feat: Ubuntu 20.04 images with CUDA and Miniconda3

.env

@@ -0,0 +1,46 @@
+# Exposed ports
+LITELLM_PORT=11111
+JUPYTER_PORT=37799
+# Redis ports at host side
+HOST_REDIS_SERVER_PORT=16379
+HOST_REDIS_INSIGHT_PORT=13333
+# Posgres variables
+POSTGRES_USER=litellm
+POSTGRES_PASSWORD=mysecretpassword
+POSTGRES_DB=litellm_memory
+POSTGRES_HOST_PORT=15432
+POSTGRES_CONTAINER_PORT=5432
+# Default Ollama model
+LITELLM_DEFAULT_MODEL=mistral
+# Default models
+EMBEDDING_MODEL=llama2
+# Directories
+APP_DIR=/var/lib/opendevin
+# Path to ollama models directory at the host machine
+HOST_MODELS_DIR=/mnt/g/LLMs/ollama/models
+# Devin workspace directory
+WORKSPACE_DIR=/opt/workspace
+# mitmproxy vуrsion
+MITMPROXY_VERSION=10.2.4
+# mitmproxy directory inside the container
+MITMPROXY_DIR=/home/mitmproxy/.mitmproxy
+# Toggle debug mode: empty or 'yes'
+DEBUG=yes
+# NodeJS version
+NODE_VERSION=18.20.1
+# NodeJS environment
+NODE_ENV=development
+# API Keys
+OPENAI_API_KEY=sk-12345678
+# Name of the container's Conda vitual environment
+VENV_NAME=od_env
+# Time zone is needed by some images to build
+TIMEZONE=Europe/Kyiv
+# MemGPT configuration file name inside container
+MEMGPT_CONFIG_FILE=/etc/memgpt/memgpt.json
+# Miniconda root directory
+CONDA_DIR=/root/miniconda3
+CONDA_CACHE_DIR=/root/anaconda/pkgs
+PIP_CACHE_DIR=/root/.cache/pip
+PGVECTOR_TEST_DB_URL=postgresql+pg8000://memgpt:memgpt@localhost:8888/memgpt
+

.env.dist

@@ -1,8 +1,8 @@
 # Exposed ports
 LITELLM_PORT=11111
 JUPYTER_PORT=37799
-REDIS_SERVER_HOST_PORT=16379
-REDIS_INSIGHT_HOST_PORT=13333
+HOST_REDIS_SERVER_PORT=16379
+HOST_REDIS_INSIGHT_PORT=13333
 # Posgres variables
 POSTGRES_USER=litellm
 POSTGRES_PASSWORD=mysecretpassword
@@ -32,6 +32,5 @@ NODE_ENV=production
 # API Keys
 OPENAI_API_KEY=sk-12345678
 # Nvidia image variables
-CUDA_VERSION=12.4.0
 CUDA_IMAGE_OS="ubuntu22.04"
 VENV_NAME=od_env

.gitignore

@@ -99,7 +99,7 @@ ipython_config.py
 #   This is especially recommended for binary packages to ensure reproducibility, and is more
 #   commonly ignored for libraries.
 #   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
-# poetry.lock
+#poetry.lock
 
 # pdm
 #   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
@@ -127,7 +127,6 @@ venv/
 ENV/
 env.bak/
 venv.bak/
-*venv/
 
 # Spyder project settings
 .spyderproject
@@ -197,7 +196,6 @@ logs
 .envrc
 /workspace
 /debug
-cache
 
 # configuration
 config.toml

README.md

@@ -7,6 +7,8 @@
 *** Thanks again! Now go create something AMAZING! :D
 -->
 
+
+
 <!-- PROJECT SHIELDS -->
 <!--
 *** I'm using markdown "reference style" links for readability.
@@ -34,8 +36,9 @@
 </div>
 
 
+
+
 <!-- TABLE OF CONTENTS -->
-<!--
 <details>
   <summary>🗂️ Table of Contents</summary>
   <ol>
@@ -59,7 +62,6 @@
     <li><a href="#-license">📜 License</a></li>
   </ol>
 </details>
--->
 
 ## 🎯 Mission
 
@@ -96,6 +98,13 @@ The OpenDevin project is born out of a desire to replicate, enhance, and innovat
 
 OpenDevin is currently a work in progress, but you can already run the alpha version to see the end-to-end system in action. The project team is actively working on the following key milestones:
 
+- **UI**: Developing a user-friendly interface, including a chat interface, a shell demonstrating commands, and a web browser.
+- **Architecture**: Building a stable agent framework with a robust backend that can read, write, and run simple commands.
+- **Agent Capabilities**: Enhancing the agent's abilities to generate bash scripts, run tests, and perform other software engineering tasks.
+- **Evaluation**: Establishing a minimal evaluation pipeline that is consistent with Devin's evaluation criteria.
+
+After completing the MVP, the team will focus on research in various areas, including foundation models, specialist capabilities, evaluation, and agent studies.
+
 <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
     <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
         ↑ Back to Top ↑
@@ -110,6 +119,7 @@ Getting started with the OpenDevin project is incredibly easy. Follow these simp
 * Linux, Mac OS, or [WSL on Windows](https://learn.microsoft.com/en-us/windows/wsl/install)
 * [Docker](https://docs.docker.com/engine/install/)
 * [Python](https://www.python.org/downloads/) >= 3.11
+* [NodeJS](https://nodejs.org/en/download/package-manager) >= 18.17.1
 
 ### 2. Build and Setup The Environment
 
@@ -145,19 +155,6 @@ For a full list of the LM providers and models available, please consult the [li
     docker compose up
     ```
 
-### 5. Individual Server Startup
-
-- **Start the Backend Server:** If you prefer, you can start the backend server independently to focus on backend-related tasks or configurations.
-    ```bash
-    docker compose up devin-app
-    ```
-
-- **Start the Frontend Server:** Similarly, you can start the frontend server on its own to work on frontend-related components or interface enhancements.
-    ```bash
-    docker compose up devin-ui
-    ```
-
-
 <p align="right" style="font-size: 14px; color: #555; margin-top: 20px;">
     <a href="#readme-top" style="text-decoration: none; color: #007bff; font-weight: bold;">
         ↑ Back to Top ↑