Minor fixes: Fix links, icons, reduce duplication, formatting fixes

docs_new/advanced-features/azure-openai.mdx

@@ -58,6 +58,7 @@ ceo = Agent(
     model="azure-model-deployment-name"
 )
 ```
+
 </Step>
 
 <Step title="Run Your Agency">

docs_new/advanced-features/custom-communication-flows/common-use-cases.mdx

@@ -120,7 +120,8 @@ class SendMessageAPI(SendMessage):
 This is very powerful, as you can even allow your agents to collaborate with agents outside your system. More on this is coming soon!
 
 <Tip title="Contributing">
-If you have any ideas for new communication flows, please either adjust this page in docs, or add your new send message tool in the `agency_swarm/tools/send_message` folder and open a PR!
+  If you have any ideas for new communication flows, please either adjust this page in docs, or add your new send
+  message tool in the `agency_swarm/tools/send_message` folder and open a PR!
 </Tip>
 
 **After implementing your own `SendMessage` tool**, simply pass it into the `send_message_tool_class` parameter when initializing the `Agency` class:

docs_new/advanced-features/deployment-to-production.mdx

@@ -91,13 +91,13 @@ Simplify deployment by deploying your agents and tools together using our ready-
 Leverage our Railway deployment template to quickly deploy your agency as a web service. Railway is a platform that simplifies deploying applications without the overhead of managing servers.
 
 <Card
-    title="API Railway Template"
-    color="#F3A78B"
-    href="https://github.com/VRSEN/agency-swarm-api-railway-template"
-    icon="train"
-    iconType="duotone"
+  title="API Railway Template"
+  color="#F3A78B"
+  href="https://github.com/VRSEN/agency-swarm-api-railway-template"
+  icon="train"
+  iconType="duotone"
 >
-    Click here to access the template and follow the instructions to get your agency deployed.
+  Click here to access the template and follow the instructions to get your agency deployed.
 </Card>
 
 Find more detailed instructions in the video below:
@@ -108,12 +108,13 @@ Find more detailed instructions in the video below:
 
 <Accordion title="Option 2: Deploy Tools as Separate API Endpoints" defaultOpen={false}>
 
-Alternatively, you can deploy your tools as separate API endpoints (e.g., serverless functions) and integrate them into your agents using [OpenAPI schemas](/advanced-features/openapi-schemas). This approach allows for greater scalability and modularity, especially if you plan to reuse tools across different agents or services.
+Alternatively, you can deploy your tools as separate API endpoints (e.g., serverless functions) and integrate them into your agents using [OpenAPI schemas](/advanced-features/openapi-schemas). This method is ideal if you plan to reuse tools across different agents or services.
 
-Deploying tools separately allows for greater flexibility and scalability. You can deploy individual tools as serverless functions on platforms like AWS Lambda, Google Cloud Functions, or Azure Functions. This approach provides on-demand scalability and cost efficiency. Alternatively, you can host your tools as custom API endpoints using frameworks like FastAPI or Flask and deploy them on platforms such as Heroku, DigitalOcean, Railway, or your own servers.
+Deploying tools separately provides flexibility and scalability. You can deploy individual tools as serverless functions on platforms like AWS Lambda, Google Cloud Functions, or Azure Functions. This ensures on-demand scaling and cost efficiency. Alternatively, you can host your tools as custom API endpoints using frameworks like FastAPI or Flask and deploy them on platforms such as Heroku, DigitalOcean, Railway, or your own servers.
 
 <Note>
-When deploying tools separately, ensure proper authentication and secure communication between your agents and the tool APIs.
+  When deploying tools separately, ensure proper authentication and secure communication between your agents and the
+  tool APIs.
 </Note>
 
 </Accordion>

docs_new/advanced-features/few-shot-examples.mdx

@@ -59,6 +59,7 @@ You can add few-shot examples to your agent either during initialization or afte
     ```
 
     </Tab>
+
 </Tabs>
 
 ## Crafting Effective Examples

docs_new/advanced-features/open-source-models.mdx

@@ -10,20 +10,27 @@ While OpenAI is generally recommended, there are situations where you might pref
 
 <CardGroup>
 
-<Card title="Astra Assistants API" icon="rocket" iconType="solid" href="https://github.com/datastax/astra-assistants-api">
-The best and the easiest option for running Open Source models. Supports Assistants API V2. See example [notebook](https://github.com/VRSEN/agency-swarm/blob/main/notebooks/os_models_with_astra_assistants_api.ipynb).
+<Card
+  title="Astra Assistants API"
+  icon="rocket"
+  iconType="solid"
+  href="https://github.com/datastax/astra-assistants-api"
+>
+  The best and the easiest option for running Open Source models. Supports Assistants API V2. See example
+  [notebook](https://github.com/VRSEN/agency-swarm/blob/main/notebooks/os_models_with_astra_assistants_api.ipynb).
 </Card>
 
 <Card title="Open Assistant API" icon="users" iconType="solid" href="https://github.com/MLT-OSS/open-assistant-api">
-Fully local, stable, and tested, but only supports Assistants V1. See example [here](https://github.com/VRSEN/agency-swarm-lab/tree/main/OpenSourceSwarm).
+  Fully local, stable, and tested, but only supports Assistants V1. See example
+  [here](https://github.com/VRSEN/agency-swarm-lab/tree/main/OpenSourceSwarm).
 </Card>
 
 <Card title="OpenOpenAI" icon="code" iconType="solid" href="https://github.com/transitive-bullshit/OpenOpenAI">
-Unverified.
+  Unverified.
 </Card>
 
 <Card title="LiteLLM" icon="code" iconType="solid" href="https://github.com/BerriAI/litellm/issues/2842">
-Assistants API Proxy in development.
+  Assistants API Proxy in development.
 </Card>
 
 </CardGroup>
@@ -33,8 +40,9 @@ Assistants API Proxy in development.
 <Steps>
 
 <Step title="1. Create an account on Astra Assistants API and obtain an API key." icon="user">
-Open the [Astra Assistants API](https://astra.datastax.com/signup) and create an account. Once you have an account, you can obtain an API key by clicking on the "Generate Token" button.
-![Astra Assistants API Example](https://firebasestorage.googleapis.com/v0/b/vrsen-ai/o/public%2Fgithub%2FScreenshot%202024-07-01%20at%208.19.00%E2%80%AFAM.png?alt=media&token=b4f1a7ad-3b77-40fa-a5da-866a4f1410bd)
+  Open the [Astra Assistants API](https://astra.datastax.com/signup) and create an account. Once you have an account,
+  you can obtain an API key by clicking on the "Generate Token" button. ![Astra Assistants API
+  Example](https://firebasestorage.googleapis.com/v0/b/vrsen-ai/o/public%2Fgithub%2FScreenshot%202024-07-01%20at%208.19.00%E2%80%AFAM.png?alt=media&token=b4f1a7ad-3b77-40fa-a5da-866a4f1410bd)
 </Step>
 
 <Step title="2. Add Astra DB Token to your .env file:" icon="file">
@@ -43,6 +51,7 @@ Copy the token from the file that starts with "AstraCS:" and paste it into your
 ```env
 ASTRA_DB_APPLICATION_TOKEN=AstraCS:dsfkgn...
 ```
+
 </Step>
 
 <Step title="3. Add other model provider API keys to .env as well:" icon="key">
@@ -60,7 +69,7 @@ pip install astra-assistants-api gradio
 ```
 </Step>
 
-<Step title="5. Patch the OpenAI client:" icon="cogs">
+<Step title="5. Patch the OpenAI client:" icon="code">
 ```python
 from openai import OpenAI
 from astra_assistants import patch
@@ -92,6 +101,7 @@ ceo = Agent(
     files_folder="path/to/your/files"
 )
 ```
+
 </Step>
 
 <Step title="7. Create an agency:" icon="people-arrows">
@@ -102,6 +112,7 @@ from agency_swarm import Agency
 
 agency = Agency([ceo])
 ```
+
 </Step>
 
 <Step title="8. Start Gradio:" icon="play">
@@ -115,6 +126,7 @@ agency = Agency([ceo])
 
 demo_gradio(agency)
 ```
+
 </Step>
 
 </Steps>
@@ -127,24 +139,24 @@ To use agency-swarm with any other projects that mimic the Assistants API, gener
 
 <Steps>
 
-<Step title="1. Install the previous version of agency-swarm as most projects are not yet compatible with streaming and Assistants V2:" icon="download">
+<Step title="Install the previous version of agency-swarm as most projects are not yet compatible with streaming and Assistants V2:">
 ```bash
 pip install agency-swarm==0.1.7
 ```
 </Step>
 
-<Step title="2. Switch out the OpenAI client:" icon="cogs">
+<Step title="Switch out the OpenAI client:">
 ```python
 import openai
 from agency_swarm import set_openai_client
 
-client = openai.OpenAI(api_key="whatever", base_url="http://127.0.0.1:8000/")
+client = openai.OpenAI(api_key="your-api-key", base_url="http://127.0.0.1:8000/")
 
 set_openai_client(client)
 ```
 </Step>
 
-<Step title="3. Set the model parameter:" icon="user">
+<Step title="Set the model parameter:">
 ```python
 from agency_swarm import Agent
 
@@ -154,9 +166,10 @@ ceo = Agent(
     model='ollama/llama3'
 )
 ```
+
 </Step>
 
-<Step title="4. Start Gradio:" icon="play">
+<Step title="Start Gradio:">
 To utilize your agency in Gradio, apply a specific non-streaming `demo_gradio` method from the [agency-swarm-lab](https://github.com/VRSEN/agency-swarm-lab/blob/main/OpenSourceSwarm/demo_gradio.py) repository:
 
 ```python
@@ -167,9 +180,10 @@ agency = Agency([ceo])
 
 demo_gradio(agency)
 ```
+
 </Step>
 
-<Step title="5. For backend integrations, simply use:" icon="code">
+<Step title="For backend integrations, simply use:">
 ```python
 agency.get_completion("I am the CEO")
 ```

docs_new/advanced-features/streaming.mdx

@@ -11,7 +11,9 @@ Agency Swarm supports streaming responses from language models, providing real-t
 To stream the conversation between agents, you can use the `get_completion_stream` method with your event handler. The process follows a similar pattern to the [official OpenAI documentation](https://platform.openai.com/docs/api-reference/assistants-streaming).
 
 <Note>
-The main difference is that you must extend the `AgencyEventHandler` class, which provides two additional properties: `agent_name` and `recipient_agent_name`. These help identify the agents communicating with each other (see the `on_text_created` method below).
+  The main difference is that you must extend the `AgencyEventHandler` class, which provides two additional properties:
+  `agent_name` and `recipient_agent_name`. These help identify the agents communicating with each other (see the
+  `on_text_created` method below).
 </Note>
 
 ```python
@@ -49,5 +51,7 @@ response = agency.get_completion_stream("I want you to build me a website", even
 ```
 
 <Note>
-The `on_all_streams_end` class method is called when all streams have ended. This is particularly important since your event handler might be called multiple times and possibly by multiple agents, unlike in the official OpenAI documentation.
+  The `on_all_streams_end` class method is called when all streams have ended. This is particularly important since your
+  event handler might be called multiple times and possibly by multiple agents, unlike in the official OpenAI
+  documentation.
 </Note>

docs_new/api.mdx

@@ -155,7 +155,6 @@ def demo_gradio(self, height: int = 450, dark_mode: bool = True, **kwargs):
 
 </CodeGroup>
 
-
 ## Agent Class
 
 The Agent class is the core component of Agency Swarm that represents an AI assistant. Each agent has specific capabilities, tools, and can process files and instructions.
@@ -235,7 +234,6 @@ def add_shared_instructions(self, instructions: str):
 
 </CodeGroup>
 
-
 ## BaseTool Class
 
 The base class for creating custom tools that agents can use. Tools allow agents to perform specific actions or access external functionality.