Search Memories & Documents in Project

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/api/v1/projects/proj-a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6/search' \
  -H 'Authorization: Bearer sk_xxxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "query": "What were the quarterly sales figures in 2024?",
    "user_id": "user-abc123",
    "top_n": 10,
    "threshold": 0.3
  }'

{
  "success": true,
  "message": "Operation completed successfully",
  "data": {
    "documents": [
      {
        "type": "paragraph",
        "document_id": "doc-123",
        "document_name": "report_2024.pdf",
        "paragraph_block_id": "blk-456",
        "highlight": {
          "chunks": [
            { "text": "Q1 2024 sales reached $2.5M...", "range": "p12" }
          ]
        },
        "source_document": { "file_name": "report_2024.pdf" }
      },
      {
        "type": "table",
        "document_id": "doc-789",
        "document_name": "sales_data.xlsx",
        "table_id": "tbl-001",
        "title": "Quarterly Sales Summary",
        "sheet_name": "Sheet1",
        "semantic_sheet_name": "2024 Quarterly Sales",
        "table_region_info": "A1:D50",
        "highlight": {
          "inner_tables": [
            {
              "id": "itbl-001",
              "data_range": "A1:D50",
              "num_rows": 49,
              "persist_path": "tables/doc-789/itbl-001",
              "columns": [
                {
                  "id": "col-1",
                  "name": "Quarter",
                  "data_type": "string",
                  "range": "A2:A50",
                  "count": 49,
                  "null_count": 0,
                  "approx_ndv": 4,
                  "examples": [{ "v": "Q1" }, { "v": "Q2" }],
                  "display_examples": [{ "v": "Q1" }, { "v": "Q2" }]
                },
                {
                  "id": "col-2",
                  "name": "Revenue",
                  "data_type": "number",
                  "range": "B2:B50",
                  "min_value": "1200000",
                  "max_value": "3100000"
                }
              ]
            }
          ]
        },
        "source_document": { "file_name": "sales_data.xlsx" }
      },
      {
        "type": "figure",
        "document_id": "doc-456",
        "document_name": "report_2024.pdf",
        "figure_id": 7,
        "highlight": {
          "figure": {
            "caption": "Figure 7. Quarterly revenue trend, 2024",
            "text": "Q1 $2.5M  Q2 $2.8M  Q3 $3.0M  Q4 $3.1M",
            "summary_text": "Bar chart showing steady quarterly revenue growth across 2024.",
            "prequestion_list": [
              "Which quarter had the highest revenue in 2024?",
              "What was the revenue trend across 2024?"
            ],
            "persist_path": "figures/doc-456/fig-7.png"
          }
        },
        "source_document": { "file_name": "report_2024.pdf" }
      }
    ],
    "memories": [
      {
        "id": "mem-123",
        "content": "User prefers Hangzhou cuisine restaurants",
        "user_id": "user-abc123",
        "expired": false,
        "has_unresolved_conflict": false,
        "created_at": "2024-01-15T10:00:00Z",
        "updated_at": "2024-01-15T10:00:00Z"
      }
    ]
  }
}

POST /openapi/memorylake/api/v1/projects/{id}/search

Searches across everything the project knows — both the ingested document content and the accumulated conversation memories — and returns the matches grouped by source. A single query surfaces the full picture, which is what you typically want in a chat assistant that grounds answers on documents and personalizes them with memories.

Items in documents and memories have the same shapes as Search Documents and Search Memories respectively — the relevant request knobs (top_n, threshold) carry the same meaning here.

Permission required: project:search · instance

Path Parameters

string

required

Project ID

Request Body

query

string

required

Natural-language search query. Used by both sub-searches.

user_id

string

required

User ID filter for the memory sub-search. Document search ignores this field.

top_n

integer

default:"10"

Maximum number of results to return, 1–1000. Applied to both document and memory matches — e.g. top_n=10 yields up to 10 documents and up to 10 memories.

threshold

number

default:"0.3"

Minimum similarity score for memory results. Scores below this are filtered out. Does not apply to documents.

with_conflicts

boolean

default:"false"

Include conflict info on memory results.

curl -X POST 'https://app.memorylake.ai/openapi/memorylake/api/v1/projects/proj-a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6/search' \
  -H 'Authorization: Bearer sk_xxxxxx' \
  -H 'Content-Type: application/json' \
  -d '{
    "query": "What were the quarterly sales figures in 2024?",
    "user_id": "user-abc123",
    "top_n": 10,
    "threshold": 0.3
  }'

Response

data

object

Show Combined search result

documents

array

Document search results. Each item is a discriminated union — type decides which variant-only fields are present and which sub-field of highlight is populated. Click to expand the full per-item shape.

Show Document result item

type

string

required

Discriminator. One of paragraph, table, or figure.

document_id

string

Document ID

document_name

string

Document file name, e.g. report_2024.xlsx

source_document

object

Source file info.

Show source_document properties

file_name

string

Original file name

highlight

object

Matched content. The object always has the same three optional fields below — exactly one is populated, selected by the parent item’s type.

Show highlight properties

chunks

Chunk[]

Populated when type=paragraph. Matched text spans, in document order. Absent otherwise.

Show Chunk properties

text

string

Plain-text snippet of the match

range

string

Location hint (e.g. page number p12, or a cell range for workbook paragraphs)

inner_tables

InnerTable[]

Populated when type=table. Matched sub-tables within the source table region. Absent otherwise.

Show InnerTable properties

string

Inner table ID

data_range

string

Cell range covered, e.g. A1:D50

num_rows

integer

Number of data rows

persist_path

string

Internal storage path of the materialized table

columns

TableColumn[]

Column descriptors.

Show TableColumn properties

string

Column ID

name

string

Column header name

data_type

string

Inferred data type (e.g. string, number, date)

range

string

Column cell range

count

integer

Non-null value count

null_count

integer

Null value count

approx_ndv

integer

Approximate number of distinct values

min_value

string

Minimum value (string-encoded)

max_value

string

Maximum value (string-encoded)

examples

object[]

Sample raw values from the column

display_examples

object[]

Sample formatted/display values

semantic_comment

string

Model-inferred semantic comment for the column

has_hierarchy

boolean

Whether the column participates in a row hierarchy

figure

object

Populated when type=figure. The matched figure descriptor. Absent otherwise.

Show figure properties

caption

string

Original figure caption

text

string

OCR / extracted text inside the figure

summary_text

string

Model-generated summary of the figure

prequestion_list

string[]

Pre-generated questions the figure can answer

persist_path

string

Internal storage path of the figure asset

paragraph_block_id

string

Only when type=paragraph. Paragraph block ID inside the document.

table_id

string

Only when type=table. Table entity ID.

title

string

Only when type=table. Table title.

footnote

string

Only when type=table. Table footnote.

sheet_name

string

Only when type=table. Worksheet name (workbook tables).

semantic_sheet_name

string

Only when type=table. Model-inferred semantic name for the worksheet.

semantic_comment

string

Only when type=table. Model-inferred semantic comment for the worksheet.

table_region_info

string

Only when type=table. Table region location, e.g. A1:D50.

figure_id

integer

Only when type=figure. Figure numeric ID.

memories

array

Memory search results. Same shape as Search Memories.

Show Memory result item

string

Memory ID

content

string

Memory content

user_id

string

Associated user ID

expired

boolean

Whether this memory has expired

has_unresolved_conflict

boolean

Whether this memory has an unresolved conflict (only meaningful when with_conflicts=true)

created_at

string

Creation timestamp (ISO 8601)

updated_at

string

Last update timestamp (ISO 8601)

{
  "success": true,
  "message": "Operation completed successfully",
  "data": {
    "documents": [
      {
        "type": "paragraph",
        "document_id": "doc-123",
        "document_name": "report_2024.pdf",
        "paragraph_block_id": "blk-456",
        "highlight": {
          "chunks": [
            { "text": "Q1 2024 sales reached $2.5M...", "range": "p12" }
          ]
        },
        "source_document": { "file_name": "report_2024.pdf" }
      },
      {
        "type": "table",
        "document_id": "doc-789",
        "document_name": "sales_data.xlsx",
        "table_id": "tbl-001",
        "title": "Quarterly Sales Summary",
        "sheet_name": "Sheet1",
        "semantic_sheet_name": "2024 Quarterly Sales",
        "table_region_info": "A1:D50",
        "highlight": {
          "inner_tables": [
            {
              "id": "itbl-001",
              "data_range": "A1:D50",
              "num_rows": 49,
              "persist_path": "tables/doc-789/itbl-001",
              "columns": [
                {
                  "id": "col-1",
                  "name": "Quarter",
                  "data_type": "string",
                  "range": "A2:A50",
                  "count": 49,
                  "null_count": 0,
                  "approx_ndv": 4,
                  "examples": [{ "v": "Q1" }, { "v": "Q2" }],
                  "display_examples": [{ "v": "Q1" }, { "v": "Q2" }]
                },
                {
                  "id": "col-2",
                  "name": "Revenue",
                  "data_type": "number",
                  "range": "B2:B50",
                  "min_value": "1200000",
                  "max_value": "3100000"
                }
              ]
            }
          ]
        },
        "source_document": { "file_name": "sales_data.xlsx" }
      },
      {
        "type": "figure",
        "document_id": "doc-456",
        "document_name": "report_2024.pdf",
        "figure_id": 7,
        "highlight": {
          "figure": {
            "caption": "Figure 7. Quarterly revenue trend, 2024",
            "text": "Q1 $2.5M  Q2 $2.8M  Q3 $3.0M  Q4 $3.1M",
            "summary_text": "Bar chart showing steady quarterly revenue growth across 2024.",
            "prequestion_list": [
              "Which quarter had the highest revenue in 2024?",
              "What was the revenue trend across 2024?"
            ],
            "persist_path": "figures/doc-456/fig-7.png"
          }
        },
        "source_document": { "file_name": "report_2024.pdf" }
      }
    ],
    "memories": [
      {
        "id": "mem-123",
        "content": "User prefers Hangzhou cuisine restaurants",
        "user_id": "user-abc123",
        "expired": false,
        "has_unresolved_conflict": false,
        "created_at": "2024-01-15T10:00:00Z",
        "updated_at": "2024-01-15T10:00:00Z"
      }
    ]
  }
}

Either list can be empty if no matches cross the threshold. Treat documents and memories independently — they’re just two lookups returned together for convenience.

Delete Project List Documents

​Path Parameters

​Request Body

​Response

Path Parameters

Request Body

Response