Create a superior search experience

AI-powered hybrid search combines best-in-class full-text search and semantic search capabilities

Learn More

Back to the Future

Feel-good Sci-Fi classics

Full-text Search

Semantic Search

Hybrid Search

Back to the Future II

1989

Back to the Future

1985

Back to the Future III

1990

Take full control of your search setup for optimal results

Adjust your semantic ratio to achieve the ideal balance between AI-powered semantic search and full-text search capabilities.

Full-text search ➜

Best when you know precisely what to look for

Semantic search ➜

Ideal when searching for concepts instead of focusing solely on words

✨ Hybrid search

Combine the best of both worlds

The easiest path to creating a top-notch search experience

Generate AI embedders

Generate vector embeddings using a third party, or submit your locally generated embeddings. - Open AI embedders - 🆕 Open source embedders - Provide own embeddings

Learn more

Prompting made better

Add a prompt template of key information to help ingest prompts and help the model interpret relevant metadata from the get-go.

Learn more

NEW

Configure your semantic ratio

Choose where you want your results to fall on the spectrum from pure keyword-based to fully semantic search.

Learn more

Search enters your AI application stack

Meilisearch comes with tailored SDKs for your favorite framework or language.

from langchain.vectorstores import Meilisearch
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.document_loaders import JSONLoader  

# Load documents 
loader = JSONLoader(
     file_path="./movies.json",
     jq_schema=".[] | {id: .id, title: .title, overview: .overview}",
     text_content=False,
) 
documents = loader.load()  

# Index documents
embeddings = OpenAIEmbeddings()
vector_store = Meilisearch.from_documents(documents=documents, embedding=embeddings)

# Search
query = "superhero fighting villains in a city corrupted by crime"
results = vector_store.similarity_search(
     query=query,
     k=3,
)