Component List
Last update: November 17, 2025.
The GL SDK is ✨ ever-growing, with ✨ 50+ types of components available at your disposal. Please find the complete list below:
AI Agents Package
Useful for building dynamic agents.
Python client library for building and managing AI agents, tools, and connections with session-aware support aligned to the FastAPI backend.
Command-line interface that enables users to manage agents, tools, and MCP connections without writing code.
Backend interface for managing agents, tools, MCP connections, language models, accounts, and utilities.
Document Processing
Useful for processing raw documents into a useable knowledge.
Downloads data from a designated source.
Loads data content.
Parses data into a structured format.
Chunks data with certain strategy.
Generates additional information for the data.
Indexes data into data stores.
Routes data to determines processing paths.
Evaluator
Useful for performing evaluation of certain modules.
Orchestrates the entire evaluation process, from data loading to result tracking, in a single function call.
Evaluates modules using certain metrics.
Measures and assesses the performance of language models.
It provides a standardized interface to load data, iterate through them, and expose them in a consistent format.
It logs model inputs/outputs, evaluation scores, configuration parameters, timestamps, and aggregated results to compare runs, reproduce them, and monitor performance changes over time.
Fine-Tuning
Useful for fine-tuning models.
Manages Supervised Fine-Tuning (SFT) life-cycle.
Manages Group Relative Policy Optimization (GRPO) life-cycle.
i18n/l10n
Useful for implementing i18n (internationalization) & l10n (localization).
Detects the language of a text.
Normalizes text into a standard, canonical form.
Converts text between writing systems.
Translates text between languages.
Model Context Protocol
Useful for working with MCP (Model Context Protocol)s.
GDP Labs' in-house MCP Client, framework-agnostic and adaptable to other agentic frameworks.
GDP Labs' maintained Connectors for third party applications.
Multimodality
Useful for working with multimodal data.
Transform data from one modality to another (e.g., audio → text, image → text).
Wrapper Component that transform an input modality into other modalities using one or more modality converters.
Retrieval-Augmented Generation
Useful for building dynamic Retrieval-Augmented Generation (RAG) pipelines.
Core
Useful for managing shared functionality across the RAG components.
Basic executable unit; foundation of all Gen AI components.
MCP-style schema to provide functionalities to an AI agent.
Manages logging across Gen AI apps.
Manages event emitting (including streaming) across Gen AI apps.
Inference
Useful for managing model inferences.
Invokes embedding models.
Invokes language models.
Manages prompts as language models inputs.
Parses language model outputs.
Orchestrates language model invocation end-to-end process, which includes prompt building, invocation, and output parsing.
Interacts with language models in realtime.
Data Store
Useful for managing data stores.
Stores data for knowledge management.
Enables caching management using data stores.
Retrieval
Useful for managing knowledge retrieval.
Transforms query to improve retrieval.
Extracts retrieval parameters from query.
Retrieves knowledge from a designated source.
Transforms retrieved chunks.
Reranks retrieved chunks.
Generation
Useful for managing response generation.
Enriches chunks with additional information.
Filters chunks based on relevance.
Repacks chunks as a context.
Compresses context for compacity.
Synthesizes response based on provided inputs.
Manages reference formatting based on the response.
Memory
Useful for managing memory.
Manages chat history.
Manages memory.
Pipeline
Useful for managing pipeline building process.
Orchestrates RAG components as pipelines.
Manages various step behavior in a pipeline.
Routes inputs into the most appropriate output.
Builds pipeline with builder patterns.
Security & Privacy
Useful for managing security & privacy.
Manages content filtering and safety checks.
Anonymizes PII (Personal Identifiable Information) data.
Smart Search
Useful for performing smart knowledge retrievals.
The Web Search module enables you to perform searches across the web, retrieve URLs, fetch page content, and extract structured insights such as snippets or keypoints.
The Connector capability lets Smart Search access third-party data sources such as Google Drive, Google Mail, Google Calendar, and GitHub.
Why GL SDK? ❓
Unlock your full potential in the AI era. The GL SDK provides the foundation you need to build groundbreaking applications without compromise.
Low Code: Achieve complex AI tasks in as few as five lines of code, drastically accelerating development and reducing errors.
Simple, But Flexible: Offers straightforward solutions without sacrificing the granular control needed for advanced use cases.
Low Maintenance: We handle all the underlying open-source dependency management, updates, and compatibility, so your applications simply "just work."
One-Stop Shop: The GL SDK provides a comprehensive, integrated solution for building production-ready AI applications.
Designed with Developer Experience in Mind: Meticulously crafted for intuitive use, quickly making beginners productive.
Learn more about GL SDK's advantages here.
Last updated