# 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.
ComponentDescription
Python SDKPython client library for building and managing AI agents, tools, and connections with session-aware support aligned to the FastAPI backend.
CLI CommandsCommand-line interface that enables users to manage agents, tools, and MCP connections without writing code.
REST APIBackend interface for managing agents, tools, MCP connections, language models, accounts, and utilities.
## Document Processing Useful for processing raw documents into a useable knowledge.
ComponentDescription
DownloaderDownloads data from a designated source.
LoaderLoads data content.
ParserParses data into a structured format.
ChunkerChunks data with certain strategy.
Data GeneratorGenerates additional information for the data.
IndexerIndexes data into data stores.
DPO RouterRoutes data to determines processing paths.
## Evaluator Useful for performing evaluation of certain modules.
ComponentDescription
End-to-End EvaluationOrchestrates the entire evaluation process, from data loading to result tracking, in a single function call.
Evaluator / ScorerEvaluates modules using certain metrics.
MetricMeasures and assesses the performance of language models.
DatasetIt provides a standardized interface to load data, iterate through them, and expose them in a consistent format.
Experiment TrackerIt 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.
ComponentDescription
SFT TrainerManages Supervised Fine-Tuning (SFT) life-cycle.
GRPO TrainerManages Group Relative Policy Optimization (GRPO) life-cycle.
## i18n/l10n Useful for implementing i18n (internationalization) & l10n (localization).
ComponentDescription
Language DetectorDetects the language of a text.
Text NormalizerNormalizes text into a standard, canonical form.
TransliteratorConverts text between writing systems.
TranslatorTranslates text between languages.
## Model Context Protocol Useful for working with MCP (Model Context Protocol)s.
ComponentDescription
MCP ClientGDP Labs' in-house MCP Client, framework-agnostic and adaptable to other agentic frameworks.
## Multimodality Useful for working with multimodal data.
ComponentDescription
Modality ConverterTransform data from one modality to another (e.g., audio → text, image → text).
Modality TransformerWrapper 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.
ComponentDescription
ComponentBasic executable unit; foundation of all Gen AI components.
ToolMCP-style schema to provide functionalities to an AI agent.
Logger ManagerManages logging across Gen AI apps.
Event EmitterManages event emitting (including streaming) across Gen AI apps.
### Inference Useful for managing model inferences.
ComponentDescription
EM InvokerInvokes embedding models.
LM InvokerInvokes language models.
Prompt BuilderManages prompts as language models inputs.
Output ParserParses language model outputs.
LM Request ProcessorOrchestrates language model invocation end-to-end process, which includes prompt building, invocation, and output parsing.
[BETA] Realtime ChatInteracts with language models in realtime.
### Data Store Useful for managing data stores.
ComponentDescription
Data StoreStores data for knowledge management.
CacheEnables caching management using data stores.
### Retrieval Useful for managing knowledge retrieval.
ComponentDescription
Query TransformerTransforms query to improve retrieval.
Retrieval Parameter ExtractorExtracts retrieval parameters from query.
RetrieverRetrieves knowledge from a designated source.
Chunk ProcessorTransforms retrieved chunks.
RerankerReranks retrieved chunks.
### Generation Useful for managing response generation.
ComponentDescription
Context EnricherEnriches chunks with additional information.
Relevance FilterFilters chunks based on relevance.
RepackerRepacks chunks as a context.
CompressorCompresses context for compacity.
Response SynthesizerSynthesizes response based on provided inputs.
Reference FormatterManages reference formatting based on the response.
### Memory Useful for managing memory.
ComponentDescription
Chat History ManagerManages chat history.
Memory ManagerManages memory.
### Pipeline Useful for managing pipeline building process.
ComponentDescription
PipelineOrchestrates RAG components as pipelines.
StepManages various step behavior in a pipeline.
RouterRoutes inputs into the most appropriate output.
[BETA] ComposerBuilds pipeline with builder patterns.
## Security & Privacy Useful for managing security & privacy.
ComponentDescription
GuardrailManages content filtering and safety checks.
PII AnonymizerAnonymizes PII (Personal Identifiable Information) data.
## Smart Search Useful for performing smart knowledge retrievals.
ComponentDescription
Web SearchThe 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.
Connector SearchThe Connector capability lets Smart Search access third-party data sources such as Google Drive, Google Mail, Google Calendar, and GitHub.
## Why GL SDK? :question: Unlock your full potential in the AI era. The GL SDK provides the foundation you need to build groundbreaking applications without compromise. 1. **Low Code:** Achieve complex AI tasks in as few as five lines of code, drastically accelerating development and reducing errors. 2. **Simple, But Flexible:** Offers straightforward solutions without sacrificing the granular control needed for advanced use cases. 3. **Low Maintenance:** We handle all the underlying open-source dependency management, updates, and compatibility, so your applications simply "just work." 4. **One-Stop Shop:** The GL SDK provides a comprehensive, integrated solution for building production-ready AI applications. 5. **Designed with Developer Experience in Mind:** Meticulously crafted for intuitive use, quickly making beginners productive. {% hint style="success" %} **Learn more about GL SDK's advantages** [**here**](https://gdplabs.gitbook.io/sdk/~/revisions/beykCxz0UanaEX0sPJJu/overview/why-gl-sdk)**.** {% endhint %}