# Neuron ## Neuron - v1 - [Introduction](https://docs.neuron-ai.dev/v1/getting-started/readme.md): Learn what NeuronAI is and what you can do with it. - [Fast Learning by Video](https://docs.neuron-ai.dev/v1/getting-started/fast-learning-by-video.md): Position yourself in the AI Agent era with our extensive tutorials and technical insights into NeuronAI capabilities. Learn from practical examples and real-world use cases. - [Getting Started](https://docs.neuron-ai.dev/v1/getting-started/getting-started.md): Step by step instructions on how to install NeuronAI in your application and create an Agent. - [Agent](https://docs.neuron-ai.dev/v1/getting-started/agent.md): Easily implement LLM interactions extending the basic Agent class. - [Tools](https://docs.neuron-ai.dev/v1/getting-started/tools.md): Give Agents the ability to interact with your application context and services. - [Streaming](https://docs.neuron-ai.dev/v1/getting-started/streaming.md): Presenting AI response to your user in real-time. - [Structured Output](https://docs.neuron-ai.dev/v1/getting-started/structured-output.md): Enforce the Agent output based on the provided schema. - [Attachments (Documents & Images)](https://docs.neuron-ai.dev/v1/getting-started/attachments-documents-and-images.md): Attach documents and images to your message. - [RAG](https://docs.neuron-ai.dev/v1/advanced/rag.md): Step by Step guide on how to implement Retrieval-Augmented Generation with Neuron AI framework. - [MCP Connector](https://docs.neuron-ai.dev/v1/advanced/mcp-connector.md): Connect your agent with Tools provided by MCP (Model Context Protocol) servers. - [Monitoring & Debugging](https://docs.neuron-ai.dev/v1/advanced/observability.md): Monitor your AI Agents, RAGs, and Workflows in real-time. - [Error Handling](https://docs.neuron-ai.dev/v1/advanced/error-handling.md): Managing errors fired by your agent. - [Asynchronous Processing](https://docs.neuron-ai.dev/v1/advanced/asynchronous-processing.md): Execute multiple parallel processes using NeuronAI async interface. - [AI Provider](https://docs.neuron-ai.dev/v1/components/ai-provider.md): Interact with LLM providers or extend the framework to implement new ones. - [Chat History & Memory](https://docs.neuron-ai.dev/v1/components/chat-history-and-memory.md): Learn how Neuron AI manage multi turn conversations. - [Embeddings Provider](https://docs.neuron-ai.dev/v1/components/embeddings-provider.md): Integrate services to transform text into vectors for semantic search. - [Vector Store](https://docs.neuron-ai.dev/v1/components/vector-store.md): NeuronAI provides you with several ready to use interfaces against several vector databases. - [Pre/Post Processor](https://docs.neuron-ai.dev/v1/components/pre-post-processor.md): Improve the RAG output by pre/post processing prompts and retrieval results. - [Data loader](https://docs.neuron-ai.dev/v1/components/data-loader.md): Learn how to create data loader pipelines to feed your RAG applications. - [Getting Started](https://docs.neuron-ai.dev/v1/workflow/getting-started.md): Guide, moderate, and control your agentic system with human-in-the-loop. - [Node, Edge & State](https://docs.neuron-ai.dev/v1/workflow/node-edge-and-state.md): Learn how to use the fundamental elements to create your Workflow. - [Human In The Loop](https://docs.neuron-ai.dev/v1/workflow/human-in-the-loop.md): The key breakthrough is that interruption isn't a bug – it's a feature. - [Persistence](https://docs.neuron-ai.dev/v1/workflow/persistence.md): Store the workflow State on a persistent memory. ## Neuron - v2 - [Introduction](https://docs.neuron-ai.dev/v2/overview/readme.md): Learn what Neuron is and what you can do with it. - [Upgrade To v2 From v1](https://docs.neuron-ai.dev/v2/overview/readme/upgrade-to-v2-from-v1.md) - [Repository Migration](https://docs.neuron-ai.dev/v2/overview/readme/repository-migration.md) - [Fast Learning by Video](https://docs.neuron-ai.dev/v2/overview/fast-learning-by-video.md): Position yourself in the AI Agent era with our extensive tutorials and technical insights into Neuron capabilities. Learn from practical examples and real-world use cases. - [Agentic Development](https://docs.neuron-ai.dev/v2/overview/agentic-development.md): Connect the documentation to coding agents for AI Assisted Development - [Installation](https://docs.neuron-ai.dev/v2/the-basics/getting-started.md): Step by step instructions on how to install Neuron in your application and create an Agent. - [Agent](https://docs.neuron-ai.dev/v2/the-basics/agent.md): Easily implement LLM interactions extending the basic Agent class. - [AI Provider](https://docs.neuron-ai.dev/v2/the-basics/ai-provider.md): Interact with LLM providers or extend the framework to implement new ones. - [Tools & Toolkits](https://docs.neuron-ai.dev/v2/the-basics/tools.md): Give Agents the ability to interact with your application context and services. - [MCP](https://docs.neuron-ai.dev/v2/the-basics/mcp-connector.md): Connect the tools provided by Model Context Protocol (MCP) servers to your agent. - [Chat History](https://docs.neuron-ai.dev/v2/the-basics/chat-history-and-memory.md): Learn how Neuron AI manage multi turn conversations. - [Streaming](https://docs.neuron-ai.dev/v2/the-basics/streaming.md): Presenting AI response to your user in real-time. - [Structured Output](https://docs.neuron-ai.dev/v2/the-basics/structured-output.md): Enforce the Agent output based on the provided schema. - [Attachments (Documents & Images)](https://docs.neuron-ai.dev/v2/the-basics/attachments-documents-and-images.md): Attach documents and images to your message. - [Async](https://docs.neuron-ai.dev/v2/the-basics/asynchronous-processing.md): Execute multiple parallel processes using Neuron async interface. - [Monitoring & Debugging](https://docs.neuron-ai.dev/v2/the-basics/observability.md): Monitor your AI Agents, RAGs, and Workflows in real-time. - [Error Handling](https://docs.neuron-ai.dev/v2/the-basics/error-handling.md): Managing errors fired by your agent. - [Evaluation](https://docs.neuron-ai.dev/v2/the-basics/evaluation.md): Evaluating the output of your agentic system - [Getting Started](https://docs.neuron-ai.dev/v2/rag/rag.md): Step by Step guide on how to implement Retrieval-Augmented Generation with Neuron framework. - [Data loader](https://docs.neuron-ai.dev/v2/rag/data-loader.md): Learn how to create data loader pipelines to feed your RAG applications. - [Embeddings Provider](https://docs.neuron-ai.dev/v2/rag/embeddings-provider.md): Integrate services to transform text into vectors for semantic search. - [Vector Store](https://docs.neuron-ai.dev/v2/rag/vector-store.md): Neuron provides you with ready to use components to connect your agent to vector databases. - [Pre/Post Processor](https://docs.neuron-ai.dev/v2/rag/pre-post-processor.md): Improve the RAG output by pre/post processing prompts and retrieval results. - [Retrieval](https://docs.neuron-ai.dev/v2/rag/retrieval.md): Implement custom retrieval strategies - [Getting Started](https://docs.neuron-ai.dev/v2/workflow/getting-started.md): Guide, moderate, and control your multi-agent system with human-in-the-loop. - [Single Step Workflow](https://docs.neuron-ai.dev/v2/workflow/single-step-workflow.md): How to create the first workflow with a single node - [Multi Step Workflow](https://docs.neuron-ai.dev/v2/workflow/multi-step-workflow.md): Learn how to handle complex execution flow orchestrating the execution of multiple nodes - [Loops & Branches](https://docs.neuron-ai.dev/v2/workflow/loops-and-branches.md) - [Managing the State](https://docs.neuron-ai.dev/v2/workflow/managing-the-state.md): Learn how to pass data around the workflow - [Human In The Loop](https://docs.neuron-ai.dev/v2/workflow/human-in-the-loop.md): The key breakthrough is that interruption isn't a bug – it's a feature. - [Persistence](https://docs.neuron-ai.dev/v2/workflow/persistence.md): Persist the Workflow State across executions. - [Streaming](https://docs.neuron-ai.dev/v2/workflow/streaming.md): Stream real -time updates during workflow execution - [Examples](https://docs.neuron-ai.dev/v2/workflow/examples.md): Learn about the Workflow features through real code examples - [Testing](https://docs.neuron-ai.dev/v2/resources/testing.md): Fake components to help you test your AI powered system ## Neuron - v3 - [Introduction](https://docs.neuron-ai.dev/overview/readme.md): Learn what Neuron is and what you can do with it. - [Installation](https://docs.neuron-ai.dev/overview/getting-started.md): Step by step instructions on how to install Neuron in your application and create an Agent. - [Upgrade](https://docs.neuron-ai.dev/overview/upgrade.md) - [Video Tutorials](https://docs.neuron-ai.dev/overview/fast-learning-by-video.md): Position yourself in the AI Agent era with our extensive tutorials and technical insights into Neuron capabilities. Learn from practical examples and real-world use cases. - [Agentic Development](https://docs.neuron-ai.dev/overview/agentic-development.md): Connect the documentation to coding agents for AI Assisted Development - [Agent](https://docs.neuron-ai.dev/agent/agent.md): Easily implement LLM interactions with built-in memory and tool usage. - [Messages](https://docs.neuron-ai.dev/agent/messages.md): Unified context unit across AI providers and LLMs. - [Tools & Toolkits](https://docs.neuron-ai.dev/agent/tools.md): Give Agents the ability to interact with your application context and services. - [Chat History](https://docs.neuron-ai.dev/agent/chat-history-and-memory.md): Learn how Neuron AI manage multi turn conversations. - [Streaming](https://docs.neuron-ai.dev/agent/streaming.md): Presenting AI response to your user in real-time. - [Structured Output](https://docs.neuron-ai.dev/agent/structured-output.md): Enforce the Agent output based on the provided schema. - [MCP](https://docs.neuron-ai.dev/agent/mcp-connector.md): Connect the tools provided by Model Context Protocol (MCP) servers to your agent. - [Middleware](https://docs.neuron-ai.dev/agent/middleware.md): Interact with the agent execution flow to customize its behaviour. - [Async](https://docs.neuron-ai.dev/agent/async.md): Run workflows in an async context. - [Monitoring & Debugging](https://docs.neuron-ai.dev/agent/observability.md): Monitor your AI Agents, RAGs, and Workflows in real-time. - [Error Handling](https://docs.neuron-ai.dev/agent/error-handling.md): Managing errors fired by your agent. - [Evals](https://docs.neuron-ai.dev/agent/evaluation.md): Evaluating the output of your agentic system - [Testing](https://docs.neuron-ai.dev/agent/testing.md): Fake components to help you test your AI powered system - [AI Provider](https://docs.neuron-ai.dev/providers/ai-provider.md): Interact with LLM providers or extend the framework to implement new ones. - [Audio](https://docs.neuron-ai.dev/providers/audio.md): Connect providers specialized in processing Audio to Text and vice-versa - [Image](https://docs.neuron-ai.dev/providers/image.md): Generate images from text - [Getting Started](https://docs.neuron-ai.dev/rag/rag.md): Step by Step guide on how to implement Retrieval-Augmented Generation with Neuron framework. - [Data loader](https://docs.neuron-ai.dev/rag/data-loader.md): Learn how to create data loader pipelines to feed your RAG applications. - [Embeddings Provider](https://docs.neuron-ai.dev/rag/embeddings-provider.md): Integrate services to transform text into vectors for semantic search. - [Vector Store](https://docs.neuron-ai.dev/rag/vector-store.md): Neuron provides you with ready to use components to connect your agent to vector databases. - [Pre/Post Processor](https://docs.neuron-ai.dev/rag/pre-post-processor.md): Improve the RAG output by pre/post processing prompts and retrieval results. - [Retrieval](https://docs.neuron-ai.dev/rag/retrieval.md): Implement custom retrieval strategies - [Getting Started](https://docs.neuron-ai.dev/workflow/getting-started.md): Guide, moderate, and control your multi-agent system with human-in-the-loop. - [Single Step Workflow](https://docs.neuron-ai.dev/workflow/single-step-workflow.md): How to create the first workflow with a single node - [Multi Step Workflow](https://docs.neuron-ai.dev/workflow/multi-step-workflow.md): Learn how to handle complex execution flow orchestrating the execution of multiple nodes - [Loops & Branches](https://docs.neuron-ai.dev/workflow/loops-and-branches.md) - [Managing the State](https://docs.neuron-ai.dev/workflow/managing-the-state.md): Learn how to pass data around the workflow - [Interruption](https://docs.neuron-ai.dev/workflow/human-in-the-loop.md): The key breakthrough is that interruption isn't a bug, it's a feature. - [Persistence](https://docs.neuron-ai.dev/workflow/persistence.md): Persist the Workflow State across executions. - [Streaming](https://docs.neuron-ai.dev/workflow/streaming.md): Stream real -time updates during workflow execution - [Middleware](https://docs.neuron-ai.dev/workflow/middleware.md): Control and customize agent execution at every step - [Tips & Tricks](https://docs.neuron-ai.dev/resources/examples.md): Overcome bottlenecks, and learn about the Workflow features through real code examples --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on a page URL with the `ask` query parameter: ``` GET https://docs.neuron-ai.dev/overview/readme.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.