Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.transluce.org/llms.txt

Use this file to discover all available pages before exploring further.

Collections support arbitrary key-value metadata. Updates use deep merge — nested dictionaries are merged recursively, preserving existing keys. See Metadata for more on how metadata works in Docent.

​
Get Metadata

from docent import Docent

client = Docent()

metadata = client.get_collection_metadata("my-collection-id")
print(metadata)  # {"team": "support", "model": "gpt-4"}

​
Parameters

​
collection_id
str
required
ID of the collection.

​
Returns

​
metadata
dict
The collection’s metadata dictionary.

​
Update Metadata

Updates are deep-merged into existing metadata. Existing keys not in the update are preserved. 
# Existing metadata: {"team": "support", "config": {"model": "gpt-4"}}

client.update_collection_metadata("my-collection-id", {
    "config": {"temperature": 0.7},
    "version": "v2",
})

# Result: {"team": "support", "config": {"model": "gpt-4", "temperature": 0.7}, "version": "v2"}

​
Parameters

​
collection_id
str
required
ID of the collection.
​
metadata
dict
required
Metadata to merge into the existing metadata.

​
Returns

​
metadata
dict
The full merged metadata dictionary after the update.

​
Delete Metadata Keys

Remove specific keys from metadata. Supports dot-delimited paths for nested deletion. 
# Existing metadata: {"team": "support", "config": {"model": "gpt-4", "temperature": 0.7}}

metadata, not_found = client.delete_collection_metadata_keys(
    "my-collection-id",
    keys=["config.temperature", "nonexistent_key"],
)

print(metadata)    # {"team": "support", "config": {"model": "gpt-4"}}
print(not_found)   # ["nonexistent_key"]

​
Parameters

​
collection_id
str
required
ID of the collection.
​
keys
list[str]
required
Keys to remove. Use dot notation for nested keys (e.g., "config.model").

​
Returns

Returns a tuple of two values:
​
metadata
dict
The metadata dictionary after deletion.
​
not_found
list[str]
Keys that were not found in the metadata.