Langflow 1.12 just released!

153k

25k

10k

16k

Getting Started

Call Classification Analytics

Build an automated call transcription and classification system using Langflow that converts audio files into structured data with AI-powered analysis for topic, sentiment, resolution status, and urgency labeling.

Create a prompt template with dynamic variables.

Call Classification & Analytics Agent You are a smart Call Classification & Analytics Agent. Your role is to analyze call transcripts and classify them based on specific characteristics. 🎯 Your Objectives - Classify the call transcript based on: - Topic: e.g., Billing, Technical Support, Cancellation, Sales, Feedback. - Resolution: e.g., Resolved, Escalated, Pending. - Sentiment: e.g., Positive, Neutral, Negative. - Urgency: e.g., Low, Medium, High. Save both the original transcript and the classification in the expected format. 📥 Input Example json "text": "Hello, I've been charged…

Display a chat message in the Playground.

AssemblyAI Start Transcript

Create a transcription job for an audio file using AssemblyAI with advanced options

Assembly API Key *

Type something...

Enable Speaker Labels

AssemblyAI Poll Transcript

Poll for the status of a transcription job using AssemblyAI

Assembly API Key *

Type something...

Transcript ID *

Transcription Result

Extracts text using a template.

Data or DataFrame *

ParserStringify

"transcriptText":"{text}"

Define the agent's instructions, then enter a task to complete using tools.

Type something...

Agent Instructions

You are a helpful assistant that can use tools to answer questions and perform tasks.

Type something...

Runs a language model given a specified provider.

Type something...

Type something...

Type something...

Structured Output

Uses an LLM to generate structured data. Ideal for extraction and consistency.

Language Model *

Input Message *

Type something...

Format Instructions *

You are an AI that extracts structured JSON objects from unstructured text. Use a predefined schema with expected types (str, int, float, bool, dict). Extract ALL relevant instances that match the schema - if multiple patterns exist, capture them all. Fill missing or ambiguous values with defaults: null for missing values. Remove exact duplicates but keep variations that have different field values. Always return valid JSON in the expected format, never throw errors. If multiple objects can be extracted, return them all in the structured format.

Output Schema *

Structured Output

Structured Output

Chunk Classification

Automate document processing with this Langflow workflow that ingests files, splits them into chunks...

CSV Query Assistant

Automated document analysis assistant built with Langflow that processes uploaded files, extracts in...

Data Extraction

Transform unstructured documents like PDFs, emails, and web pages into structured, machine-readable ...

Create your first flow

Join thousands of developers accelerating their AI workflows. Start your first Langflow project now.