Collection

Properties

Name	Type	Description	Notes
id	str	A unique identifier of the collection
name	str	Name of the collection
description	str	Description of the collection
embedding_model	str
document_count	int	A number of documents in the collection
document_size	int	Total size in bytes of all documents in the collection
created_at	datetime	Time when the collection was created
updated_at	datetime	Last time when the collection was modified
user_count	int	A number of users having access to the collection
is_public	bool	Is publicly accessible
username	str	Name of the user owning the collection
sessions_count	int	A number of chat sessions with the collection
status	str	Status of the collection
prompt_template_id	str	A unique identifier of a prompt template associated with the collection.	[optional]
thumbnail	str	A file name of a thumbnail image.	[optional]
size_limit	int	Maximum size of data that could be contained in the collection.	[optional]
expiry_date	datetime	An expiry date	[optional]
inactivity_interval	int	The inactivity interval as an integer number of days.	[optional]
rag_type	str	RAG type options: * `auto` - Automatically select the best rag_type. * `llm_only` LLM Only - Answer the query without any supporting document contexts. Requires 1 LLM call. * `rag` RAG (Retrieval Augmented Generation) - Use supporting document contexts to answer the query. Requires 1 LLM call. * `hyde1` LLM Only + RAG composite - HyDE RAG (Hypothetical Document Embedding). Use ‘LLM Only’ response to find relevant contexts from a collection for generating a response. Requires 2 LLM calls. * `hyde2` HyDE + RAG composite - Use the ‘HyDE RAG’ response to find relevant contexts from a collection for generating a response. Requires 3 LLM calls. * `rag+` Summary RAG - Like RAG, but uses more context and recursive summarization to overcome LLM context limits. Keeps all retrieved chunks, puts them in order, adds neighboring chunks, then uses the summary API to get the answer. Can require several LLM calls. * `all_data` All Data RAG - Like Summary RAG, but includes all document chunks. Uses recursive summarization to overcome LLM context limits. Can require several LLM calls.	[optional]
metadata_dict	Dict[str, object]		[optional]

Example

from h2ogpte.rest_async.models.collection import Collection

# TODO update the JSON string below
json = "{}"
# create an instance of Collection from a JSON string
collection_instance = Collection.from_json(json)
# print the JSON string representation of the object
print(Collection.to_json())

# convert the object into a dict
collection_dict = collection_instance.to_dict()
# create an instance of Collection from a dict
collection_from_dict = Collection.from_dict(collection_dict)