Contents Menu Expand Light mode Dark mode Auto light/dark mode
Light Logo Dark Logo
Light Logo Dark Logo
JoinDiscord

Getting Started

  • What is Argilla?
  • ๐Ÿš€ Quickstart
    • Installation
    • Workflow Feedback Dataset
    • Workflow of Other Datasets
  • ๐ŸŽผ Cheatsheet
  • ๐Ÿ”ง Installation
    • Python
    • Docker
    • Docker Quickstart
    • Docker-compose
    • Cloud Providers and Kubernetes
    • Hugging Face Spaces
    • Google Colab
  • โš™๏ธ Configuration
    • Elasticsearch
    • Server configuration
    • User Management
    • Workspace and Dataset Management
    • Database Migrations
    • Image Support

Conceptual Guides

  • Argilla concepts
  • Data collection for LLMs
    • Collecting RLHF data
    • Collecting demonstration data
    • Collecting comparison data

Practical Guides

  • ๐Ÿ—บ๏ธ Practical guides overview
  • ๐Ÿง Choose a dataset type
  • ๐Ÿง‘โ€๐Ÿ’ป Create and update a dataset
    • โบ๏ธ Add and update records
    • ๐Ÿ’พ Work with metadata
    • ๐ŸŽซ Work with vectors
    • ๐Ÿค” Work with suggestions and responses
  • ๐Ÿ—‚๏ธ Assign records to your team
  • ๐Ÿ”Ž Filter and query datasets
  • โœ๏ธ Annotate a dataset
  • ๐ŸŒŠ Simplify annotation with machine feedback workflows
    • ๐Ÿง‘โ€๐Ÿซ Active Learning
    • ๐Ÿ‘ฎ Weak Supervision
    • ๐Ÿ”ฆ Semantic Search
    • โฒ๏ธ Job Scheduling and Callbacks
    • ๐Ÿ“‡ Add Text Descriptives as Metadata
  • ๐Ÿ“Š Collect responses and metrics
  • ๐Ÿ“ฅ Export a dataset
  • ๐Ÿฆพ Fine-tune LLMs and other language models

Tutorials and Integrations

  • Tutorials
  • Integrations
    • langchain: Monitoring LLMs in apps, chains, and agents and tools
    • unstructured: Large-scale document processing for LLMs
    • fastapi: Monitor NLP models with ArgillaLogHTTPMiddleware
    • textdescriptives: Add basic descriptive features as Metadata
    • sentence-transformers: Add semantic vectors to your dataset
    • llamaindex: Build LLM applications with LlamaIndex and monitor the data with Argilla.

Reference

  • Python
    • Client
    • Metrics
    • Labeling
    • Training
    • Monitoring
    • Listeners
    • Users
    • Workspaces
    • Annotation metrics
  • CLI
  • Argilla UI
    • Pages
    • Features
  • Notebooks
    • ๐Ÿ” Backup and version Argilla Datasets using DVC
    • ๐Ÿš€ Run Argilla with a Transformer in an active learning loop and a free GPU in your browser
    • ๐Ÿ’พ Monitor FastAPI model endpoints
    • ๐Ÿงธ Using LLMs for Text Classification and Summarization Suggestions with spacy-llm
    • ๐Ÿ—บ๏ธ Add bias-equality features to datasets with disaggregators
    • ๐Ÿ’ก Build and evaluate a zero-shot sentiment classifier with GPT-3
    • ๐Ÿ’จ Label data with semantic search and Sentence Transformers
    • ๐Ÿ“ธ Bulk Labeling Multimodal Data
    • ๐Ÿงฑ Augment weak supervision rules with Sentence Transformers
    • ๐Ÿ”ซ Zero-shot and few-shot classification with SetFit
    • ๐Ÿ—‚ Multi-label text classification with weak supervision
    • ๐Ÿ“ฐ Train a text classifier with weak supervision
    • ๐Ÿ—‚๏ธ Assign records to your annotation team
    • ๐Ÿฉน Delete labels from a Token or Text Classification dataset
    • ๐Ÿ”ซ Evaluate a zero-shot NER with Flair
    • ๐Ÿญ Train a NER model with skweak
    • ๐Ÿ’ซ Explore and analyze spaCy NER predictions
    • ๐Ÿ”— Using LLMs for Few-Shot Token Classification Suggestions with spacy-llm
    • ๐Ÿง Find label errors with cleanlab
    • ๐Ÿฅ‡ Compare Text Classification Models
    • ๐Ÿ•ต๏ธโ€โ™€๏ธ Analyze predictions with explainability methods
    • ๐Ÿงผ Clean labels using your modelโ€™s loss
    • ๐Ÿค” Fine-tunning a NER model with BERT for Beginners
    • Text classification active learning with classy-classification
    • ๐Ÿค” Text Classification active learning with ModAL
    • ๐Ÿคฏ Few-shot classification with SetFit
    • ๐Ÿค— Train a sentiment classifier with SetFit
    • ๐Ÿ‘‚ Text Classification: Active Learning with small-text
    • ๐Ÿท๏ธ Fine-tune a sentiment classifier with your own data
    • ๐Ÿ•ธ๏ธ Train a summarization model with Unstructured and Transformers
  • Telemetry

Community

  • Discord
  • Github
  • Developer Documentation
  • Contributor Documentation
  • Migration from Rubrix
Back to top
JoinDiscord

๐Ÿ”ฆ Semantic search#

These tutorials show you how to use semantic search with Argilla.

๐Ÿ“ธ Bulk Labelling Multimodal Data

MLOps Steps: Labelling
NLP Tasks: TextClassification (images)
Libraries: Argilla, sentence-transformers
Techniques: Semantic search

๐Ÿ’จ Speed-up data labelling with Sentence Transformer embeddings

MLOps Steps: Labelling
NLP Tasks: TextClassification
Libraries: Argilla, sentence-transformers
Techniques: Semantic search

Copyright © 2025, Argilla.io
Made with Sphinx and @pradyunsg's Furo
Signup Here For
Our Community Meetup