT_PUBLIC_SUPABASE_ANON_KEY` - Supabase anonymous key you got in the previous step as `anon key: eyJh......`++### 4. Start the app+```+npm run dev+```+Then open page on [http://localhost:3000](http://localhost:3000) and sign in with the testing credentials:++**Email**+++**Password**++++# Features+## π Bring your own XWhile e2b will offer the "batteries-included" solution, our goal is to let users:- **BYOM** - Bring Your Own Model- **BYOP** - Bring Your Own Prompt@@ -73,7 +116,7 @@ We think the AI-powered IDE for the future should be open-sourced and allow anyb- [ ] Claude v1.3- [ ] Claude Instant v1-### **Model or provider you like isn't supported?**+### **Model or model hosting provider you like isn't supported?**π Please open the ["New model request" issue](https://github.com/e2b-dev/e2b/issues/new?assignees=&labels=new+model+request&template=new-model-request.md&title=) π