Launching regex search support

You can now search in Chroma using regular expressions.

Regex search enables you to:

Use case	Example regex
Identify function calls in code	`\b\w+\(`
Find email addresses inside any document	`[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}`
Extract TODO comments in code	`TODO[: ]`
Locate US phone numbers	`$?\d{3}$?[-.\s]?\d{3}[-.\s]?\d{4}`
Check for URLs	`https?://[^\s]+`

API#

To run a regex search, apply the $regex or $not_regex operator on the where_document field in a .query or .get.

Example#

Here is an example in Python:

python

# pip install chromadb
import chromadb
client = chromadb.Client()
collection = client.get_or_create_collection("code_snippets")
collection.add(
    ids=["1", "2", "3"],
    documents=[
        "def add(a, b): return a + b",
        "numbers_doubled = list(map(lambda x: x * 2, numbers))",
        "print('Hello, world!')"
    ]
)
func_regex = r"^\s*def\s+\w+\("
matched = collection.get(where_document={"$regex": func_regex})
print(f"Snippets with a function definition: {matched['documents']}")
non_matched = collection.get(where_document={"$not_regex": func_regex})
print(f"Snippets without a function definition: {non_matched['documents']}")

Regex support is also now directly supported in the Chroma Cloud UI.

Regex demo in Chroma Cloud

(This example searches for numbers with significant digits)

Learn more on the Chroma docs →

Launching regex search support

API#

Example#

Product

Follow

Company

Legal