DOCSEARCHbyAlgolia
Submit Docs

Nocodo AI Documentation

website·Indexed 31 days ago

https://docs.nocodo.ai

Documentation for Nocodo AI, a platform for building complex AI workflows using a variety of nodes. Features include LLM integration, Master and Validation Agents, vector store readers and writers, image generation and embedding, and data source connectors for PostgreSQL, OpenSearch, and Apollo.io.

Tokens
25K
Snippets
25
Records
238
Agent score
53%

What's inside Nocodo AI

  1. Overview of the Document Splitter node

    The Document Splitter is used to efficiently split and manage large documents, making them suitable for text analysis, machine learning, and seamless processing. It provides flexible splitting options to handle large volumes of text.

  2. Overview of the Master Agent orchestration node

    The Master Agent is an advanced orchestration node that acts as a central controller to manage task delegation and workflow execution. It coordinates multiple specialized agents and tools to execute complex AI workflows, synthesizing results into a final deliverable.

  3. Overview of the Text to Speech Node

    The Text to Speech (TTS) node is a unified interface in Nocodo that converts text into high-quality spoken audio. It supports multiple AI providers, allowing users to choose based on speed, quality, or language requirements. The node accepts text input and produces audio output that can be routed to other nodes, such as the File Writer node, to save the resulting audio file.

  4. Overview of the Speech to Text Node

    The Speech to Text (STT) node is a unified interface for transcribing audio into text using high-accuracy models from multiple providers. It supports common audio formats such as MP3, WAV, M4A, FLAC, and OGG. The node can be connected to a File Reader for input and a File Writer or Text Output for the resulting transcription.

  6. Overview of the Nocodo LLM Node

    The Large Language Model (LLM) node allows users to execute language tasks using AI models from multiple providers. It supports text generation, multimodal processing (images), reasoning tasks, and both standard and streaming outputs.

  7. Overview of the Text Embedder Node

    The Text Embedder Node transforms text, documents, or paragraphs into numerical representations called embeddings. These embeddings capture semantic meaning, allowing computers to process text for applications such as semantic search, similarity analysis, and intelligent content retrieval.

  8. Generate image embeddings for similarity search and analysis

    Use the Image Embedder to generate embeddings from images using AI models. These embeddings can be utilized for similarity searches, clustering, and various visual analysis tasks.

  9. Use the Validation Agent to optimize workflow execution

    The Validation Agent is used to analyze failed steps within a workflow and provide improved alternatives. This helps developers increase execution quality and optimize the overall workflow logic by identifying why a step failed and how to correct it.

  10. Integrate B2B sales intelligence using Apollo.io

    Use the Apollo.io node to access B2B sales intelligence data. This integration allows developers to enrich contact profiles and search for prospects by leveraging Apollo.io's comprehensive business database.

  11. Extract and transform data using the JSON Query node

    The JSON Query node allows you to select specific fields or values from complex JSON structures and reshape them. It supports three query languages:

    • JSONata: A comprehensive expression language with functional programming features, ideal for complex transformations and calculations.
    • JMESPath: A clean syntax for extracting and transforming JSON elements.
    • JSONPath: An XPath-like syntax for navigating JSON documents, best for simple extractions.

  12. Use the Data Conversion node to transform data formats

    The Data Conversion node acts as a translator between workflow components that require different data formats. It allows you to transform input from one format into another to prevent format mismatch errors. Supported formats include Text, Number, JSON, File, and Boolean.