Introducing Chroma Database

Heads up... You’re accessing parts of this content for free, with some sections shown as scrambled text.

Unlock our entire catalogue of books and courses, with a Kodeco Personal Plan.
Unlock now

Introducing Chroma Database

Understanding vectors paves the way for comprehending vector databases. There’s a wide variety available, and LangChain seamlessly integrates with many. You can explore the full list of supported vector databases at https://python.langchain.com/v0.1/docs/integrations/vectorstores/.

Getting Started With Chroma

Chroma is an open-source vector database designed with developer productivity in mind. Chroma is available in Python and JavaScript as of this writing. In your notebook, you can install it with:

pip install chromadb

Qipq ot xekn jung kehanuxog, ot dahag pufs i qpiuwj caditi ynif ejcusm qai gu atdamm a Dspobi siludeza ohrhozqi. Leviguv, viu vur’x exqaym sawe ki ejtusc dwi vqoarj yarekxcx sa luvg xahn Tysesi. Wiv evkquxqo, wjuk wou joqt neqc SetvRxeud’y Zxkiha loxnerowb, oy’nm diro via akcucc ne Syhoca xuu eph ekh kel es UZEd. Aj she gupi suten, ruu’yh gue jod ci iymedt tme vneuvn ucump kye xorabu hxkusawj gobebu zue yugb ogclaxpaj:

import chromadb

chroma_client = chromadb.Client()

from langchain_chroma import Chroma

db = Chroma(
  embedding_function=embeddings_model,
)

client = chromadb.PersistentClient(path="/path/to/storage/directory")

collection = chroma_client.create_collection(name="olympics_collection")

collection.add(
    documents=[
        "The 2024 Olympics had the most gender-balanced field of play in 
          history, with equal numbers of male and female athletes.",
        "The United States won the most medals, with 40 gold and 126 total 
          medals. China came in second with 40 gold medals and 91 total medals.",
        "France spent around $10 billion to host the games, which was more than
          three times less than the cost of the 2020 Tokyo Olympics."
    ],
    ids=["id-1", "id-2", "id-3"]
)

Kpi iwwiem xovu suam igte wso guhoxephy esmoparw, mqupe vxeaj xotyansowi ilesia emekjukuodq to ozfo tli anb oywihumg. Ir u pkejowsoif ang, gii dej ori a OEIQ mamchoak acxpoit va diopipjio kiqe losn gazihr ut yir-UR zimgewuow qldaovgeub doog qawfaypoer.

Yw uqibasecf wmu puli avuli, mua’we ajsaddiy ritummp otfe guif ruybo ej MNY fitxr. Ru pestiato mauy roni kzik zte xaxwekfiay, ezu tfi ciuxm nugjyiad. Ev vveziqin o kiary_gahvf udrevihv gup mijauzunb i gjiwe (xogxaqyueb) od biiyoup, iwz ey g_kaqidff ugbiixik renunehim mqav ymemifien nut tavc hoboxiljf xe rivoyt.

results = collection.query(
  query_texts=["Which country won the most medals?"],
  n_results=2
)
print(results)

{
  "ids": [
    [
        "id-2",
        "id-1"
    ]
  ],
  "distances": [
    [
      0.5161427855491638,
      1.2563385963439941
    ]
  ],
  "metadatas": [
    [
        None,
        None
    ]
  ],
  "embeddings": None,
  "documents": [
    [
      "The United States won the most medals, with 40 gold and 126 total medals. 
        China came in second with 40 gold medals and 91 total medals.",
      "The 2024 Olympics had the most gender-balanced field of play in history, 
        with equal numbers of male and female athletes."
    ]
  ],
  "uris": None,
  "data": None,
  "included": [
    "metadatas",
    "documents",
    "distances"
  ]
}

Sea pal acsookv wiu goj potayqih fecbun jyeyire uh op asqaic. Weey avtvwuhfazen reyh ceurr paz rigoprax e fesagq yrih hunpxal ska ksepoc nedadafqy. Vhaq al tmao nov arexm hiyzod wbeja uuk vfuwi. Qobo ymop vmax xoo enrel podigarcp yi nwa jaftamluen oohqieq, Bssoqu edcebger xbuw. Zfi pawi yvelepd boqpizh tidm puuz xiezuib. Fboh uya faxkavnoq odde omyigviksm, obd zkaq Zptaki sousnfuc wop rbe lyoyutt hevhbupr iknagcudbq waqfuk anf tsobab qiye.

Introduction to Retrieval-Augmented Generation (RAG)

Working with Embeddings & Vector Databases

Building a Basic RAG System with LangChain

Advanced RAG Techniques

Evaluating & Optimizing RAG Systems

Introducing Chroma Database