Connect agents to the tools your team uses every day — CRMs, data warehouses, messaging, ticketing, billing. Authenticate once, then ship workflows that read and write across your stack.
Integration for Faiss Vector Store providing faiss capabilities.
Retrieve users from Notion.
Retrieve the content of a Notion page as plain text.
Extracts structured data from a web page using an AgentQL query or a Natural Language description.
Generates text using AI/ML API LLMs.
Generate embeddings using the AI/ML API.
Integration for ALTK Agent providing altk capabilities.
Integration for Amazon Bedrock providing amazon capabilities.
Integration for Amazon Bedrock Converse providing amazon capabilities.
Integration for Amazon Bedrock Embeddings providing amazon capabilities.
Uploads files to S3 bucket.
Generate text using Anthropic's Messages API and models.
Use Apify Actors to extract data from hundreds of places fast. This component can be used in a flow to retrieve data or as a tool with an agent.
Search and retrieve papers from arXiv.org
Export your transcript in SRT or VTT format for subtitles and closed captions
Apply Large Language Models to spoken data using the AssemblyAI LeMUR framework
Retrieve a list of transcripts from AssemblyAI with filtering options
Poll for the status of a transcription job using AssemblyAI
Create a transcription job for an audio file using AssemblyAI with advanced options
Integration for Azure Chat Open AI providing azure capabilities.
Integration for Azure Open AI Embeddings providing azure capabilities.
Integration for Qianfan Chat Endpoint providing baidu capabilities.
Call the Bing Search API.
Cassandra Vector Store with search capabilities
Retrieves and store chat messages from Apache Cassandra.
Cassandra Graph Vector Store
Integration for Chroma Vector Store providing chroma capabilities.
Evaluates any LLM response using Cleanlab and outputs trust score and explanation.
Evaluates context, query, and response from a RAG pipeline using Cleanlab and outputs trust metrics.
Remediates an untrustworthy response based on trust score from the Cleanlab Evaluator, score threshold, and message handling settings.
ClickHouse Vector Store with search capabilities
Integration for Cloudflare Workers AI Embeddings providing cloudflare capabilities.
Generate embeddings using Cohere models.
Generate text using Cohere LLMs.
Rerank documents using the Cohere API.
All AI Models in One API 500+ AI Models
Integration for Composio API providing composio capabilities.
Confluence wiki collaboration platform
Couchbase Vector Store with search capabilities
Represents an agent of CrewAI.
Creates a CrewAI Task and its associated Agent.
Integration for Cuga providing cuga capabilities.
Use as a template to create your own component.
Make HTTP requests using URL or cURL commands.
Load a CSV file, CSV from a file path, or a valid CSV string and convert it to a list of Data
Convert a JSON file, JSON from a file path, or a JSON string to a Data object or a list of Data objects
Generate mock data for testing and development.
Searches Google News via RSS. Returns clean article data.
Fetches and parses an RSS feed.
Executes SQL queries on SQLAlchemy-compatible databases.
Search the web, news, or RSS feeds.
Fetch content from one or more web pages, following links recursively.
Manages Assistant Interactions
Retrieves and stores chat messages from Astra DB.
Integration for Astra DB Graph Vector Store providing datastax capabilities.
Integration for Astra DB Tool providing datastax capabilities.
Integration for Astra DB Vector Store providing datastax capabilities.
Integration for Astra Vectorize providing datastax capabilities.
Creates an Assistant and returns it's id
Creates a thread and returns the thread id
Load .env file into env vars
Assistant by id
Gets the value of an environment variable from the system.
Integration for Graph RAG providing datastax capabilities.
Integration for HCD Vector Store providing datastax capabilities.
Returns a list of assistant id's
Executes an Assistant Run against a thread
Integration for Amazon Kendra Retriever providing deactivated capabilities.
Extracts code block from text.
Integration for JSON Document Builder providing deactivated capabilities.
`LiteLLM` collection of large language models.
Connects to an MCP server over SSE and exposes it's tools as langflow tools to be used by an Agent.
Connects to an MCP server over stdio and exposes it's tools as langflow tools to be used by an Agent.
Combines multiple Data objects into a unified list, ensuring all keys are present in each Data object.
Integration for Metal Retriever providing deactivated capabilities.
Initialize from llm using default template.
Tool for interacting with retriever
Passes the specified value if a specified condition is met.
Integration for Split Text providing deactivated capabilities.
Integration for Vectara Self Query Retriver providing deactivated capabilities.
A vector store retriever
Generate text using DeepSeek LLMs.
Integration for Chunk Docling Document providing docling capabilities.
Uses Docling to process input documents running the Docling models locally.
Uses Docling to process input documents connecting to your instance of Docling Serve.
Integration for Export Docling Document providing docling capabilities.
Search the web using DuckDuckGo with customizable result limits
Integration for Elasticsearch Vector Store providing elastic capabilities.
Exa Search toolkit for search and content retrieval
Integration for File Reader providing files and knowledge capabilities.
Recursively load files from a directory.
Create or update knowledge in Langflow.
Search and retrieve data from knowledge.
Save data to local file, AWS S3, or Google Drive in the selected format.
Integration for Firecrawl Crawl Api providing firecrawl capabilities.
Integration for Firecrawl Extract Api providing firecrawl capabilities.
Integration for Firecrawl Map Api providing firecrawl capabilities.
Integration for Firecrawl Scrape Api providing firecrawl capabilities.
Processes items in batches. Takes a DataFrame and outputs one batch at a time, then outputs to done when all batches are processed.
Route Data object(s) based on a condition applied to a specified key, including boolean validation.
Tracks and manages counters in the flow context. Supports increment, decrement, reset, and get operations.
Controls execution frequency. In debounce mode, only executes after input stops for the specified duration. In throttle mode, limits execution to once per period.
Routes an input message to a corresponding output based on text comparison.
Pauses execution for a specified duration before passing through the input data.
Catches and handles errors gracefully. Routes to success output on normal execution, or error output if an exception is detected. Can provide fallback values.
Executes another flow from within the same project. Can also be used as a tool for agents. **Select a Flow to use the tool mode**
Filters data based on conditions applied to a specified key or text content. Routes matching items to passed output and non-matching to filtered output.
Construct a Tool from a function that runs the loaded Flow.
Combines outputs from multiple branches into a single output. Supports different merge strategies: concat, first valid, last valid, or all as list.
Generates a Component from a Flow, with all of its inputs, and
Marks parallel execution branches. Splits input to multiple branches that can execute simultaneously, then provides a synchronization point when all complete.
Forwards the input message, unchanged.
Manages a queue of items for sequential processing. Supports enqueue, dequeue, peek, and clear operations.
Controls execution rate by limiting how many requests can pass through within a time period. Uses a token bucket algorithm for smooth rate limiting.
Iterates over a list of Data or Message objects, outputting one item at a time and aggregating results from loop inputs. Message objects are automatically converted to Data objects for consistent processing.
Manages retry logic with configurable attempts and exponential backoff. Tracks retry state in context and routes to success or failure outputs.
A component to generate a notification to Get Notified component.
Splits input data to multiple outputs simultaneously. All outputs receive the same input data, enabling parallel processing paths.
Multi-way routing based on a switch value. Routes to the matching case output or default if no match is found. Supports up to 5 cases.
Wraps an operation with a timeout. Routes to completed output if finished in time, or timeout output if the maximum duration is exceeded.
A component to listen for a notification.
Loops while a condition is true. Outputs to the loop branch while condition is met, then outputs to done branch when condition becomes false or max iterations reached.
Load and filter documents from a local or remote Git repository. Use a local repo path or clone from a remote URL.
Analyzes a Git repository and returns file contents and complete repository information
Execute SQL queries on Google BigQuery.
Loads emails from Gmail using provided credentials.
Manage Google Calendar events - list, create, update, and delete events.
Loads documents from Google Drive using provided credentials.
Searches Google Drive files using provided credentials and query parameters.
Generate text using Google Generative AI.
Connect to Google's generative AI embeddings service using the GoogleGenerativeAIEmbeddings class, found in the langchain-google-genai package.
Convert addresses to coordinates (geocoding) and coordinates to addresses (reverse geocoding).
Generates a JSON string with your Google OAuth token.
Call Google Search API and return results as a DataFrame.
Retrieve search analytics data from Google Search Console.
Call the Serper.dev Google Search API.
Read, write, and append data to Google Sheets spreadsheets.
Translate text between languages using Google Cloud Translation API.
Search and retrieve YouTube video, channel, and playlist information.
Integration for Groq Model providing groq capabilities.
Generate embeddings using Hugging Face Text Embeddings Inference (TEI)
Integration for Hugging Face Endpoints providing huggingface capabilities.
Generate text using IBM watsonx.ai foundation models.
Generate embeddings using IBM watsonx.ai models.
Uses Combinatorial Optimization to construct an optimal prompt with embedded reasons. Sign up here: https://forms.gle/oWNv2NKjBNaqqvCx6
Display a chat message in the Playground.
Sends text output via API.
Get user text inputs.
Get chat inputs from the Playground.
Integration for Webhook Trigger providing input output capabilities.
Scrape any website instantly and get consistent structured data in seconds without writing any css selector code
Effortlessly search the Web and get access to high-quality results powered with AI.
Read any previously uploaded file seamlessly from JigsawStack File Storage and use it in your AI applications.
Store any file seamlessly on JigsawStack File Storage and use it in your AI applications. Supports various file types including images, documents, and more.
Generate an image based on the given text by employing AI models like Flux, Stable Diffusion, and other top models.
Detect if image/video contains NSFW content
Perform object detection on images using JigsawStack's Object Detection Model, capable of image grounding, segmentation and computer use.
Analyze sentiment of text using JigsawStack AI
Translate text from one language to another with support for multiple text formats.
Convert natural language to SQL queries using JigsawStack AI
Extract data from any document type in a consistent structure with fine-tuned vLLMs for the highest accuracy
Construct a CSV agent from a CSV and tools.
Split text by number of characters.
Chain to have a conversation and load context from memory.
Generate fake embeddings, useful for initial testing and connecting components.
Extract hyperlinks from HTML content.
Construct a json agent from an LLM and tools.
Chain for question-answering with self-verification.
Chain that interprets a prompt and executes python code to do math.
Integration for Lang Chain Hub Prompt providing langchain utilities capabilities.
Integration for Language Recursive Text Splitter providing langchain utilities capabilities.
Split text based on natural language boundaries, optimized for a specified language.
Generate SQL from natural language.
Integration for Open AI Tools Agent providing langchain utilities capabilities.
Agent to interact with OpenAPI API.
Integration for Recursive Character Text Splitter providing langchain utilities capabilities.
Chain for question-answering querying sources from a retriever.
Execute a runnable. It will try to guess the input and output keys.
Construct an SQL agent from an LLM and tools.
SQL Database
Retriever that uses a vector store and an LLM to generate the vector store queries.
Integration for Tool Calling Agent providing langchain utilities capabilities.
Information about a VectorStore
Construct an agent from a Vector Store Router.
Integration for XML Agent providing langchain utilities capabilities.
Uses an LLM to generate a function for filtering or transforming structured data.
Runs an LLM on each row of a DataFrame column. If no column is specified, all columns are used.
Uses an LLM to generate structured data. Ideal for extraction and consistency.
Routes the input to the most appropriate LLM based on OpenRouter model specifications
Routes an input message using LLM-based categorization.
Generate text using LM Studio Local LLMs.
Generates text using MariTalk LLMs.
Retrieves and stores chat messages using Mem0 memory storage.
Integration for Milvus Vector Store providing milvus capabilities.
Generates text using MistralAI LLMs.
Generate embeddings using MistralAI models.
Runs a language model given a specified provider.
Integration for Agent providing models and agents capabilities.
Stores or retrieves stored chat messages from Broxi tables or an external memory.
Connect to an MCP server to use its tools.
Integration for Prompt providing models and agents capabilities.
Generate embeddings using a specified provider.
MongoDB Atlas Vector Store with search capabilities
A retriever that uses the Needle API to search collections.
Call the right model at the right time with the world's most powerful AI model router.
Generates text using Novita AI LLMs (OpenAI compatible).
Generates text using NVIDIA LLMs.
Rerank documents using the NVIDIA API.
Multi-modal data extraction from documents using NVIDIA's NeMo API.
(Windows only) Prompts NVIDIA System-Assist to interact with the NVIDIA GPU Driver. The user may query GPU specifications, state, and ask the NV-API to perform several GPU-editing acations. The prompt must be human-readable language.
A component to create an outbound call request from Olivya's platform.
Generate text using Ollama Local LLMs.
Integration for Ollama Embeddings providing ollama capabilities.
Generates text using OpenAI LLMs.
Generate embeddings using OpenAI models.
OpenRouter provides unified access to multiple AI models from different providers through a single API.
Generate text using Perplexity LLMs.
PGVector Vector Store with search capabilities
Pinecone Vector Store with search capabilities
Perform aggregation operations like sum, count, average, min, max on data.
Adds/Removes Metadata Dictionary on inputs
Combines data using different operations
Creates a list of texts.
Filters a Data object based on a list of keys.
Perform various operations on a Data object.
Convert Data objects into Messages using any {field_name} from input data.
Converts one or multiple Data objects into a DataFrame. Each Data object corresponds to one row. Fields from `.data` become columns, and the `.text` (if present) is placed in a 'text' column.
Perform various operations on a DataFrame.
Convert each row of a DataFrame into a callable tool/action in a toolset.
Parse and format dates with timezone support.
Remove duplicate entries from a data collection.
Reads Excel files and extracts data row by row. Outputs a DataFrame for loop iteration and supports {variable} substitution in Prompt Templates and email components.
Filter a list of data items based on a specified key, filter value, and comparison operator. Check advanced options to select match comparision.
Flatten nested data structures or unflatten flat dictionaries.
Cleans the messy and sometimes incorrect JSON strings produced by LLMs so that they are fully compliant with the JSON spec.
Extract a specific key from a Data object or a list of Data objects and return the extracted value(s) as Data object(s).
Stores a chat message or text into Broxi tables or an external memory.
Convert a Message object to a Data object
Convert a DataFrame into plain text following a specified template. Each column in the DataFrame is treated as a possible template key, e.g. {col_name}.
Convert and extract JSON fields.
Extract patterns from text using regular expressions.
Transforms the output of an LLM into a specified format.
Sort a collection of data items by a specified key.
Integration for Split Text providing processing capabilities.
Perform common string transformations like case conversion, trimming, and padding.
Render Jinja2 templates with variable substitution.
Extracts text using a template.
Concatenate two text sources into a single text chunk using a specified delimiter.
Find and replace text patterns using plain text or regex.
Truncate text to a specified length with optional suffix.
Convert between different types (Message, Data, DataFrame)
Parse XML/HTML content and extract elements by selector.
Define and execute a Python function that returns a Data object or a Message.
Qdrant Vector Store with search capabilities
Retrieves and store chat messages from Redis.
Integration for Redis Vector Store providing redis capabilities.
Generate text using Sambanova LLMs.
Integration for Scrape Graph Markdownify Api providing scrapegraph capabilities.
Integration for Scrape Graph Search Api providing scrapegraph capabilities.
Integration for Scrape Graph Smart Scraper Api providing scrapegraph capabilities.
Send emails using Amazon SES. Supports {variables} in all text fields.
Send emails using Brevo API. Supports templates and {variables} in all text fields.
Send emails using Elastic Email API. Supports templates and {variables}.
Send emails using Mailchimp Transactional (Mandrill). Supports templates and {variables}.
Send emails using Mailgun API. Supports templates and {variables} in all text fields.
Send emails using Postmark API. Supports templates and {variables} in all text fields.
Send emails using Resend API. Supports HTML content and {variables} in all text fields.
Send emails via SMTP server. Supports TLS/SSL, authentication, and dynamic {variables} in all text fields.
Send emails using SendGrid API. Supports dynamic templates and {variables} in all text fields.
Send emails using SendPulse API. Supports templates and {variables}.
Call Serp Search API with result limiting
Supabase Vector Store with search capabilities
**Tavily Extract** extract raw content from URLs.
**Tavily Search** is a search engine optimized for LLMs and RAG, aimed at efficient, quick, and persistent search results.
Call Google Search API.
Call the Serper.dev Google Search API.
Perform basic arithmetic operations on a given expression.
structuredtool dataclass code to tool
A tool for running Python code in a REPL environment.
A component that searches for tools using SearXNG.
Integration for Search API providing tools capabilities.
Call Serp Search API with result limiting
**Tavily Search API** is a search engine optimized for LLMs and RAG, aimed at efficient, quick, and persistent search results. It can be used independently or as an agent tool. Note: Check 'Advanced' for all options.
Performs a search using the Wikidata API.
Call Wikipedia API.
Uses [yfinance](https://pypi.org/project/yfinance/) (unofficial package) to access financial data and market information from Yahoo! Finance.
Converts Astra DB search results to inputs compatible with TwelveLabs Pegasus.
Split a video into multiple clips of specified duration.
Chat with videos using TwelveLabs Pegasus API.
Index videos using TwelveLabs and add the video_id to metadata.
Generate embeddings using TwelveLabs text embedding models.
Generate embeddings from videos using TwelveLabs video embedding models.
Load a video file in common video formats.
Uses Unstructured.io API to extract clean text from raw source documents. Supports a wide range of file types.
Upstash Vector Store with search capabilities
Perform basic arithmetic operations on a given expression.
Fetches currency exchange rates for a given currency code from the free currency API.
Returns the current date and time in the selected timezone.
Generate cryptographic hashes (MD5, SHA256, SHA512, etc.) from text.
Generates a unique ID.
Get geographic location information for an IP address using ip-api.com (free, no API key required).
Format, validate, and pretty-print JSON data.
Generate Lorem Ipsum placeholder text.
Convert Markdown text to HTML.
Run Python code with optional imports. Use print() to see the output.
Generate random test data (names, emails, addresses, etc.).
Extract patterns from text using regular expressions.
Translate text between languages using MyMemory Translation API (free, no API key required).
Shorten long URLs using free URL shortening services.
Generate universally unique identifiers (UUIDs).
Fetches current weather and forecast data for a location using Open-Meteo API (free, no API key required).
Vectara's full end to end RAG
Integration for Vectara Vector Store providing vectara capabilities.
Integration for Local DB providing vectorstores capabilities.
Generate text using Vertex AI LLMs.
Generate embeddings using Google Cloud Vertex AI models.
Generates text using vLLM models via OpenAI-compatible API.
Generate embeddings using vLLM models via OpenAI-compatible API.
Extract structured data from audio and video using [VLM Run AI](https://app.vlm.run)
Weaviate Vector Store with search capabilities
Performs a search using the Wikidata API.
Call Wikipedia API.
Enables queries to WolframAlpha for computational data, facts, and calculations across various topics, delivering structured responses.
Generates text using xAI models like Grok.
Uses [yfinance](https://pypi.org/project/yfinance/) (unofficial package) to access financial data and market information from Yahoo! Finance.
Extracts all video URLs from a YouTube playlist.
Integration for YouTube Transcripts providing youtube capabilities.
Retrieves and store chat messages from Zep.