Émile RAG internal API
The RAG internal API from Émile — 4 operation(s) for rag internal.
The RAG internal API from Émile — 4 operation(s) for rag internal.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
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.curl "https://apis.io/api/v1/apis/emile-wine:emile-wine-rag-internal-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a 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: 3.2.0
info:
title: Émile RAG internal API
description: '# Émile API
Public API for the Émile wine cellar app.
## Authentication
Two methods are supported:
**1. API Key** (recommended for external clients: MCP servers, scripts, ChatGPT custom connectors)
Send your key in the `X-API-Key` header OR as `Authorization: Bearer emile_live_...`.
Generate keys from your iOS app: **Profil → Paramètres → Clés API**.
**2. Supabase JWT** (used by the official iOS app — internal)
Send `Authorization: Bearer `.
## Rate Limits
All endpoints are rate-limited per user. See each endpoint''s documentation for specific limits.
On exceeded: HTTP 429 with `Retry-After` header and `X-RateLimit-*` informational headers.
| Endpoint | Limit |
|---|---|
| `POST /scan` | 10/min, 50/day |
| `POST /me/scan:batch` | 5/hour |
| `POST /recommendations` | 20/min, 100/day |
| `POST /cellars/{id}/bottles` | 60/min, 500/day |
| `POST /me/bottles:batch` | 10/hour, 50/day |
| `POST /me/keys` | 5/hour, 20/day |'
version: '1.0'
tags:
- name: RAG internal
paths:
/internal/knowledge/search:
post:
tags:
- RAG internal
summary: Internal Search
description: 'Internal-traffic search (same logic as /knowledge/search) auth''d via
X-Internal-Secret rather than a user JWT. Used by the n8n content pipeline
so it doesn''t need to impersonate a real Émile user.'
operationId: internal_search_internal_knowledge_search_post
parameters:
- name: x-internal-secret
in: header
required: false
schema:
type: string
default: ''
title: X-Internal-Secret
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/SearchQuery'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
type: object
additionalProperties: true
title: Response Internal Search Internal Knowledge Search Post
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/internal/knowledge/search_grounded:
post:
tags:
- RAG internal
summary: Internal Search Grounded
description: 'RAG + Exa web search merged into a single result list.
Used by the n8n content pipeline when curated RAG alone is too sparse
(most pillars except ''vins''/''appellations'' have no FR content). Both
legs fire in parallel; Exa is best-effort (returns [] on key missing or
upstream error) so RAG outages don''t take the whole call down.'
operationId: internal_search_grounded_internal_knowledge_search_grounded_post
parameters:
- name: x-internal-secret
in: header
required: false
schema:
type: string
default: ''
title: X-Internal-Secret
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/SearchQuery'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
type: object
additionalProperties: true
title: Response Internal Search Grounded Internal Knowledge Search Grounded Post
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/internal/knowledge/bulk_insert:
post:
tags:
- RAG internal
summary: Bulk Insert
description: 'Insert pre-embedded chunks. The ingestion script computes embeddings
in bulk (cheaper than per-query) and pushes them here.'
operationId: bulk_insert_internal_knowledge_bulk_insert_post
parameters:
- name: x-internal-secret
in: header
required: false
schema:
type: string
default: ''
title: X-Internal-Secret
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/BulkInsertRequest'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
type: object
additionalProperties: true
title: Response Bulk Insert Internal Knowledge Bulk Insert Post
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/internal/knowledge/by_source/{source}:
delete:
tags:
- RAG internal
summary: Delete By Source
description: 'Wipe all knowledge_chunks rows for a given source name. Used by the
ingestion script before re-running a source — bulk_insert is not
idempotent on (source, source_url, content_text), so a re-run would
otherwise duplicate everything that was already ingested.'
operationId: delete_by_source_internal_knowledge_by_source__source__delete
parameters:
- name: source
in: path
required: true
schema:
type: string
title: Source
- name: x-internal-secret
in: header
required: false
schema:
type: string
default: ''
title: X-Internal-Secret
responses:
'200':
description: Successful Response
content:
application/json:
schema:
type: object
additionalProperties: true
title: Response Delete By Source Internal Knowledge By Source Source Delete
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
components:
schemas:
BulkInsertRequest:
properties:
chunks:
items:
$ref: '#/components/schemas/KnowledgeChunk'
type: array
title: Chunks
type: object
required:
- chunks
title: BulkInsertRequest
description: 'Wrapper for the bulk_insert payload — keeps the door open for
future top-level metadata (batch_id, source_run, etc.) without breaking
the wire format.'
KnowledgeChunk:
properties:
id:
anyOf:
- type: string
- type: 'null'
title: Id
source:
type: string
title: Source
source_url:
anyOf:
- type: string
- type: 'null'
title: Source Url
content_text:
type: string
minLength: 10
title: Content Text
content_embedding:
anyOf:
- items:
type: number
type: array
- type: 'null'
title: Content Embedding
language:
type: string
enum:
- fr
- en
title: Language
pillar:
type: string
enum:
- vins
- viticulture
- cave
- sommellerie
- accord
- appellations
title: Pillar
topic:
anyOf:
- type: string
- type: 'null'
title: Topic
token_count:
anyOf:
- type: integer
- type: 'null'
title: Token Count
type: object
required:
- source
- content_text
- language
- pillar
title: KnowledgeChunk
description: A single ingested chunk with metadata.
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
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
SearchQuery:
properties:
query:
type: string
minLength: 2
title: Query
language:
type: string
enum:
- fr
- en
title: Language
default: fr
pillars:
anyOf:
- items:
type: string
enum:
- vins
- viticulture
- cave
- sommellerie
- accord
- appellations
type: array
- type: 'null'
title: Pillars
top_k:
type: integer
maximum: 20.0
minimum: 1.0
title: Top K
default: 8
type: object
required:
- query
title: SearchQuery
description: Input for /knowledge/search.
securitySchemes:
HTTPBearer:
type: http
scheme: bearer