Meta tags:
description=Open-source search infrastructure for AI;

Headings (most frequently used words):

and, open, source, search, infrastructure, hidden, for, ai, fast, serverless, scalable, supporting, vector, full, text, regex, metadata, built, on, object, storage, trusted, by, millions, of, developers, apache, product, follow, company, legal,

Text of the page (most frequently used words):
#search (35), and (30), chroma (27), with (20), for (16), your (15), the (13), 2025 (12), open (11), #source (10), context (10), cloud (9), vector (9), query (9), collection (9), data (8), sparse (8), metadata (8), github (7), 2026 (7), read (7), support (7), fast (7), storage (7), engineering (7), docs (6), full (6), our (6), object (6), bm25 (6), sync (5), are (5), performance (5), vectors (5), community (5), over (5), ops (5), multi (5), document (5), database (4), started (4), get (4), team (4), regex (4), write (4), built (4), jan (4), results (4), research (4), all (4), discord (4), infrastructure (4), vpc (4), text (4), indexes (4), per (4), documents (4), score (4), about (3), youtube (3), contact (3), mcp (3), enterprise (3), start (3), free (3), javascript (3), typescript (3), python (3), see (3), join (3), using (3), new (3), aug (3), collections (3), log (3), splade (3), keys (3), control (3), indexing (3), serverless (3), updates (3), embedding (3), retrieval (3), agent (3), run (3), what (3), databases (3), build (3), apache (3), tiering (3), latency (3), embeddings (3), const (3), security (2), changelog (2), status (2), package (2), install (2), chromadb (2), getting (2), people (2), who (2), dedicated (2), class (2), jun (2), client (2), boost (2), throughput (2), execution (2), engine (2), rust (2), designing (2), introducing (2), copy (2), forking (2), sep (2), repos (2), ahead (2), oct (2), automatically (2), chunk (2), embed (2), index (2), web (2), own (2), encryption (2), managed (2), time (2), arrays (2), evaluating (2), chunking (2), strategies (2), systems (2), how (2), input (2), rot (2), ensure (2), plan (2), direct (2), help (2), system (2), from (2), engineers (2), stars (2), you (2), need (2), large (2), more (2), scale (2), lexical (2), videos (2), byoc (2), region (2), replication (2), plane (2), hidden (2), scalable (2), memory (2), automatic (2), pricing (2), scales (2), layer (2), cache (2), warm (2), cold (2), records (2), qps (2), specific (2), can (2), billions (2), tenant (2), id1 (2), id2 (2), tutorial (2), await (2), sparserank (2), add (2), 27k (2), knowledge_base (2), case (2), study (2), resources (2), products (2), dpa, terms, privacy, legal, careers, company, follow, product, view, documentation, npm, pip, quick, running, seconds, less, credits, roles, looking, curious, becoming, world, their, craft, complete, rewrite, reduced, bundle, size, regular, expressions, operators, jul, base64, encoding, increase, push, based, morsel, driven, now, generally, available, duplication, thousands, through, wal3, first, nov, crawl, scrape, pages, dec, encrypt, customer, group, aggregate, groupby, secure, connectivity, aws, privatelink, private, networking, consistency, only, modes, level, monitor, real, progress, feb, store, strings, numbers, booleans, mar, ingestion, project, rapidly, improving, here, latest, lightweight, transforms, accuracy, adapters, methods, generative, benchmarking, increasing, tokens, impacts, llm, training, self, editing, spans, both, basic, applied, agents, customized, slas, gets, assistance, slack, communication, iterating, pro, helpful, plans, 10k, person, strong, expert, deployment, guides, oss, find, greater, social, building, has, 26k, used, 90k, other, codebases, downloaded, 11m, times, month, give, flexibility, exactly, licensing, limits, vendor, lock, just, reliable, backed, visit, channel, dspy, reliability, outer, loop, long, live, beyond, episode, lance, martin, langchain, schema, apis, deep, dive, reranking, improve, monitoring, backups, management, learn, point, recovery, resilient, same, story, brings, compliance, education, operational, model, enterprises, architecture, not, expensive, 1gb, 15gb, takes, advantage, aware, caching, manual, tuning, auto, usage, unlike, legacy, want, call, hot, ssd, intelligent, gcs, zero, infra, 100, recall, 200, concurrent, reads, 2000, technical, specs, poc, workload, clusters, scaled, requirements, 57ms, p99, 27ms, p90, 650ms, 20ms, p50, 384, dim, 100k, optimized, offering, unparalleled, cost, state, art, node, connecting, connected, successfully, creating, my_collection, created, adding, added, querying, completed, 18ms, ranked, terminal, output, select, limit, rank, execute, sparse_embedding, key, knn, ids, configure, command, line, tools, development, cli, dataset, versioning, testing, roll, outs, filtering, faceted, trigram, semantic, similarity, features, traffic, soc, type, cheaper, 10x, queries, low, monthly, downloads, 15m, awaiting, 277, 467, does, else, uses, ask, question, app, locally, supporting, trusted, millions, developers, sign, use, cases,

Text of the page (random words):
chroma open source search infrastructure for ai products products sync database agent docs research resources resources use cases updates videos changelog discord github support hidden pricing 27k log in sign up open source search infrastructure for ai fast serverless and scalable infrastructure supporting vector full text regex and metadata search built on object storage and trusted by millions of developers open source apache 2 0 start free on cloud read the docs or get started locally read case study read case study agent search ai app ask a question what can i build with chroma who else uses chroma how does chroma scale knowledge_base chroma knowledge_base 1 277 467 records awaiting query input 15m monthly downloads apache 2 0 27k github stars low latency search fast queries over billions of multi tenant indexes up to 10x cheaper built on object storage with automatic data tiering no engineering ops scales with your data and traffic soc 2 type ii features sparse vector search lexical search bm25 splade vector search semantic similarity search full text search trigram and regex search metadata search filtering and faceted search forking dataset versioning a b testing and roll outs cli command line tools for development typescript python rust copy configure client and collection for sparse embeddings bm25 splade add documents with sparse embeddings bm25 await collection add ids id1 id2 documents document about databases ml tutorial query with sparse vector const sparserank knn query ml key sparse_embedding build and execute search const search new search rank sparserank limit 10 select k document k score const results await collection search search terminal output node sparse search js connecting to chroma connected successfully creating collection my_collection collection created adding documents with sparse embeddings bm25 added 2 documents querying with sparse vector query completed in 18ms results ranked by bm25 score id id1 document document about databases score 0 87 metadata id id2 document ml tutorial score 0 45 metadata performance fast search over billions of multi tenant indexes chroma s indexes are built and optimized for object storage offering unparalleled cost and performance state of the art vector full text and regex search latency query latency 384 dim at 100k vectors warm cold p50 20ms 650ms p90 27ms 1 2s p99 57ms 1 5s contact us to run a poc for your specific workload dedicated clusters can be scaled to your specific requirements technical specs write throughput per collection 30 mb s 2000 qps concurrent reads per collection 10 200 qps collections per database 1m records per collection 5m recall 90 100 zero ops infra query layer fast memory cache hot ssd cache warm intelligent tiering storage layer s3 gcs cold all vectors all metadata all indexes unlike legacy search systems chroma is a database you ll want to be on call for auto scales with usage no manual tuning serverless pricing chroma takes full advantage of object storage with automatic query aware data tiering and caching vectors are large 1gb text 15gb of vectors memory is expensive 5 gb mo object storage is not 0 02 gb mo enterprise chroma brings the security compliance education and operational model enterprises need with our apache 2 0 architecture byoc in your vpc multi cloud multi region replication point in time recovery ensure a resilient and scalable search system with the same 0 ops story as cloud learn more contact us hidden your vpc data plane your data your cloud chroma vpc control plane managed by chroma monitoring backups ops byoc in your vpc multi region replication 0 ops management videos deep dive using reranking to improve search results 15 23 chroma context 1 13 20 lexical search in chroma 4 41 schema and search apis 9 02 context engineering episode 3 lance martin langchain 1 02 36 beyond the embedding vector indexing 11 26 long live context engineering 57 00 context rot 7 55 context engineering the outer loop 23 43 context engineering for engineers 11 16 reliability at scale 26 30 context engineering with dspy 12 46 see more visit our youtube channel open source community open source databases give your team the control and flexibility to build exactly what you need no licensing limits no vendor lock in just reliable performance backed by a large community github chroma has over 26k github stars and is used in over 90k other open source codebases on github it is downloaded over 11m times a month discord join the discord to see what people are building social find the greater community on x and youtube run chroma oss run chroma on your own infrastructure with our open source deployment guides support open source join our 10k person strong discord community to get fast and expert help from the open source community all plans helpful support direct from engineers on the chroma team pro plan direct slack communication for fast support and help designing and iterating your search system enterprise plan customized slas ensure your team gets 24 7 assistance research our research spans both basic and applied research for search retrieval agents and context engineering context 1 training a self editing search agent context rot how increasing input tokens impacts llm performance generative benchmarking new methods for evaluating retrieval systems chunking strategies evaluating chunking strategies in retrieval for ai embedding adapters lightweight transforms to boost embedding accuracy updates chroma s project is rapidly improving here are the latest updates chroma cloud sync serverless data ingestion for chroma cloud mar 2026 metadata arrays store arrays of strings numbers and booleans in metadata feb 2026 indexing status monitor real time indexing progress of your collections jan 2026 read level control read consistency with index only or full read modes jan 2026 private networking secure connectivity with aws privatelink support jan 2026 groupby group and aggregate search results by metadata keys jan 2026 customer managed encryption keys encrypt your data with your own encryption keys dec 2025 chroma web sync automatically crawl scrape chunk and embed web pages nov 2025 sparse vector search first class support for bm25 and splade vectors oct 2025 introducing chroma sync automatically chunk embed and index github repos oct 2025 wal3 chroma s write ahead log a write ahead log for chroma built on object storage sep 2025 package search mcp query thousands of open source repos through mcp sep 2025 collection forking fast duplication of collections with copy on write aug 2025 introducing chroma cloud chroma cloud is now generally available aug 2025 designing a query execution engine a push based morsel driven execution engine in rust aug 2025 70 data throughput increase performance boost using base64 vector encoding jul 2025 regex search support search using regular expressions with new operators jun 2025 javascript client v3 complete rewrite with reduced bundle size jun 2025 we re looking for curious people who are dedicated to becoming world class at their craft to join our team see open roles get started get up and running in 30 seconds or less with 5 in free credits quick start python python getting started docs pip install chromadb javascript typescript javascript typescript getting started docs npm install chromadb view full documentation start free on cloud read the docs 2026 product database sync enterprise package search mcp docs status contact follow github x youtube company about changelog careers legal privacy terms security dpa