For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
PlaygroundDiscordStatusDashboardSign Up >
DocumentationSDK ReferenceGraphiti
DocumentationSDK ReferenceGraphiti
  • SDK Reference
        • GETGets a list of DocumentCollections
        • GETGets a DocumentCollection
        • POSTCreates a new DocumentCollection
        • DELDeletes a DocumentCollection
        • PATCHUpdates a DocumentCollection
        • POSTCreates Multiple Documents in a DocumentCollection
        • POSTBatch Deletes Documents from a DocumentCollection by UUID
        • POSTBatch Gets Documents from a DocumentCollection
        • PATCHBatch Updates Documents in a DocumentCollection
        • GETGets a Document from a DocumentCollection by UUID
        • DELDelete Document from a DocumentCollection by UUID
        • PATCHUpdates a Document
        • POSTSearches Documents in a DocumentCollection
LogoLogo
PlaygroundDiscordStatusDashboardSign Up >
SDK ReferenceDeprecatedDocument

Searches Documents in a DocumentCollection

Deprecated
POST
https://api.getzep.com/api/v2/collections/:collectionName/search
POST
/api/v2/collections/:collectionName/search
$curl -X POST https://api.getzep.com/api/v2/collections/collectionName/search \
> -H "Authorization: <apiKey>" \
> -H "Content-Type: application/json" \
> -d '{}'
1{
2 "current_page": 1,
3 "query_vector": [
4 1.1
5 ],
6 "result_count": 1,
7 "results": [
8 {
9 "content": "string",
10 "created_at": "string",
11 "document_id": "string",
12 "embedding": [
13 1.1
14 ],
15 "is_embedded": true,
16 "metadata": {},
17 "score": 1.1,
18 "updated_at": "string",
19 "uuid": "string"
20 }
21 ],
22 "total_pages": 1
23}
Searches over documents in a collection based on provided search criteria. One of text or metadata must be provided. Returns an empty list if no documents are found.
Was this page helpful?
Previous
Built with

Path parameters

collectionNamestringRequired
Name of the Document Collection

Query parameters

limitintegerOptional
Limit the number of returned documents

Request

Search criteria
metadatamap from strings to anyOptional
Document metadata to filter on.
min_scoredoubleOptional
mmr_lambdadoubleOptional
The lambda parameter for the MMR Reranking Algorithm.
search_typeenumOptional
The type of search to perform. Defaults to "similarity". Must be one of "similarity" or "mmr".
Allowed values:
textstringOptional
The search text.

Response

OK
current_pageinteger
query_vectorlist of doubles
result_countinteger
resultslist of objects
total_pagesinteger

Errors

400
Bad Request Error
401
Unauthorized Error
500
Internal Server Error