Skip to content

Instantly share code, notes, and snippets.

@pzarzycki
Created October 9, 2025 03:00
Show Gist options
  • Save pzarzycki/b260d774e69e6e3de9848b3690e23391 to your computer and use it in GitHub Desktop.
Save pzarzycki/b260d774e69e6e3de9848b3690e23391 to your computer and use it in GitHub Desktop.
# Install dependencies first (if not already installed):
# pip install chromadb sentence-transformers
import chromadb
from chromadb.utils import embedding_functions
# 1. Create or connect to a local ChromaDB client
client = chromadb.Client()
# 2. Define an embedding function (using a small local model)
embedding_func = embedding_functions.SentenceTransformerEmbeddingFunction(
model_name="all-MiniLM-L6-v2"
)
# 3. Create a collection (like a table)
collection = client.create_collection(name="my_collection", embedding_function=embedding_func)
# 4. Add some documents
collection.add(
ids=["doc1", "doc2", "doc3"],
documents=[
"Chroma is a database for embeddings.",
"OpenAI builds powerful language models.",
"Python is a versatile programming language."
]
)
# 5. Run a similarity search
results = collection.query(
query_texts=["What is Chroma?"],
n_results=2
)
print(results)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment