Fix 'ask_user' error

README.md

@@ -54,20 +54,55 @@ Read [**README.md**](docs/architecture) for the detailed documentation.
 
 
 ## Getting Started
-
-### Requirements
-```
-Version's requirements
-  - Python >= 3.10 and < 3.12
-  - NodeJs >= 18
-  - bun
-```
-
+- Nvidia Driver installation
+
+  https://linuxconfig.org/how-to-install-nvidia-drivers-on-ubuntu-24-04
+
+  nvtop to see installed Nvidia Cards
+
+- Python >= 3.10 and < 3.12
+
+  sudo apt update && sudo apt upgrade
+
+  sudo apt install python3 python-is-python3
+
+- NodeJs >= 18 Installation
+  [NodeJs >= 18 Installation](https://linuxconfig.org/how-to-install-node-js-on-ubuntu-24-04)
+
+  sudo apt install nodejs
+
+  sudo apt install npm
+
+  node -v
+
+- Pip Installation
+
+  sudo apt install pip
+
+  python3 -m pip config set global.break-system-packages true
+
+  als Alternative im uv pip installieren ???
+
+  sudo apt install python3-pip
+
 - Install uv - Python Package manager [download](https://github.com/astral-sh/uv)
+
+  $ pip install uv
+
 - Install bun - JavaScript runtime [download](https://bun.sh/docs/installation)
 - For ollama [ollama setup guide](docs/Installation/ollama.md) (optinal: if you don't want to use the local models then you can skip this step)
+
+  curl -fsSL https://ollama.com/install.sh | sh
+
+  ./get-ollama-models.sh
+
+
+
 - For API models, configure the API keys via setting page in UI.
 
+  Keys without <> 
+
+
 
 ### Installation
 
@@ -99,6 +134,7 @@ To install Devika, follow these steps:
    ```
 5. Start the Devika server:
    ```bash
+   npm install @sveltejs/adapter-node
    python devika.py
    ```
 6. if everything is working fine, you see the following output:
@@ -113,6 +149,27 @@ To install Devika, follow these steps:
    ```
 8. Access the Devika web interface by opening a browser and navigating to `http://127.0.0.1:3001`
 
+9. Install xterm in wsl
+
+    sudo apt install xterm
+
+10. Windows run Xming Server from http://www.straightrunning.com/XmingNotes/#head-16
+
+11. Change Fontsize in xterm
+
+    sudo apt install x11-xserver-utils
+
+    vi ~./Xresources
+
+    xterm*font:     *-fixed-*-*-*-18-*
+
+    run xrdb -merge ~/.Xresources
+
+14. Install Code
+
+    sudo snap install --classic code
+
+
 ### how to use
 
 To start using Devika, follow these steps:

app.dockerfile

@@ -1,29 +1,29 @@
-FROM debian:12
+# Pulling stage 1 image, keep alias as layer1
+FROM node:latest as layer1
 
-# setting up build variable
+# Setting necessary arguments
 ARG VITE_API_BASE_URL
 ENV VITE_API_BASE_URL=${VITE_API_BASE_URL}
 
-# setting up os env
-USER root
+# Copy UI source code
+copy ui /home/nonroot/client
+
+# Change Work directory
 WORKDIR /home/nonroot/client
-RUN groupadd -r nonroot && useradd -r -g nonroot -d /home/nonroot/client -s /bin/bash nonroot
 
-# install node js 
-RUN apt-get update && apt-get upgrade -y
-RUN apt-get install -y build-essential software-properties-common curl sudo wget git
-RUN curl -fsSL https://deb.nodesource.com/setup_20.x | sudo -E bash -
-RUN apt-get install nodejs
+RUN npm install
+# Building APP bundle
+RUN npm run build
 
-# copying devika app client only
-COPY ui /home/nonroot/client/ui
-COPY src /home/nonroot/client/src
-COPY config.toml /home/nonroot/client/
+# Pulling stage 2 image, to significantly reduce image size
+FROM gcr.io/distroless/nodejs20-debian11
 
-RUN cd ui && npm install && npm install -g npm && npm install -g bun
-RUN chown -R nonroot:nonroot /home/nonroot/client
+# Copy build files from layer 1
+COPY --from=layer1 /home/nonroot/client/build /app
+COPY --from=layer1 /home/nonroot/client/package.json /app
 
-USER nonroot
-WORKDIR /home/nonroot/client/ui
+# Change Work directory
+WORKDIR /app
 
-ENTRYPOINT [ "npx", "bun", "run", "dev", "--", "--host" ]
+# RUN APP
+CMD ["index.js"]

devika.py

@@ -29,22 +29,24 @@
 CORS(app, resources={r"/*": {"origins": # Change the origin to your frontend URL
                              [
                                  "https://localhost:3000",
+                                 "https://localhost:3001",
                                  "http://localhost:3000",
+                                 "http://localhost:3001"
                                  ]}}) 
 app.register_blueprint(project_bp)
 socketio.init_app(app)
 
 
 log = logging.getLogger("werkzeug")
-log.disabled = True
+log.disabled = False
 
 
 TIKTOKEN_ENC = tiktoken.get_encoding("cl100k_base")
 
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
 
 manager = ProjectManager()
-AgentState = AgentState()
+agent_state = AgentState()
 config = Config()
 logger = Logger()
 
@@ -84,17 +86,17 @@ def handle_message(data):
 
     agent = Agent(base_model=base_model, search_engine=search_engine)
 
-    state = AgentState.get_latest_state(project_name)
+    state = agent_state.get_latest_state(project_name)
     if not state:
         thread = Thread(target=lambda: agent.execute(message, project_name))
         thread.start()
     else:
-        if AgentState.is_agent_completed(project_name):
+        if AgentState.is_agent_completed(agent_state, project_name):
             thread = Thread(target=lambda: agent.subsequent_execute(message, project_name))
             thread.start()
         else:
             emit_agent("info", {"type": "warning", "message": "previous agent doesn't completed it's task."})
-            last_state = AgentState.get_latest_state(project_name)
+            last_state = agent_state.get_latest_state(project_name)
             if last_state["agent_is_active"] or not last_state["completed"]:
                 thread = Thread(target=lambda: agent.execute(message, project_name))
                 thread.start()
@@ -107,7 +109,7 @@ def handle_message(data):
 def is_agent_active():
     data = request.json
     project_name = data.get("project_name")
-    is_active = AgentState.is_agent_active(project_name)
+    is_active = agent_state.is_agent_active(project_name)
     return jsonify({"is_active": is_active})
 
 
@@ -116,8 +118,8 @@ def is_agent_active():
 def get_agent_state():
     data = request.json
     project_name = data.get("project_name")
-    agent_state = AgentState.get_latest_state(project_name)
-    return jsonify({"state": agent_state})
+    latest_state = agent_state.get_latest_state(project_name)
+    return jsonify({"state": latest_state})
 
 
 @app.route("/api/get-browser-snapshot", methods=["GET"])
@@ -131,23 +133,23 @@ def browser_snapshot():
 @route_logger(logger)
 def get_browser_session():
     project_name = request.args.get("project_name")
-    agent_state = AgentState.get_latest_state(project_name)
-    if not agent_state:
+    latest_state = agent_state.get_latest_state(project_name)
+    if not latest_state:
         return jsonify({"session": None})
     else:
-        browser_session = agent_state["browser_session"]
+        browser_session = latest_state["browser_session"]
         return jsonify({"session": browser_session})
 
 
 @app.route("/api/get-terminal-session", methods=["GET"])
 @route_logger(logger)
 def get_terminal_session():
     project_name = request.args.get("project_name")
-    agent_state = AgentState.get_latest_state(project_name)
-    if not agent_state:
+    latest_state = agent_state.get_latest_state(project_name)
+    if not latest_state:
         return jsonify({"terminal_state": None})
     else:
-        terminal_state = agent_state["terminal_session"]
+        terminal_state = latest_state["terminal_session"]
         return jsonify({"terminal_state": terminal_state})
 
 
@@ -174,7 +176,7 @@ def calculate_tokens():
 @route_logger(logger)
 def token_usage():
     project_name = request.args.get("project_name")
-    token_count = AgentState.get_latest_token_usage(project_name)
+    token_count = agent_state.get_latest_token_usage(project_name)
     return jsonify({"token_usage": token_count})
 
 

docs/Installation/search_engine.md

@@ -1,33 +1,53 @@
-# search Engine setup
+# Search Engine Setup for Devika
 
-To use the search engine capabilities of Devika, you need to set up the search engine API keys. Currently, Devika supports Bing, Google and DuckDuckGo search engines. If you want to use duckduckgo, you don't need to set up any API keys.
+Devika supports three search engines: **Bing**, **Google**, and **DuckDuckGo**. While **DuckDuckGo** does not require any API keys, **Bing** and **Google** do. Follow the steps below to set up the API keys for Bing and Google.
 
-For Bing and Google search engines, you need to set up the API keys. Here's how you can do it:
+## 1. Bing Search API Setup
 
-## Bing Search API
-- Create Azure account. You can create a free account [here](https://azure.microsoft.com/en-us/free/). 
-- Go to the [Bing Search API](https://www.microsoft.com/en-us/bing/apis/bing-web-search-api) website.
-- click on the `Try now` button.
-- Sign in/sign up with your Azure account.
-- Create a new resource group (if you don't have any).
-![alt text](images/bing.png)
-- click on the `Review and create` button.
-- if everything is fine, click on the `Create` button.
+### Step 1: Create an Azure Account
+- Visit the [Azure website](https://azure.microsoft.com/en-us/free/) and create a free account.
+
+### Step 2: Access the Bing Search API
+- Go to the [Bing Search API](https://www.microsoft.com/en-us/bing/apis/bing-web-search-api) page.
+- Click on the `Try now` button.
+- Sign in or sign up using your Azure account.
+
+### Step 3: Create a Resource Group
+- If you don't have a resource group, create one during the setup process.
+
+### Step 4: Create a Bing Search API Resource
+- Fill in the necessary details for your Bing Search API resource.
+- Click on the `Review and create` button.
+- If everything is correct, click on the `Create` button.
+
+### Step 5: Retrieve Your API Keys and Endpoint
 - Once the resource is created, go to the `Keys and Endpoint` tab.
-![alt text](images/bing-1.png)
-- Copy either `Key1` or `Key2` and paste it into the `API_KEYS` field with the name `BING` in the `config.toml` file located in the root directory of Devika, or you can set it via the UI.
+- ![Keys and Endpoint](images/bing-1.png)
+- Copy either `Key1` or `Key2`.
+- Paste the key into the `API_KEYS` field with the name `BING` in the `config.toml` file located in the root directory of Devika, or you can set it via the UI.
 - Copy the `Endpoint` and paste it into the `API_Endpoints` field with the name `BING` in the `config.toml` file located in the root directory of Devika, or you can set it via the UI.
 
+## 2. Google Search API Setup
+
+### Step 1: Create a Google Cloud Project
+- If you don't have one, create a Google Cloud Project via the [Google Cloud Console](https://console.cloud.google.com/).
+
+### Step 2: Enable the Custom Search API
+- Visit the [Google Custom Search API Documentation](https://developers.google.com/custom-search/v1/overview).
+- Click on `Get a Key`.
+- Select your project or create a new one.
+- ![Create Project](images/google.png)
+- This will enable the Custom Search API for your project and generate an API key.
+
+### Step 3: Retrieve Your API Key
+- Copy the API key.
+- Paste it in the `API_KEYS` field with the name `GOOGLE_SEARCH` in the `config.toml` file located in the root directory of Devika, or you can set it via the UI.
+
+### Step 4: Create a Custom Search Engine
+- Go to the [Google Custom Search Engine](https://programmablesearchengine.google.com/controlpanel/all) website.
+- Click on the `Add` button to create a new search engine.
+- ![Create Search Engine](images/google-2.png)
+- After creating the engine, copy the `Search Engine ID`.
+- Paste it in the `API_Endpoints` field with the name `GOOGLE_SEARCH_ENGINE_ID` in the `config.toml` file located in the root directory of Devika, or you can set it via the UI.
+```
 
-## Google Search API
-- if don't have then create GCP account [Google Cloud Console](https://console.cloud.google.com/).
-- visit [Here](https://developers.google.com/custom-search/v1/overview) is the official documentation.
-- click on `Get a Key`.
-- select the project you have or create a new project. click on next.
-![alt text](images/google.png)
-- it enable the Custom Search API for the project and create the API key.
-- Copy the API key and paste it in the API_KEYS field with the name `GOOGLE_SEARCH` in the `config.toml` file in the root directory of Devika or you can set it via UI.
-- for the search engine id, go to the [Google Custom Search Engine](https://programmablesearchengine.google.com/controlpanel/all) website.
-- click on the `Add` button.
-![alt text](images/google-2.png)
-- After creating the engine. Copy the `Search Engine ID` and paste it in the API_Endpoints field with the name `GOOGLE_SEARCH_ENGINE_ID` in the `config.toml` file in the root directory of Devika or you can set it via UI.

docs/architecture/README.md

@@ -12,5 +12,5 @@ Devika's system architecture consists of the following key components:
 8. **Knowledge Base**: Stores and retrieves project-specific information, code snippets, and learned knowledge for efficient access.
 9. **Database**: Persists project data, agent states, and configuration settings.
 
-Read [ARCHITECTURE.md](https://github.com/stitionai/devika/Docs/architecture/ARCHITECTURE.md) for the detailed architecture of Devika.
-Read [UNDER_THE_HOOD.md](https://github.com/stitionai/devika/Docs/architecture/UNDER_THE_HOOD.md) for the detailed working of Devika.
+Read [ARCHITECTURE.md](https://github.com/stitionai/devika/blob/main/docs/architecture/ARCHITECTURE.md) for the detailed architecture of Devika.
+Read [UNDER_THE_HOOD.md](https://github.com/stitionai/devika/blob/main/docs/architecture/UNDER_THE_HOOD.md) for the detailed working of Devika.

get-ollama-models.sh

@@ -0,0 +1,43 @@
+#! /bin/bash
+echo "/usr/local/bin/ollama pull llama3.2"
+echo 
+/usr/local/bin/ollama pull llama3.2
+echo
+echo "/usr/local/bin/ollama pull llama3.1"
+/usr/local/bin/ollama pull llama3.1
+echo
+echo "/usr/local/bin/ollama pull llama3"
+/usr/local/bin/ollama pull llama3
+echo
+echo "/usr/local/bin/ollama pull gemma"
+/usr/local/bin/ollama pull gemma
+echo
+echo "/usr/local/bin/ollama pull qwen"
+/usr/local/bin/ollama pull qwen
+echo
+echo "/usr/local/bin/ollama pull qwen2"
+/usr/local/bin/ollama pull qwen2
+echo
+echo "/usr/local/bin/ollama pull mistral"
+/usr/local/bin/ollama pull mistral
+echo
+echo "/usr/local/bin/ollama pull phi3:14b"
+/usr/local/bin/ollama pull phi3:14b
+echo
+echo "/usr/local/bin/ollama pull phi3:3.8b"
+/usr/local/bin/ollama pull phi3:3.8b
+echo
+echo "/usr/local/bin/ollama pull codellama"
+/usr/local/bin/ollama pull codellama
+echo
+echo "/usr/local/bin/ollama pull qwen2.5"
+/usr/local/bin/ollama pull qwen2.5
+echo
+echo "/usr/local/bin/ollama pull llama2"
+/usr/local/bin/ollama pull llama2
+echo
+echo "/usr/local/bin/ollama pull gemma2"
+/usr/local/bin/ollama pull gemma2
+echo
+echo "/usr/local/bin/ollama pull llama3.1:70b"
+/usr/local/bin/ollama pull llama3.1:70b

requirements.txt

@@ -31,3 +31,5 @@ orjson
 gevent
 gevent-websocket
 curl_cffi
+vite
+shutils