Returns semantically similar content based on the input query
cURL
curl --request POST \ --url https://api.liquidindex.dev/query/project \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data ' { "project_id": "<string>", "query": "<string>", "top_k": 5 } '
{ "results": { "chunks": [ { "score": 123, "content": "<string>", "metadata": { "id": "<string>", "file": "<string>", "source": "<string>", "type": "<string>" } } ], "llm": "<string>" }, "usage": { "read_units": 123, "embedding_units": 123 } }
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Bearer <token>
<token>
The Project ID to query from
The input text used to find similar matches
Number of matches to return
Successful query response
Show child attributes
Similarity score of the matched content
The matched content
Additional information about the matched content
Unique identifier of the content
Source file name
Content source (e.g., Google Docs, Notion)
Content type (e.g., TEXT, IMAGE, VIDEO)
LLM generated response based on the query and chunks
Number of read units consumed
Number of embedding units consumed