TESSA Marketing & Technology Vectors API

The Vectors API from TESSA Marketing & Technology — 5 operation(s) for vectors.

Operations 5

GET /vectors/health Vectors Health #
GET /vectors/info Vectors Info #
POST /vectors/search Vectors Search #
POST /vectors/upsert Vectors Upsert #
POST /vectors/delete Vectors Delete #

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/tessa-tech:tessa-tech-vectors-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

tessa-tech-vectors-api-openapi.yml Raw ↑
openapi: 3.2.0
info:
  title: TESSA Agent Directory Vectors API
  version: 0.1.0
  description: 'TESSA Marketing & Technology''s FastAPI service behind aiagent.tessa.tech: the A2A agent card and JSON-RPC endpoint, per-service and per-tenant agent cards, the professional-services directory (firm cards, profiles, introduction requests, claim/verify/removal/takedown flows), the TESSA Professional Services A2A extension, service-type taxonomies, an admin/vector surface, and the mount point of the MCP server (/mcp, Streamable HTTP).'
  contact:
    name: TESSA Marketing & Technology
    url: https://tessa.tech
    email: sales@tessa.tech
  x-apievangelist-provenance:
    harvested: '2026-09-19'
    method: searched
    source: https://aiagent.tessa.tech/openapi.json
    original: openapi/_original/tessa-tech-openapi.json
    original_sha256: 3349c7e2613aca4fb5736b570f082a2d509e1147b8a82183b71dafff0722f6da
    changes:
    - servers[] added (the harvested spec declares none); hosts taken from the provider's own root document at https://aiagent.tessa.tech/ and verified by an identical-byte spec at complianceregistry.net/openapi.json and marketingregistry.org/openapi.json
    - info.description and info.contact added; contact values from the agent card (_meta.tessa.contact) and server.json (support_email)
    ownership: Served on tessa.tech's own subdomain; info.title names TESSA; the agent card at the same host names TESSA Marketing & Technology as provider with url https://tessa.tech; the root document names the app 'TESSA MCP Server + Agent Directory'.
servers:
- url: https://aiagent.tessa.tech
  description: TESSA's own agent host — agent card, A2A JSON-RPC, MCP (/mcp/), service cards (/s), OpenAPI. Registry-scoped routes return 421 here.
- url: https://complianceregistry.net
  description: TESSA-operated Compliance Registry (same application, same spec bytes). Registry routes (/registry.json, /taxonomy, /extensions, /{slug}) resolve here.
- url: https://marketingregistry.org
  description: TESSA-operated Local Business / Marketing Registry (same application, same spec bytes).
tags:
- name: Vectors
paths:
  /vectors/health:
    get:
      summary: Vectors Health
      description: 'Unauthenticated liveness probe: is the extension present and the table there?'
      operationId: vectors_health_vectors_health_get
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
      tags:
      - Vectors
  /vectors/info:
    get:
      summary: Vectors Info
      operationId: vectors_info_vectors_info_get
      parameters:
      - name: collection
        in: query
        required: true
        schema:
          type: string
          title: Collection
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Vectors
  /vectors/search:
    post:
      summary: Vectors Search
      description: 'Dense + keyword search fused with reciprocal rank fusion.


        Both legs receive the same filter, matching how the Qdrant client applied

        the filter to both prefetch branches.'
      operationId: vectors_search_vectors_search_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/SearchRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Vectors
  /vectors/upsert:
    post:
      summary: Vectors Upsert
      description: 'Insert or replace points. Matches Qdrant''s upsert-by-point-id semantics.


        Conflict target is (collection, id), not id alone: the plugins derive point

        IDs from post_id/chunk_index without the collection, so both plugins produce

        identical IDs for the same WordPress post. Keying on id alone let one

        collection''s upsert steal rows from the other.


        The `bm25` sparse vector Qdrant used is ignored: Postgres derives the

        keyword index from chunk_text via a generated tsvector column.'
      operationId: vectors_upsert_vectors_upsert_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/UpsertRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Vectors
  /vectors/delete:
    post:
      summary: Vectors Delete
      description: 'Delete every point in a collection matching a Qdrant-style filter.


        An absent/empty filter clears the whole collection, which is what the

        plugin''s delete_collection() relies on. Deliberately scoped to the

        collection: the table is shared, so a DROP would take out both plugins.'
      operationId: vectors_delete_vectors_delete_post
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DeleteRequest'
        required: true
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      tags:
      - Vectors
components:
  schemas:
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    UpsertRequest:
      properties:
        collection:
          type: string
          maxLength: 64
          minLength: 1
          title: Collection
        points:
          items:
            $ref: '#/components/schemas/Point'
          type: array
          title: Points
      type: object
      required:
      - collection
      - points
      title: UpsertRequest
    SearchRequest:
      properties:
        collection:
          type: string
          maxLength: 64
          minLength: 1
          title: Collection
        vector:
          items:
            type: number
          type: array
          minItems: 1
          title: Vector
        query:
          type: string
          title: Query
          default: ''
        limit:
          type: integer
          maximum: 100.0
          minimum: 1.0
          title: Limit
          default: 10
        prefetch_limit:
          type: integer
          maximum: 500.0
          minimum: 1.0
          title: Prefetch Limit
          default: 20
        filter:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Filter
      type: object
      required:
      - collection
      - vector
      title: SearchRequest
    Point:
      properties:
        id:
          type: string
          title: Id
        vector:
          anyOf:
          - additionalProperties: true
            type: object
          - items:
              type: number
            type: array
          title: Vector
        payload:
          additionalProperties: true
          type: object
          title: Payload
      type: object
      required:
      - id
      - vector
      title: Point
    DeleteRequest:
      properties:
        collection:
          type: string
          maxLength: 64
          minLength: 1
          title: Collection
        filter:
          anyOf:
          - additionalProperties: true
            type: object
          - type: 'null'
          title: Filter
      type: object
      required:
      - collection
      title: DeleteRequest
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
        input:
          title: Input
        ctx:
          type: object
          title: Context
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError