touch ups to docker setup

README.md

@@ -213,32 +213,86 @@ For more detailed installation steps along with the reasons for doing each pleas
 Finally, for use of SalesGPT create an `.env` file just as our `.env.example` and put your API keys there by specifying a new line just as we have done.
 
 ## Run an Example AI Sales agent
-If you used a local installation of SalesGPT skip the next two steps and directly run either script: 
-
-`git clone https://github.com/filip-michalsky/SalesGPT.git`
+Navigate into the SalesGPT directory: 
 
 `cd SalesGPT`
 
-### Docker utilization 
-If you have Docker installed or would prefer to use Docker, follow these simple steps:
-Before proceeding with the Docker steps, ensure you have Docker installed on your system. If not, please follow the installation instructions on the [official Docker website](https://docs.docker.com/get-docker/).
+SalesGPT can be run in various ways, tailored to your preferences and setup. Below are the methods available:
+
+### 1. Using Docker
+For those who prefer containerization, Docker offers an isolated and consistent environment. Ensure Docker is installed on your system by following the [official Docker installation guide](https://docs.docker.com/get-docker/).
+
+To run SalesGPT with Docker, execute the following steps:
+
+1. **Start the Application with Docker Compose:**
+
+   Use the command below to start SalesGPT in detached mode:
+   ```
+   docker-compose up -d
+   ```
+   If you've made changes and want them to reflect, append `--build` to the command above.
+
+2. **Stopping the Application:**
+
+   To stop and remove all running containers related to SalesGPT, execute:
+   ```
+   docker-compose down
+   ```
+
+**Troubleshooting:**
+
+- **Clean Up Docker Resources:** If you encounter errors, you can clean up Docker by removing all unused containers, networks, images, and volumes with caution:
+  ```
+  docker system prune --volumes
+  ```
+- **Rebuild Without Cache:** To rebuild and start the services afresh without using cache, run:
+  ```
+  docker-compose up -d --build --no-cache
+  ```
+
+After successful setup, access SalesGPT at [localhost:3000/chat](http://localhost:3000/chat) in your browser.
+
+### 2. Direct User Interface Launch
+If Docker is not part of your workflow, you can directly launch the SalesGPT user interface. Please refer to the `README.md` file in the frontend directory for instructions on setting up the UI locally.
+
+### 3. Using the Terminal
+For terminal enthusiasts or automation scripts, run SalesGPT with the following command:
+`python run.py --verbose True --config examples/example_agent_setup.json`
+
+### 4. 
+### 4. Running Only the Backend
+For those who wish to integrate SalesGPT's backend with their own user interface or application, running only the backend is a straightforward process. This allows you to leverage the powerful features of SalesGPT while maintaining full control over the user experience.
+
+To run only the backend of SalesGPT, follow these steps:
+1. **Start the Backend Service:**
+
+   Use the following command to start the backend service. This will initiate the server on port 8000 by default, making the API accessible:
+   ```
+   docker-compose up -d backend
+   ```
+
+   If you need to rebuild the backend image, perhaps after making changes, you can add `--build` to the command above.
+
+2. **Accessing the Backend:**
 
-1. Clone the SalesGPT Github repository:
+   With the backend running, you can access the API endpoints at `http://localhost:8000`. Refer to the API documentation for details on available endpoints and their usage.
 
-   `git clone https://github.com/filip-michalsky/SalesGPT.git`
+3. **Stopping the Backend:**
 
-2. Navigate to the SalesGPT directory:
+   To stop the backend service, execute:
+   ```
+   docker-compose stop backend
+   ```
 
-   `cd SalesGPT`
+   If you wish to remove the backend container entirely, use:
+   ```
+   docker-compose down
+   ```
 
-3. Run the application using Docker Compose:
+This setup is ideal for developers looking to integrate SalesGPT's backend into custom applications or those who prefer to use a different frontend technology.
 
-   `docker-compose up`
 
-This will build and start the necessary Docker containers for SalesGPT. You can then access the application by opening the following link in any of your browsers: [localhost:3000/chat](http://localhost:3000/chat)
 
-### Direct user interface launch
-If you do not have Docker installed please use the README.md file in the frontend directory to launch the user interface.
 
 ## Test your setup
 

requirements-dev.txt

@@ -0,0 +1,4 @@
+-r requirements.txt
+pytest>=7.4.3
+pytest-cov>=4.1.0
+pytest-asyncio>=0.23.1

requirements.txt

@@ -5,8 +5,4 @@ tiktoken>=0.5.2
 pydantic>=2.5.2
 litellm>=1.10.2
 ipykernel>=6.27.1
-pytest>=7.4.3
-pytest-cov>=4.1.0
-pytest-asyncio>=0.23.1
-langchain-openai==0.0.2
-
+langchain-openai==0.0.2