# Cloud - [Collection Forking](https://docs.trychroma.com/cloud/features/collection-forking): The page details the concept and process of Collection Forking in Chroma Cloud, explaining how it allows instant creation of a new collection from an existing one using copy-on-write, along with usage guidelines and pricing information. - [Chroma Cloud](https://docs.trychroma.com/cloud/getting-started): The page provides an overview of Chroma Cloud, detailing its features as a fully managed, serverless service that offers easy scalability, reliability, security, and an advanced search API, while being based on the open-source Apache 2.0 Chroma engine. - [Package Search MCP Server](https://docs.trychroma.com/cloud/package-search/mcp): The page explains the Package Search MCP Server, detailing its role in improving AI coding task performance by providing AI agents with context about code packages, and offers steps to integrate and use this server with various SDKs and platforms through API keys and configuration. - [Package Search Registry](https://docs.trychroma.com/cloud/package-search/registry): The page describes the Chroma Package Search Registry, explaining how it indexes public code packages, supports multiple registries, and can be updated with additional packages through a GitHub repository. - [Pricing](https://docs.trychroma.com/cloud/pricing): The page details Chroma Cloud's usage-based pricing model, covering charges for writes, reads, storage, and additional information such as forking costs and frequently asked questions regarding billing. - [Quotas & Limits](https://docs.trychroma.com/cloud/quotas-limits): The page details the quotas and limits enforced by Chroma Cloud to maintain stability and fairness, including various maximum input and query dimensions, with guidance on requesting higher limits if necessary. - [Index Configuration Reference](https://docs.trychroma.com/cloud/schema/index-reference): The page provides a comprehensive reference for Chroma's index types and configuration parameters, detailing their use cases, limitations, and specific configurations for various data types. - [Schema Overview](https://docs.trychroma.com/cloud/schema/overview): The page provides an overview of the Schema feature in Chroma, detailing how it allows fine-grained control over index configuration in collections to enable advanced search capabilities and optimize performance. - [Schema Basics](https://docs.trychroma.com/cloud/schema/schema-basics): The page provides an overview of Schema Basics in Chroma, explaining how to create, use, and configure schemas to control index behavior in Chroma collections, including details on defaults, specific key configurations, creating and disabling indexes, and using schemas with collections. - [Sparse Vector Search Setup](https://docs.trychroma.com/cloud/schema/sparse-vector-search): The page provides a comprehensive guide on setting up and using sparse vectors for keyword-based search in Chroma, and details how to combine them with dense embeddings for hybrid search capabilities. - [Batch Operations](https://docs.trychroma.com/cloud/search-api/batch-operations): The page explains how to execute multiple searches using batch operations in Chroma to enhance search performance and facilitate result comparison, including usage examples, benefits, and best practices. - [Examples & Patterns](https://docs.trychroma.com/cloud/search-api/examples): The page provides complete end-to-end examples demonstrating real-world use cases of the Chroma Search API, including building an e-commerce product search, a personalized content recommendation system, and performing multi-category searches using batch operations, along with best practices and next steps in handling search operations effectively. - [Filtering with Where](https://docs.trychroma.com/cloud/search-api/filtering): The page explains how to use the "Where" expression and the Key/K class in Chroma for filtering search results by document fields, IDs, and metadata, including examples in Python and TypeScript, supported operators, logical combinations, and best practices. - [Group By & Aggregation](https://docs.trychroma.com/cloud/search-api/group-by): The page explains how to use the Group By & Aggregation feature in Chroma to organize and aggregate search results by metadata keys, with examples and guidance on setting parameters and using aggregation functions like MinK and MaxK for effective data diversification and ranking. - [Hybrid Search with RRF](https://docs.trychroma.com/cloud/search-api/hybrid-search): The page covers hybrid search using Reciprocal Rank Fusion (RRF), explaining how to combine multiple ranking strategies, integrate dense and sparse embeddings, configure RRF parameters, and offering practical examples and best practices for use. - [Migration Guide](https://docs.trychroma.com/cloud/search-api/migration): The page provides a Migration Guide for transitioning from Chroma's legacy `query()` and `get()` methods to the new Search API, including parameter mappings, examples, key differences, new capabilities, and migration tips. - [Search API Overview](https://docs.trychroma.com/cloud/search-api/overview): The page provides an overview of the Search API in Chroma Cloud, detailing its functionality, unified interface, expression-based queries, advanced search capabilities, and setup requirements, along with example code in Python and TypeScript. - [Pagination & Field Selection](https://docs.trychroma.com/cloud/search-api/pagination-selection): The page covers how to control search query results in Chroma using pagination with limits and offsets, selecting specific fields for data optimization, implementing pagination patterns, and the performance considerations of different field selections in Python and TypeScript. - [Ranking and Scoring](https://docs.trychroma.com/cloud/search-api/ranking): The page provides comprehensive guidance on how to use ranking expressions in Chroma to score and order search results, utilizing K-nearest neighbor (Knn) searches and various arithmetic operations and features for custom scoring strategies. - [Search Basics](https://docs.trychroma.com/cloud/search-api/search-basics): The page describes the basics of constructing and using the Search class for querying Chroma collections, including its parameters, builder patterns, initialization patterns, and how to use it in Python and TypeScript. - [Walkthrough](https://docs.trychroma.com/cloud/sync/github): The page provides a detailed walkthrough on using Direct Sync and Platform Sync methods for syncing GitHub repositories with Chroma Cloud, including prerequisites, setup instructions, and invocation processes. - [Overview](https://docs.trychroma.com/cloud/sync/overview): The page provides an overview of the Chroma Sync API, including key concepts like source types, sources, and invocations, as well as detailed information on the usage, configuration, and endpoints for managing data syncing with sources such as GitHub repositories and web pages. - [Walkthrough](https://docs.trychroma.com/cloud/sync/web): The page explains how to use Web Sync in Chroma Cloud to sync content from websites into a Chroma database, including steps for creating an account, setting up a database, and configuring web scraping parameters. # Docs - [Browsing Collections](https://docs.trychroma.com/docs/cli/browse): The page provides instructions on browsing collections using the Chroma CLI, detailing command arguments, usage scenarios for both cloud and local setups, and features of the Collection Browser UI, including navigation and search capabilities. - [Copy Chroma Collections](https://docs.trychroma.com/docs/cli/copy): The page explains how to use the Chroma CLI to copy collections between a local Chroma server and Chroma Cloud, detailing command arguments and examples for both transfer directions. - [DB Management on Chroma Cloud](https://docs.trychroma.com/docs/cli/db): The page explains how to manage databases on Chroma Cloud using the Chroma CLI, including commands for connecting, creating, deleting, and listing databases. - [Installing the Chroma CLI](https://docs.trychroma.com/docs/cli/install): The page provides instructions for installing the Chroma CLI, detailing methods for Python and JavaScript environments, as well as global installation options using cURL and Windows commands. - [Authenticating with Chroma Cloud](https://docs.trychroma.com/docs/cli/login): The page details the process of logging into Chroma Cloud using the Chroma CLI, including creating a profile and authenticating with a specific team account. - [Profile Management](https://docs.trychroma.com/docs/cli/profile): The page provides a guide on managing profiles in the Chroma CLI, covering commands for creating, deleting, listing, showing, renaming, and using profiles for authenticating with Chroma Cloud. - [Running a Chroma Server](https://docs.trychroma.com/docs/cli/run): The page explains how to run a Chroma server locally using the Chroma CLI and describes options for configuring the server along with providing examples of connecting to the server using `HttpClient` in Python and TypeScript. - [Sample Apps](https://docs.trychroma.com/docs/cli/sample-apps): The page provides information on how to use the CLI to install and set up Chroma's sample AI applications, including commands to install apps and list available samples. - [Update](https://docs.trychroma.com/docs/cli/update): The page explains how to use the `chroma update` command to check for updates to the Chroma CLI when using the Python or JavaScript packages. - [Vacuuming](https://docs.trychroma.com/docs/cli/vacuum): The page explains the process and considerations for vacuuming a Chroma database to optimize its size and performance, especially after upgrading from versions below v0.5.6. - [Adding Data to Chroma Collections](https://docs.trychroma.com/docs/collections/add-data): The page provides instructions on how to add data to Chroma collections using the `.add` method, including examples in Python and TypeScript, options for embedding documents, handling metadata, and considerations for re-adding data when IDs already exist. - [Configuring Chroma Collections](https://docs.trychroma.com/docs/collections/configure): The page explains how to configure Chroma collections for efficient embedding index construction and approximate nearest neighbor search, detailing customizable parameters for HNSW and SPANN indexes, as well as the integration of embedding functions within the configuration process. - [Deleting Data from Chroma Collections](https://docs.trychroma.com/docs/collections/delete-data): The page explains how to delete data from Chroma collections using the `.delete` method by specifying item `ids` and optional `where` filters, with code examples in Python and TypeScript. - [Managing Chroma Collections](https://docs.trychroma.com/docs/collections/manage-collections): The page covers managing Chroma collections, detailing how to create, retrieve, modify, and delete collections, as well as specifying embedding functions, metadata, and using convenience methods. - [Updating Data in Chroma Collections](https://docs.trychroma.com/docs/collections/update-data): The page explains how to update data in Chroma collections using the `.update` method and the `upsert` operation, including code examples and handling behaviors for missing IDs, embeddings, and documents. - [Embedding Functions](https://docs.trychroma.com/docs/embeddings/embedding-functions): The page details how to use embedding functions in Chroma, explaining their role in representing data for AI tools, providing a list of supported embedding providers and their integration options, and guiding users on setting default and custom embedding functions. - [Multimodal](https://docs.trychroma.com/docs/embeddings/multimodal): The page explains how to create and manage multimodal Chroma collections that can store and query data from multiple modalities, such as text and images, using the OpenCLIP embedding function and data loaders like ImageLoader. - [About](https://docs.trychroma.com/docs/overview/about): The page provides an overview of Chroma, including its open-source commitment, founding team, commercial strategy, and investors. - [Architecture](https://docs.trychroma.com/docs/overview/architecture): The page describes Chroma's modular architecture, including its deployment modes, core components, storage and runtime operations, and request handling sequences, with a focus on balancing performance, scalability, and cost-efficiency across different deployment contexts. - [Contributing](https://docs.trychroma.com/docs/overview/contributing): The page provides guidelines for contributing to Chroma, including submitting pull requests, creating Chroma Improvement Proposals (CIPs), and utilizing community resources like Discord for idea discussions. - [Chroma Data Model](https://docs.trychroma.com/docs/overview/data-model): The page describes Chroma's data model, focusing on core abstractions like Tenants, Databases, and Collections, and details how they are used for organizing, retrieving, and managing data efficiently. - [Getting Started](https://docs.trychroma.com/docs/overview/getting-started): The page provides a step-by-step guide for getting started with Chroma, an AI-native open-source vector database, including installation, client creation, collection management, querying, and next steps for both Python and TypeScript users. - [Chroma](https://docs.trychroma.com/docs/overview/introduction): The page introduces Chroma as an open-source AI application database that facilitates building LLM apps and provides features like storing embeddings, vector search, and document storage, along with installation instructions for Python and JavaScript/TypeScript clients. - [Migration](https://docs.trychroma.com/docs/overview/migration): The page provides information on schema and data format migrations in Chroma, detailing version-specific changes, how to adjust configurations, and available migration tools to ensure seamless transitions. - [Roadmap](https://docs.trychroma.com/docs/overview/roadmap): The page outlines Chroma's roadmap, highlighting current projects, recent completions, upcoming priorities, and areas open for community contributions. - [Telemetry](https://docs.trychroma.com/docs/overview/telemetry): The page describes Chroma's telemetry feature, its purpose, how to opt out, what data is collected, and where it is stored. - [Troubleshooting](https://docs.trychroma.com/docs/overview/troubleshooting): The page provides troubleshooting solutions for common issues encountered when using Chroma, including errors related to NextJS projects, HNSW index failures, SQLite version requirements, and platform-specific build errors. - [Full Text Search and Regex](https://docs.trychroma.com/docs/querying-collections/full-text-search): The page describes the use of full-text search and regular expressions for filtering document content in Chroma collections, providing examples for both Python and TypeScript. - [Metadata Filtering](https://docs.trychroma.com/docs/querying-collections/metadata-filtering): The page explains how to use metadata filtering in Chroma's `get` and `query` operations, including examples of using comparison, logical, and inclusion operators to filter records by metadata fields in Python and TypeScript. - [Query and Get Data from Chroma Collections](https://docs.trychroma.com/docs/querying-collections/query-and-get): The page explains how to query and retrieve data from Chroma collections, including using the `.query` and `.get` methods in Python and TypeScript for similarity searches, metadata filtering, and specifying returned data. - [Running Chroma in Client-Server Mode](https://docs.trychroma.com/docs/run-chroma/client-server): The page explains how to configure and use Chroma in client-server mode, providing instructions and examples for connecting with Python and TypeScript clients. - [Cloud Client](https://docs.trychroma.com/docs/run-chroma/cloud-client): The page explains how to use the `CloudClient` to connect to Chroma Cloud, including code examples in Python and TypeScript, and details on API key and environment variable configuration. - [Ephemeral Client](https://docs.trychroma.com/docs/run-chroma/ephemeral-client): The page explains how to use the `EphemeralClient()` in Python to run an in-memory Chroma server for experimentation without data persistence. - [Persistent Client](https://docs.trychroma.com/docs/run-chroma/persistent-client): The page explains how to configure a Persistent Client in Chroma for both Python and TypeScript, including saving and loading databases locally and connecting to a Chroma server. # Guides - [Agentic Memory](https://docs.trychroma.com/guides/build/agentic-memory): The page explains how to implement and utilize agentic memory in Chroma to persist data from agent runs for improved efficiency, personalization, and performance, detailing memory schemas, memory records, and implementation strategies within an agentic harness. - [Agentic Search](https://docs.trychroma.com/guides/build/agentic-search): The page discusses agentic search, a technique for enabling AI to intelligently use retrieval processes by planning, reasoning, and iterating, to handle complex queries over datasets like BrowseComp-Plus for more comprehensive and accurate results, highlighting the process of building such a search agent and providing a practical example. - [Building with AI](https://docs.trychroma.com/guides/build/building-with-ai): The page discusses how AI, particularly Large Language Models (LLMs), can be used as programming primitives to easily process unstructured information, such as extracting names from text, and describes how to integrate LLMs into software applications using APIs with examples in Python and TypeScript. - [Chunking](https://docs.trychroma.com/guides/build/chunking): The page explains the concept of chunking for Retrieval-Augmented Generation (RAG) in the Chroma framework, detailing various strategies for effectively splitting documents into smaller, meaningful pieces that can be retrieved based on relevance to improve the quality of responses from large language models. - [Introduction to Retrieval](https://docs.trychroma.com/guides/build/intro-to-retrieval): The page introduces the concept of retrieval in AI applications, addressing the limitations of large language models by explaining how retrieval systems like Chroma can be used to manage and query large knowledge bases effectively. - [Look at Your Data](https://docs.trychroma.com/guides/build/look-at-your-data): The page discusses strategies for examining and organizing data in Chroma collections, emphasizing search modalities, choosing appropriate embedding models, structuring collections, determining chunking methods, and leveraging metadata for improved retrieval and AI application responses. - [AWS Deployment](https://docs.trychroma.com/guides/deploy/aws): The page provides instructions for deploying Chroma on AWS using a CloudFormation template, including steps for setting up an AWS account, configuring credentials, launching a stack, setting up clients, cleaning up resources, and enabling observability with OpenTelemetry. - [Azure Deployment](https://docs.trychroma.com/guides/deploy/azure): The page provides instructions for deploying Chroma on Azure using Terraform, detailing the setup process, configuration, and observability options. - [Running Chroma in Client-Server Mode](https://docs.trychroma.com/guides/deploy/client-server-mode): The page explains how to run Chroma in client-server mode, including setup instructions for Python and TypeScript, and how to connect to the server using Chroma's `HttpClient` or `AsyncHttpClient` for Python and `ChromaClient` for TypeScript. - [Docker](https://docs.trychroma.com/guides/deploy/docker): The page provides instructions on how to run and configure a Chroma server in a Docker container, including using OpenTelemetry for observability and setting up a monitoring stack with Docker Compose. - [GCP Deployment](https://docs.trychroma.com/guides/deploy/gcp): The page provides detailed instructions for deploying Chroma on Google Cloud Platform (GCP) using Terraform, including setup, configuration, and hints for ensuring proper operation and security. - [Observability](https://docs.trychroma.com/guides/deploy/observability): The page describes how Chroma supports observability through OpenTelemetry, detailing configuration options for tracing and offering guides for observability across different deployment environments. - [Single-Node Chroma: Performance and Limitations](https://docs.trychroma.com/guides/deploy/performance): The page describes the performance characteristics and limitations of single-node Chroma, covering its deployment, memory and collection size constraints, query and insert latency, concurrency handling, and guidelines for optimizing insert throughput. - [Chroma's Thin-Client](https://docs.trychroma.com/guides/deploy/python-thin-client): The page explains how to use Chroma's lightweight client-only library, `chromadb-client`, for running in client-server mode in a Python application, detailing installation methods and noting its minimal dependencies compared to the full `chromadb` package. # Integrations - [Integrations](https://docs.trychroma.com/integrations/chroma-integrations): The page details Chroma's available embedding and framework integrations, listing various AI tools and libraries that can be used with Python and JavaScript for creating embeddings and integrating business logic into applications. - [Amazon Bedrock](https://docs.trychroma.com/integrations/embedding-models/amazon-bedrock): The page describes how to use Chroma's wrapper for the Amazon Bedrock embedding API, including how to configure it with AWS credentials using the `boto3` Python package. - [Baseten](https://docs.trychroma.com/integrations/embedding-models/baseten): The page describes how to use Baseten, a model inference provider, to deploy and integrate embedding models with Chroma, including setup instructions for using Baseten Embedding Inference with the OpenAI SDK. - [Chroma BM25](https://docs.trychroma.com/integrations/embedding-models/chroma-bm25): The page describes Chroma's built-in BM25 sparse embedding function for relevance ranking of documents, including implementation details and customizable parameters for both Python and TypeScript. - [Chroma Cloud Qwen](https://docs.trychroma.com/integrations/embedding-models/chroma-cloud-qwen): The page explains how to use Chroma Cloud's Qwen embedding API with Chroma's wrapper in Python and Typescript, including code examples and API key requirements. - [Chroma Cloud Splade](https://docs.trychroma.com/integrations/embedding-models/chroma-cloud-splade): The page details the use of Chroma Cloud's Splade sparse embedding API for retrieval tasks, including setup instructions and code examples for both Python and TypeScript. - [Cloudflare Workers AI](https://docs.trychroma.com/integrations/embedding-models/cloudflare-workers-ai): The page provides information on using Chroma's wrapper for Cloudflare Workers AI embedding models, including setup instructions and code examples in Python and TypeScript. - [Cohere](https://docs.trychroma.com/integrations/embedding-models/cohere): The page explains how to use Chroma's convenient wrapper for Cohere's embedding API, including examples in Python and TypeScript for using text and multilingual embeddings, as well as a multimodal embeddings example. - [Google Gemini](https://docs.trychroma.com/integrations/embedding-models/google-gemini): The page provides a guide on how to use Chroma's wrapper for Google's Generative AI embedding API, detailing setup and usage instructions for both Python and TypeScript environments. - [Hugging Face Server](https://docs.trychroma.com/integrations/embedding-models/hugging-face-server): The page provides information on setting up and using the Hugging Face Server for text embeddings with Chroma, including installation, configuration, and authentication instructions. - [Hugging Face](https://docs.trychroma.com/integrations/embedding-models/hugging-face): The page describes how to use Chroma's wrapper around Hugging Face's embedding API, including how to authenticate with an API key and select models. - [Instructor](https://docs.trychroma.com/integrations/embedding-models/instructor): The page provides information about using the instructor-embeddings library for local text embeddings with a GPU, detailing model options, installation, and implementation examples. - [JinaAI](https://docs.trychroma.com/integrations/embedding-models/jina-ai): The page explains how to use Chroma's wrapper around Jina AI's embedding API, detailing the setup of embedding functions with examples in Python and TypeScript, and describing advanced features like late chunking and task-specific adaptations. - [Mistral](https://docs.trychroma.com/integrations/embedding-models/mistral): The page describes how to use Chroma's wrapper around Mistral's embedding API for embedding functions, including installation and code examples in Python and TypeScript. - [Morph](https://docs.trychroma.com/integrations/embedding-models/morph): The page provides details on using Chroma's wrapper for Morph's embedding API, including instructions for Python and TypeScript integration. - [Nomic](https://docs.trychroma.com/integrations/embedding-models/nomic): The page describes how to use Chroma's wrapper for Nomic's embedding API, detailing installation, configuration, and usage of the `NomicEmbeddingFunction` in Python. - [Ollama](https://docs.trychroma.com/integrations/embedding-models/ollama): The page describes how to use Chroma's wrapper for Ollama's embeddings API via the `OllamaEmbeddingFunction` to generate document embeddings in both Python and TypeScript. - [OpenCLIP](https://docs.trychroma.com/integrations/embedding-models/open-clip): The page describes Chroma's wrapper for the OpenCLIP library, which supports local text and image embeddings for multimodal applications, along with installation instructions and usage examples in Python. - [OpenAI](https://docs.trychroma.com/integrations/embedding-models/openai): This page explains how to use Chroma's wrapper around OpenAI's embedding API, detailing supported models, setup, and usage instructions for both Python and TypeScript. - [Roboflow](https://docs.trychroma.com/integrations/embedding-models/roboflow): The page explains how to use Roboflow Inference to calculate multi-modal text and image embeddings with the `RoboflowEmbeddingFunction` class in Chroma, detailing both cloud and local setup options. - [Sentence Transformer](https://docs.trychroma.com/integrations/embedding-models/sentence-transformer): The page describes Chroma's integration with Sentence Transformers, detailing how to use their Python and TypeScript wrappers for generating embeddings using pre-trained models from Hugging Face. - [Text2Vec](https://docs.trychroma.com/integrations/embedding-models/text2vec): The page describes how to use Chroma's wrapper for the Text2Vec library to run local embeddings, specifically optimized for Chinese text, using the `text2vec` Python package. - [Together AI](https://docs.trychroma.com/integrations/embedding-models/together-ai): The page describes how to use Chroma's wrapper for Together AI embedding models with Python and TypeScript, including setup instructions and code examples. - [VoyageAI](https://docs.trychroma.com/integrations/embedding-models/voyageai): The page provides instructions for using Chroma's wrapper for VoyageAI's embedding API, including installation and usage examples in Python and TypeScript, as well as a multilingual model example. - [Anthropic MCP Integration](https://docs.trychroma.com/integrations/frameworks/anthropic-mcp): The page details the integration of Anthropic's Model Context Protocol (MCP) with Chroma, including setup instructions for the Chroma MCP server, client types, and examples of usage scenarios such as team knowledge bases and project memory with Claude. - [Braintrust](https://docs.trychroma.com/integrations/frameworks/braintrust): The page describes Braintrust, an enterprise-grade tool for AI product development that integrates with Chroma, and provides a Python script to evaluate a Chroma Retrieval app using Braintrust. - [Contextual AI](https://docs.trychroma.com/integrations/frameworks/contextual-ai): The page provides an overview of Contextual AI, detailing its enterprise-grade components for building production RAG agents with document parsing, reranking, generation, and evaluation capabilities integrated with Chroma as the vector database. - [DeepEval](https://docs.trychroma.com/integrations/frameworks/deepeval): The page provides a guide on using DeepEval to evaluate and optimize Chroma retriever systems with metrics and visualization tools, including installation, test case preparation, and evaluation steps. - [Haystack](https://docs.trychroma.com/integrations/frameworks/haystack): The page provides an overview of using Haystack, an open-source LLM framework, with Chroma as a vector database, including installation instructions, example usage for document storage and building retrieval-augmented generation pipelines. - [Langchain](https://docs.trychroma.com/integrations/frameworks/langchain): The page provides links and resources related to integrating Langchain with Chroma, including tutorials, demos, and documentation for both Python and JavaScript. - [LlamaIndex](https://docs.trychroma.com/integrations/frameworks/llamaindex): The page provides links to the LlamaIndex vector store page, a demo, and a Chroma Loader on Llamahub. - [Mem0](https://docs.trychroma.com/integrations/frameworks/mem0): The page introduces Mem0, an AI memory layer for creating stateful AI systems with persistent memory, and covers its installation, configuration with Chroma, and basic usage examples, as well as potential use cases for personalized assistants and other applications. - [OpenLIT](https://docs.trychroma.com/integrations/frameworks/openlit): The page introduces OpenLIT, an OpenTelemetry-native LLM application observability tool, provides installation and initialization instructions, and guides on visualizing data for performance optimization. - [OpenLLMetry](https://docs.trychroma.com/integrations/frameworks/openllmetry): The page describes OpenLLMetry, a tool that provides observability for systems using Chroma by allowing tracing of calls to Chroma, OpenAI, and other services. - [Streamlit](https://docs.trychroma.com/integrations/frameworks/streamlit): The page introduces Streamlit, explaining its installation, integration with Chroma via `streamlit-chromadb-connection`, and provides examples and resources for creating web apps within machine learning and data science contexts. - [VoltAgent](https://docs.trychroma.com/integrations/frameworks/voltagent): The page provides a guide on setting up and using VoltAgent, a TypeScript framework for AI agents, with Chroma for efficient AI application development, including installation steps, configuration, running an application, and implementing a retriever class for integrating semantic search capabilities. # Reference - [Chroma Reference](https://docs.trychroma.com/reference/chroma-reference): The page provides a reference for Chroma's Client APIs for Python and Javascript, and instructions on accessing the backend Swagger REST API documentation. - [JS Client](https://docs.trychroma.com/reference/js/client): The page provides an overview of the JavaScript/TypeScript client for Chroma, detailing the `ChromaClient` class, its constructor, and methods for managing collections and interacting with the Chroma API. - [Class: Collection](https://docs.trychroma.com/reference/js/collection): The page provides detailed documentation for the Collection class in JavaScript/TypeScript, outlining its properties and various methods such as add, count, delete, get, modify, peek, query, search, update, and upsert, along with examples and parameter descriptions. - [Python Client](https://docs.trychroma.com/reference/python/client): The page describes various Python client methods and classes for interacting with Chroma, including configuration, different client types (e.g., EphemeralClient, PersistentClient, AsyncHttpClient), client methods for manipulating collections, and admin client methods for database and tenant management. - [Python Collection](https://docs.trychroma.com/reference/python/collection): The page describes the Python `Collection` class in the Chroma documentation, detailing its methods for managing embeddings in a data store, including operations for counting, adding, retrieving, querying, modifying, updating, upserting, and deleting embeddings.