From 61e187b10c2c8765e2c4cbd43bbf9ceb264cb8d8 Mon Sep 17 00:00:00 2001 From: Nick Bobrowski <39348559+bonk1t@users.noreply.github.com> Date: Sat, 30 Nov 2024 15:08:48 +0000 Subject: [PATCH] Fix broken-links and typos --- .../deployment-to-production.mdx | 2 +- docs_new/core-framework/agencies.mdx | 2 +- docs_new/core-framework/agents.mdx | 6 ++--- docs_new/core-framework/state-management.mdx | 2 +- .../tools/advanced-tool-features.mdx | 4 +-- docs_new/tutorials/tutorials.mdx | 2 +- .../welcome/ai-agency-vs-other-frameworks.mdx | 4 +-- .../welcome/getting-started/cursor-ide.mdx | 25 +++++++++---------- .../getting-started/genesis-agency.mdx | 4 +-- docs_new/welcome/installation.mdx | 2 +- 10 files changed, 26 insertions(+), 27 deletions(-) diff --git a/docs_new/additional-features/deployment-to-production.mdx b/docs_new/additional-features/deployment-to-production.mdx index b8aafbb8..d4583f70 100644 --- a/docs_new/additional-features/deployment-to-production.mdx +++ b/docs_new/additional-features/deployment-to-production.mdx @@ -108,7 +108,7 @@ Find more detailed instructions in the video below: -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. +Alternatively, you can deploy your tools as separate API endpoints (e.g., serverless functions) and integrate them into your agents using [OpenAPI schemas](/additional-features/openapi-schemas). This method is ideal if you plan to reuse tools across different agents or services. 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. diff --git a/docs_new/core-framework/agencies.mdx b/docs_new/core-framework/agencies.mdx index 6921794d..73c9fb7d 100644 --- a/docs_new/core-framework/agencies.mdx +++ b/docs_new/core-framework/agencies.mdx @@ -54,7 +54,7 @@ Utilizing an Agency instead of individual agents offers several advantages: In Agency Swarm, communication flows are **user-defined** and **highly flexible**. They are set up in the agency chart as a directed graph, allowing permissions to initiate communication to flow from left to right. -Communication flows are defined when creating the agency, specifying which agents can communicate with each other. More information on advanced communication flows can be found on the [Custom Communication Flows](/advanced-features/custom-communication-flows/overview) page. +Communication flows are defined when creating the agency, specifying which agents can communicate with each other. More information on advanced communication flows can be found on the [Custom Communication Flows](/additional-features/custom-communication-flows/overview) page. ## Creating an Agency diff --git a/docs_new/core-framework/agents.mdx b/docs_new/core-framework/agents.mdx index 38777aca..cadf279f 100644 --- a/docs_new/core-framework/agents.mdx +++ b/docs_new/core-framework/agents.mdx @@ -170,7 +170,7 @@ agent = Agent(name='MyAgent', model='gpt-4o-mini-model-name') -**Note**: For more information on using OpenAPI schemas to create tools for your agents, see the [OpenAPI Schemas](/advanced-features/openapi-schemas) page. +**Note**: For more information on using OpenAPI schemas to create tools for your agents, see the [OpenAPI Schemas](/additional-features/openapi-schemas) page. @@ -194,7 +194,7 @@ To check available agents, simply run the command without any arguments. ## Response Validator -See the [Output Validation](/advanced-features/output-validation) page for more information on how to use response validators to validate the response before sending it to the user or another agent. +See the [Output Validation](/additional-features/output-validation) page for more information on how to use response validators to validate the response before sending it to the user or another agent. ## Agent Template Using the CLI @@ -230,7 +230,7 @@ Running the command generates the following folder structure: **Explanation:** - **files**: Store files to be uploaded to OpenAI. Acceptable formats are listed in [File Search](https://platform.openai.com/docs/assistants/tools/file-search#supported-files) and [Code Interpreter](https://platform.openai.com/docs/assistants/tools/code-interpreter#supported-files). Uploaded files receive an ID to prevent re-uploading. -- **schemas**: Store OpenAPI schemas to be automatically converted into tools. Place the schema in this folder and specify it when initializing your agent. [Read more](/advanced-features/openapi-schemas). +- **schemas**: Store OpenAPI schemas to be automatically converted into tools. Place the schema in this folder and specify it when initializing your agent. [Read more](/additional-features/openapi-schemas). - **tools**: Store tools as Python files. Each file must have the same name as the tool class (e.g., `ExampleTool.py` must contain a class called `ExampleTool`). [Read more](./tools). diff --git a/docs_new/core-framework/state-management.mdx b/docs_new/core-framework/state-management.mdx index a1000ade..54d189aa 100644 --- a/docs_new/core-framework/state-management.mdx +++ b/docs_new/core-framework/state-management.mdx @@ -44,7 +44,7 @@ Example usage: - Set shared state within a tool: `self._shared_state.set("key", value)` - Retrieve shared state in another tool: `value = self._shared_state.get("key")` -See more in [Shared State](/advanced-features/shared-state). +See more in [Shared State](/additional-features/shared-state). ## Persistence Between Restarts diff --git a/docs_new/core-framework/tools/advanced-tool-features.mdx b/docs_new/core-framework/tools/advanced-tool-features.mdx index 1d479859..3684d7de 100644 --- a/docs_new/core-framework/tools/advanced-tool-features.mdx +++ b/docs_new/core-framework/tools/advanced-tool-features.mdx @@ -11,7 +11,7 @@ Ensuring the reliability of agent outputs is critical, especially in production - **Tool Input/Output Validation:** Tools validate data before and after execution to reduce runtime errors through Pydantic integration. - **Custom Validators:** Implement custom validation logic within tools using field validators and model validators. -See the [Output Validation](/advanced-features/output-validation) page for more information on how to use validators for tools. +See the [Output Validation](/additional-features/output-validation) page for more information on how to use validators for tools. ### Tool Error Handling @@ -99,7 +99,7 @@ self._shared_state.set("key", value) value = self._shared_state.get("key") ``` -See more in [Shared State](advanced-features/shared-state). +See more in [Shared State](additional-features/shared-state). ## Method Composition diff --git a/docs_new/tutorials/tutorials.mdx b/docs_new/tutorials/tutorials.mdx index 9d6679b3..e0a1acf3 100644 --- a/docs_new/tutorials/tutorials.mdx +++ b/docs_new/tutorials/tutorials.mdx @@ -111,4 +111,4 @@ icon: "play" ## Next Steps - **[API Reference](/api)** -- **[Advanced Topics](/advanced-features)** +- **[Advanced Topics](/additional-features)** diff --git a/docs_new/welcome/ai-agency-vs-other-frameworks.mdx b/docs_new/welcome/ai-agency-vs-other-frameworks.mdx index 398be0fb..60980822 100644 --- a/docs_new/welcome/ai-agency-vs-other-frameworks.mdx +++ b/docs_new/welcome/ai-agency-vs-other-frameworks.mdx @@ -29,9 +29,9 @@ Unlike other frameworks, Agency Swarm takes a unique approach with three key dif | **Design & Architecture** | - Modular, production-focused
- Flexible agent structure via agency chart
- Built for real business needs | - Event-driven, scalable
- Asynchronous message passing
- Supports distributed computing | - Flexible agent organization into crews
- Agents with rich attributes | | **Key Entities** | - Agents
- Tools
- Agencies | - ConversableAgent
- AssistantAgent
- UserProxyAgent | - Agents
- Tasks
- Crews | | **Prompt Flexibility** | - Full control over prompts
- No predefined prompts
- Does not write prompts for you | - Flexible prompt engineering
- Supports few-shot learning | - Extensive prompt customization | -| **Type Safety** | - Input validation with Pydantic
- Custom response validators
- Prevents hallucinations with automatic type checking and error correction | - Robust error handling
- Code execution validation
- Self-correction by agents | - No built-in type checking or error correction
- Built on Langchain | +| **Type Safety** | - Input validation with Pydantic
- Custom response validators
- Prevents hallucinations with automatic type checking and error correction | - Robust error handling
- Code execution validation
- Self-correction by agents | - No built-in type checking or error correction
- Built on LangChain | | **Communication Control** | - Enables easy definition of communication flows
- Agents determine communication based on their descriptions
- Uses specialized `SendMessage` tool | - Uses extra model call for "role play" to determine next speaker
- Recently added support for hardcoded conditions | - Uses "process" concept for communication flow
- Delegation control via agent attributes | -| **Integration with Modern Models** | - Built for modern function-calling models
- Direct integration with OpenAI Assistants API | - Supports various interaction patterns
- Event-driven architecture facilitates this | - Built on Langchain | +| **Integration with Modern Models** | - Built for modern function-calling models
- Direct integration with OpenAI Assistants API | - Supports various interaction patterns
- Event-driven architecture facilitates this | - Built on LangChain | | **State Management** | - Shared state among agents and tools
- Conversation context via OpenAI API | - Conversation history maintenance
- Dynamic context truncation | - Three-tier memory system
- Context sharing among agents and tasks | | **Production Readiness** | - Designed for production environments
- Business-oriented design
- Robust validation and error correction | - Scalable and distributed
- Active development towards production features | - Requires additional development for production
- Scalability testing needed | | **Task Delegation** | - Agent autonomy in task delegation
- Hierarchical delegation via agency chart | - Automated task coordination
- Function calls for delegation | - Autonomous delegation based on capabilities
- Hand-off mechanisms with context preservation | diff --git a/docs_new/welcome/getting-started/cursor-ide.mdx b/docs_new/welcome/getting-started/cursor-ide.mdx index 591eded5..c50e5fa1 100644 --- a/docs_new/welcome/getting-started/cursor-ide.mdx +++ b/docs_new/welcome/getting-started/cursor-ide.mdx @@ -56,32 +56,32 @@ Follow these steps to create your first Agency using Cursor: Spend as much time as possible on your first prompt. This will save you a lot of time later. Make sure to include: - All agents that you want to create - - All tools and APIs that the agents must use. - - Communication flows between your agents. + - All tools and APIs that the agents must use + - Communication flows between your agents - + Sometimes Cursor forgets certain files or hallucinates the agency structure. Make sure to verify that: - - All import statements are correct. - - `requirements.txt` file exists. - - `agency.py` file executes properly. + - All import statements are correct + - `requirements.txt` file exists + - `agency.py` file executes properly If any of these are missing or not working, instruct composer to create them or fix the code. - Run each tool file to make sure they work as expected. You will see the test cases that Cursor created at the bottom in `if __name__ == "__main__"` statements. + Run each tool file to make sure they work as expected. You will see the test cases that Cursor created at the bottom in `if __name__ == "__main__"` statements. - If any of the tools are not working, send the error message to composer and ask it to fix the code. - - If you want to adjust the functionality of the tool, either use inline editing `CMD+K` (macOS) or `Ctrl+K` (Windows/Linux) or send another message to composer. - - If you are stuck, use Chat `CMD+L` (macOS) or `Ctrl+L` (Windows/Linux) to ask questions and brain storm alternative approaches. For example, ask "What other APIs can I use for this tool?" - + - If you want to adjust the functionality of the tool, either use inline editing `Cmd+K` (macOS) or `Ctrl+K` (Windows/Linux) or send another message to composer. + - If you are stuck, use Chat `Cmd+L` (macOS) or `Ctrl+L` (Windows/Linux) to ask questions and brainstorm alternative approaches. For example, ask "What other APIs can I use for this tool?" + Verify the agent instructions and parameters are correct after adjustments. **Actually think about instructions.** - Use Chat or Inline Editing to adjust the `instruction.md` files to your needs. - Edit instructions manually and remove all boilerplate text. - - Make sure each agent has access to all the new tools either by speciying `tools_folder` path or adding them in `tools` parameter. + - Make sure each agent has access to all the new tools either by specifying `tools_folder` path or adding them in `tools` parameter. @@ -92,7 +92,7 @@ Follow these steps to create your first Agency using Cursor: - Iterate on your agency by repeating the process until you are satisfied with the results. + Iterate on your agency by repeating the process until you are satisfied with the results. **Agent Development is an Iterative Process** @@ -108,4 +108,3 @@ Follow these steps to create your first Agency using Cursor: - Learn the core concepts of Tools, Agents, and Agencies. - Watch the [Deployment Tutorial](https://www.youtube.com/watch?v=53_e3lmk6Mo). - diff --git a/docs_new/welcome/getting-started/genesis-agency.mdx b/docs_new/welcome/getting-started/genesis-agency.mdx index dd4e876d..4e87c818 100644 --- a/docs_new/welcome/getting-started/genesis-agency.mdx +++ b/docs_new/welcome/getting-started/genesis-agency.mdx @@ -40,7 +40,7 @@ Genesis Agency is a special Agency within the framework that helps you to create After executing the `genesis` command, specialized agents such as `GenesisCEO` and `ToolCreator` will begin constructing your agency's structure and developing the required tools. - + Once Genesis has created your agents, you'll find all the agent folders in the directory where you ran the `genesis` command. Fine-tune the agents and tools as needed by following these steps: 1. **Adjust Tools**: Modify the tools in each agent's `tools` directory to meet your requirements. @@ -58,5 +58,5 @@ Genesis Agency is a special Agency within the framework that helps you to create ## Next Steps -- Learn the core concepts of Tools, Agents, and Agencies. +- Learn the core concepts of [Tools](/core-framework/tools), [Agents](/core-framework/agents), and [Agencies](/core-framework/agencies). - Watch the [Deployment Tutorial](https://www.youtube.com/watch?v=53_e3lmk6Mo). diff --git a/docs_new/welcome/installation.mdx b/docs_new/welcome/installation.mdx index bf0045af..bfe87931 100644 --- a/docs_new/welcome/installation.mdx +++ b/docs_new/welcome/installation.mdx @@ -57,7 +57,7 @@ When it comes to building your first AI Agency, you have three options: fully customized solution. - Let Genesis Agency to create your agents for you. Best for simple use cases or for creating your initial agency + Let Genesis Agency create your agents for you. Best for simple use cases or for creating your initial agency structure quickly.