Merge pull request #49 from semanser/multi-llm-support

Add multi LLMs support

Author: semanser

README.md

@@ -14,47 +14,37 @@
 - 🤳 Self-hosted
 - 💅 Modern UI
 
-# Usage
+# Getting started
 The simplest way to run Codel is to use a pre-built Docker image. You can find the latest image on the [Github Container Registry](https://github.com/semanser/codel/pkgs/container/codel).
 
 
 > [!IMPORTANT]
-> Don't forget to set the required environment variables.
+> You need to use a corresponding environment variable in order to use any of the supported language models.
 
+You can run the Docker image with the following command. Remove or change the environment variables according to your needs.
 ```bash
-docker run -d \
-  -e OPEN_AI_KEY=<your_open_ai_key> \
+docker run \
+  -e OPEN_AI_KEY=your_open_ai_key \
+  -e OPEN_AI_MODEL=gpt-4-0125-preview \
+  -e OLLAMA_MODEL=llama2 \
   -p 3000:8080 \
   -v /var/run/docker.sock:/var/run/docker.sock \
   ghcr.io/semanser/codel:latest
 ```
 
-Alternatively, you can create a .env file and run the Docker image with the following command:
-```bash
-docker run -d \
-  --env-file .env \
-  -p 3000:8080 \
-  -v /var/run/docker.sock:/var/run/docker.sock \
-  ghcr.io/semanser/codel:latest
-```
+Alternatively, you can create a `.env` file and run the Docker image with the `--env-file` flag. More information can be found [here](https://docs.docker.com/reference/cli/docker/container/run/#env)
 
 Now you can visit [localhost:3000](localhost:3000) in your browser and start using Codel.
 
 <details>
-  <summary>Required environment variables</summary>
-
-    - `OPEN_AI_KEY` - OpenAI API key
-</details>
-
-<details>
-    <summary>Optional environment variables</summary>
-
-    - `OPEN_AI_MODEL` - OpenAI model (default: gpt-4-0125-preview). The list of supported OpenAI models can be found [here](https://pkg.go.dev/github.com/sashabaranov/go-openai#pkg-constants).
-    - `DATABASE_URL` - PostgreSQL database URL (eg. `postgres://user:password@localhost:5432/database`)
-    - `DOCKER_HOST` - Docker SDK API (eg. `DOCKER_HOST=unix:///Users/<my-user>/Library/Containers/com.docker.docker/Data/docker.raw.sock`) [more info](https://stackoverflow.com/a/62757128/5922857)
-    - `PORT` - Port to run the server in the Docker container (default: 8080)
+    <summary>Supported environment variables</summary>
 
+    * `OPEN_AI_KEY` - OpenAI API key. You can get the key [here](https://platform.openai.com/account/api-keys).
+    * `OPEN_AI_MODEL` - OpenAI model (default: gpt-4-0125-preview). The list of supported OpenAI models can be found [here](https://pkg.go.dev/github.com/sashabaranov/go-openai#pkg-constants).
+    * `OPEN_AI_SERVER_URL` - OpenAI server URL (default: https://api.openai.com/v1). Change this URL if you are using an OpenAI compatible server.
+    * `OLLAMA_MODEL` - locally hosted Ollama model (default: https://ollama.com/model). The list of supported Ollama models can be found [here](https://ollama.com/models).
     See backend [.env.example](./backend/.env.example) for more details.
+
 </details>
 
 # Development

backend/.env.example

@@ -1,6 +1,16 @@
-OPEN_AI_KEY=
-OPEN_AI_SERVER_URL=
+# General
 DATABASE_URL=
 DOCKER_HOST=
+PORT=
+
+# OpenAI
+OPEN_AI_KEY=
+OPEN_AI_SERVER_URL=
 OPEN_AI_MODEL=
-PORT=
+
+# Ollama
+OLLAMA_MODEL=
+
+# Goose
+GOOSE_DRIVER=
+GOOSE_DBSTRING=