Test and update getting started page (#396)

* Update getting started page * Update getting started page * polishing * polishing * Update getting started and readme.md * Polishing * Update line numbers * Add target blank * Update line numbers * Update chat.png * LFS fix --------- Co-authored-by: Davor Runje <[email protected]> Co-authored-by: Kumaran Rajendhiran <[email protected]>
airtai · Oct 15, 2024 · dd6ed3c · dd6ed3c
1 parent 04a9c90
commit dd6ed3c
Show file tree

Hide file tree

Showing 8 changed files with 58 additions and 44 deletions.
diff --git a/.secrets.baseline b/.secrets.baseline
@@ -139,7 +139,7 @@
         "filename": "docs/docs/en/getting-started/index.md",
         "hashed_secret": "3be2e9dd1980856faddf5bd205e3ff96b24776aa",
         "is_verified": false,
-        "line_number": 420,
+        "line_number": 431,
         "is_secret": false
       }
     ],
@@ -174,5 +174,5 @@
       }
     ]
   },
-  "generated_at": "2024-10-15T12:15:52Z"
+  "generated_at": "2024-10-15T13:23:39Z"
 }
diff --git a/README.md b/README.md
@@ -117,7 +117,7 @@ We will show you how to deploy your workflow using the **FastAPI + Mesop** combi
 To get started, you need to install FastAgency. You can do this using `pip`, Python's package installer. Choose the installation command based on the interface you want to use:
 
 ```console
-pip install "fastagency[autogen,mesop,fastapi]"
+pip install "fastagency[autogen,mesop,fastapi,server]"
 ```
 
 This command installs FastAgency with support for both the Console and Mesop
@@ -326,14 +326,14 @@ app = FastAgency(provider=provider, ui=MesopUI())
 Once everything is set up, you can run your FastAgency application using the following command:
 
 
-In this setup, we need to run two command in separate terminal windows:
+In this setup, we need to run **two** commands in **separate** terminal windows:
 
-#### Terminal 1
+**Terminal 1** - Start **FastAPI** application using uvicorn
 ```
 uvicorn main_1_fastapi:app --host 0.0.0.0 --port 8008 --reload
 ```
 
-#### Terminal 2
+**Terminal 2** - Start **Mesop** web interface using gunicorn
 ```
 gunicorn main_2_mesop:app -b 0.0.0.0:8888 --reload
 ```

diff --git a/docs/docs/en/getting-started/images/chat.png b/docs/docs/en/getting-started/images/chat.png
diff --git a/docs/docs/en/getting-started/index.md b/docs/docs/en/getting-started/index.md
@@ -139,7 +139,7 @@ To get started, you need to install FastAgency. You can do this using `pip`, Pyt
 
 === "FastAPI + Mesop"
     ```console
-    pip install "fastagency[autogen,mesop,fastapi]"
+    pip install "fastagency[autogen,mesop,fastapi,server]"
     ```
 
     This command installs FastAgency with support for both the Console and Mesop
@@ -148,7 +148,7 @@ To get started, you need to install FastAgency. You can do this using `pip`, Pyt
 
 === "NATS + FastAPI + Mesop"
     ```console
-    pip install "fastagency[autogen,mesop,fastapi,nats]"
+    pip install "fastagency[autogen,mesop,fastapi,server,nats]"
     ```
 
     This command installs FastAgency with support for both the Console and Mesop
@@ -172,12 +172,12 @@ To get started, you need to install FastAgency. You can do this using `pip`, Pyt
 
     === "FastAPI + Mesop"
         ```console
-        pip install "fastagency[pyautogen,mesop,fastapi]"
+        pip install "fastagency[pyautogen,mesop,fastapi,server]"
         ```
 
     === "NATS + FastAPI + Mesop"
         ```console
-        pip install "fastagency[pyautogen,mesop,fastapi,nats]"
+        pip install "fastagency[pyautogen,mesop,fastapi,server,nats]"
         ```
 
 ### Imports
@@ -383,53 +383,67 @@ Once everything is set up, you can run your FastAgency application using the fol
 
 === "Mesop"
 
-    !!! note "Terminal"
-        ```
-        fastagency run
-        ```
+    There are two options of running a Mesop application:
 
-    However, the preferred way to run the Mesop application is using a Python WSGI HTTP server like [Gunicorn](https://gunicorn.org/). First,
-    you need to install it using package manager such as `pip` and then run it as follows:
+    1. Using [`fastagency`](../cli/cli/){target="_blank"} command line:
 
-    !!! note "Terminal (alternative)"
-        ```
-        pip install gunicorn
-        gunicorn main:app
-        ```
+        !!! note "Terminal (using [fastagency](../cli/cli/){target="_blank"})"
+            ```
+            fastagency run
+            ```
+
+        !!! danger "Currently not working on **MacOS**"
+            The above command is currently not working on **MacOS**, please use the alternative way of starting the application from below ([#362](https://github.com/airtai/fastagency/issues/362)).
+
+    2. Using [Gunicorn](https://gunicorn.org/){target="_blank"} WSGI HTTP server:
+
+        The preferred way to run the Mesop application is using a Python WSGI HTTP server like [Gunicorn](https://gunicorn.org/){target="_blank"}. First, you need to install it using package manager such as `pip` and then run it as follows:
+
+        !!! note "Terminal (using [Gunicorn](https://gunicorn.org/){target="_blank"})"
+            ```
+            pip install gunicorn
+            gunicorn main:app
+            ```
 
 === "FastAPI + Mesop"
 
-    In this setup, we need to run two command in separate terminal windows:
+    In this setup, we need to run **two** commands in **separate** terminal windows:
 
+    - Start **FastAPI** application using uvicorn:
     !!! note "Terminal 1"
         ```
         uvicorn main_1_fastapi:app --host 0.0.0.0 --port 8008 --reload
         ```
 
+    - Start **Mesop** web interface using gunicorn:
     !!! note "Terminal 2"
         ```
         gunicorn main_2_mesop:app -b 0.0.0.0:8888 --reload
         ```
 
 === "NATS + FastAPI + Mesop"
 
-    In this setup, we need to run four command in separate terminal windows:
+    In this setup, we need to run **four** commands in **separate** terminal windows:
 
+    - Start **NATS** Docker container:
     !!! note "Terminal 1"
         ```
         docker run -d --name nats-fastagency --rm -p 4222:4222 -p 9222:9222 -p 8222:8222 -v $(pwd)/nats-server.conf:/etc/nats/nats-server.conf -e FASTAGENCY_NATS_PASSWORD='fastagency_nats_password' nats:latest -c /etc/nats/nats-server.conf
         ```
 
+    - Start **FastAPI** application that provides a conversational workflow:
     !!! note "Terminal 2"
         ```
         uvicorn main_1_nats:app --reload
         ```
 
+    - Start **FastAPI** application integrated with a **NATS** messaging system:
     !!! note "Terminal 3"
         ```
         uvicorn main_2_fastapi:app --host 0.0.0.0 --port 8008 --reload
         ```
 
+    - Start **Mesop** web interface using gunicorn:
     !!! note "Terminal 4"
         ```
         gunicorn main_3_mesop:app -b 0.0.0.0:8888 --reload

diff --git a/docs/docs/en/user-guide/runtimes/autogen/index.md b/docs/docs/en/user-guide/runtimes/autogen/index.md
@@ -56,21 +56,21 @@ The workflow is registered using **[AutoGenWorkflows](../../../api/fastagency/ru
 In this step, we register the weather API functions to ensure that the weather agent can call the correct functions, such as `get_daily_weather` and `get_daily_weather_weekly_get`, to retrieve the required weather data.
 
 ```python
-{! docs_src/user_guide/runtimes/autogen/main.py [ln:53-66] !}
+{! docs_src/user_guide/runtimes/autogen/main.py [ln:52-65] !}
 ```
 
 #### 6. **Enable Agent Interaction and Chat**
 Here, the user agent initiates a chat with the weather agent, which queries the API and returns the weather information. The conversation is summarized using a method provided by the LLM.
 
 ```python
-{! docs_src/user_guide/runtimes/autogen/main.py [ln:68-75] !}
+{! docs_src/user_guide/runtimes/autogen/main.py [ln:67-74] !}
 ```
 
 #### 7. **Create and Run the Application**
 Finally, we create the FastAgency application and launch it using the console interface.
 
 ```python
-{! docs_src/user_guide/runtimes/autogen/main.py [ln:78] !}
+{! docs_src/user_guide/runtimes/autogen/main.py [ln:77] !}
 ```
 
 ### Complete Application Code

diff --git a/docs/docs/en/user-guide/runtimes/autogen/interactions.md b/docs/docs/en/user-guide/runtimes/autogen/interactions.md
@@ -23,23 +23,23 @@ Let's define three functions which will be available to the agents:
 `TextInput` is suitable for free-form text messages, ideal for open-ended queries and dialogues. This function allows the student to request exam questions from the teacher and provides some suggestions using `TextInput`.
 
 ```python
-{! docs_src/user_guide/custom_user_interactions/main.py [ln:57.5,58.5,59.5,60.5,61.5,62.5,63.5,64.5,65.5,66.5,67.5,68.5,69.5,70.5,71.5,72.5,73.5,74.5,75.5] !}
+{! docs_src/user_guide/custom_user_interactions/main.py [ln:56.5,57.5,58.5,59.5,60.5,61.5,62.5,63.5,64.5,65.5,66.5,67.5,68.5,69.5,70.5,71.5,72.5,73.5] !}
 ```
 
 ### System Info Messages
 
 `SystemMessage` is used for operational or system-related instructions, such as logging data, and is not part of the agent dialogue. This function logs the final answers after the student completes the discussion using `SystemMessage` to log the event.
 
 ```python
-{! docs_src/user_guide/custom_user_interactions/main.py [ln:77.5,78.5,79.5,80.5,81.5,82.5,83.5,84.5,85.5,86.5,87.5,88.5,89.5,90.5] !}
+{! docs_src/user_guide/custom_user_interactions/main.py [ln:75.5,76.5,77.5,78.5,79.5,80.5,81.5,82.5,83.5,84.5,85.5,86.5,87.5] !}
 ```
 
 ### Multiple Choice
 
 `MultipleChoice` is used for structured responses where the user must select one of several predefined options. This function retrieves the final grade for the student's submitted answers using `MultipleChoice`, presenting the user with grading options.
 
 ```python
-{! docs_src/user_guide/custom_user_interactions/main.py [ln:92.5,93.5,94.5,95.5,96.5,97.5,98.5,99.5,100.5,101.5,102.5,103.5,104.5] !}
+{! docs_src/user_guide/custom_user_interactions/main.py [ln:89.5,90.5,91.5,92.5,93.5,94.5,95.5,96.5,97.5,98.5,99.5,100.5] !}
 ```
 
 ### Other Types of Messages
@@ -50,7 +50,7 @@ All supported messages are subclasses of the [IOMessage](../../../../api/fastage
 We now register these functions with the workflow, linking the `student_agent` as the caller and the `teacher_agent` as the executor.
 
 ```python
-{! docs_src/user_guide/custom_user_interactions/main.py [ln:106.5,107.5,108.5,109.5,110.5,111.5,112.5,113.5,114.5,115.5,116.5,117.5,118.5,119.5,120.5,121.5,122.5,123.5,124.5,125.5,126.5,127.5,128.5] !}
+{! docs_src/user_guide/custom_user_interactions/main.py [ln:102.5,103.5,104.5,105.5,106.5,107.5,108.5,109.5,110.5,111.5,112.5,113.5,114.5,115.5,116.5,117.5,118.5,119.5,120.5,121.5,122.5,123.5,124.5] !}
 ```
 
 ## Complete Application Code

diff --git a/docs/docs/en/user-guide/runtimes/autogen/websurfer.md b/docs/docs/en/user-guide/runtimes/autogen/websurfer.md
@@ -62,7 +62,7 @@ Here, the large language model is configured to use the `gpt-4o` model, and the
 
     - **WebSurferAgent**: This agent functions as a web surfer, with built-in capability to browse the web and fetch real-time data as required.
 
-    ```python hl_lines="24"
+    ```python hl_lines="18-25"
     {!> docs_src/user_guide/runtimes/autogen/websurfer.py [ln:20-45] !}
     ```
 
@@ -80,14 +80,14 @@ Here, the large language model is configured to use the `gpt-4o` model, and the
 
     - **WebSurferTool**: The tool that gives the ConversableAgent the ability to browse the web after it has been registered.
 
-    ```python
-    {!> docs_src/user_guide/runtimes/autogen/websurfer_tool.py [ln:21-54] !}
+    ```python hl_lines="27-31"
+    {!> docs_src/user_guide/runtimes/autogen/websurfer_tool.py [ln:21-52] !}
     ```
 
     Now, we need to register the WebSurferAgent with a caller and executor. This setup allows the caller to use the WebSurferAgent for performing real-time web interactions.
 
     ```python  hl_lines="2 3"
-    {!> docs_src/user_guide/runtimes/autogen/websurfer_tool.py [ln:55-58] !}
+    {!> docs_src/user_guide/runtimes/autogen/websurfer_tool.py [ln:54-58] !}
     ```
 
     The `executor` can be either a single instance of `ConversableAgent` or a `list of ConversableAgent` instances.
@@ -100,7 +100,7 @@ Here, the user agent starts a conversation with the websurfer agent, which perfo
 === "Using WebSurferAgent"
 
     ```python
-    {! docs_src/user_guide/runtimes/autogen/websurfer.py [ln:46-54] !}
+    {! docs_src/user_guide/runtimes/autogen/websurfer.py [ln:46-53] !}
     ```
 
 === "Enhancing an existing agent"
@@ -113,7 +113,7 @@ Here, the user agent starts a conversation with the websurfer agent, which perfo
 Finally, we create the FastAgency application and launch it using the console interface.
 
 ```python
-{! docs_src/user_guide/runtimes/autogen/websurfer.py [ln:57] !}
+{! docs_src/user_guide/runtimes/autogen/websurfer.py [ln:56] !}
 ```
 
 ### Complete Application Code

diff --git a/pyproject.toml b/pyproject.toml
@@ -88,13 +88,13 @@ nats = [
     "faststream[nats]>=0.5.27,<0.6",
 ]
 
-submodules = [
-    "fastagency[mesop,autogen,openapi,fastapi,nats]"
+server = [
+    "uvicorn>=0.31.0",
+    "gunicorn>=23.0.0",
 ]
 
-server = [
-    "uvicorn==0.31.0",
-    "gunicorn==23.0.0",
+submodules = [
+    "fastagency[mesop,autogen,openapi,fastapi,nats,server]"
 ]
 
 # dev dependencies
@@ -151,7 +151,7 @@ testing = [
 ]
 
 dev = [
-    "fastagency[submodules,server,lint,testing,devdocs]",
+    "fastagency[submodules,lint,testing,devdocs]",
     "pre-commit==4.0.1",
     "detect-secrets==1.5.0",
 ]