Agents
Calls, Messages, Stages
Corpora, Query, Sources
- Corpus Service (RAG) Overview
- GETList Corpora
- POSTCreate Corpus
- GETGet Corpus
- PATCHUpdate Corpus
- DELDelete Corpus
- POSTQuery Corpus
- GETList Corpus Sources
- POSTCreate Corpus Source
- GETGet Corpus Source
- PATCHUpdate Corpus Source
- DELDelete Corpus Source
- GETList Corpus Source Documents
- GETGet Corpus Source Document
- POSTCreate Corpus File Upload
Webhooks
Create Corpus Source
Creates a new source for the specified corpus
curl --request POST \
--url https://api.ultravox.ai/api/corpora/{corpus_id}/sources \
--header 'Content-Type: application/json' \
--header 'X-API-Key: <api-key>' \
--data '{
"corpusId": "<string>",
"sourceId": "<string>",
"created": "2023-11-07T05:31:56Z",
"name": "<string>",
"description": "<string>",
"stats": {
"status": "SOURCE_STATUS_UNSPECIFIED",
"lastUpdated": "2023-11-07T05:31:56Z",
"numDocs": 123
},
"loadSpec": {
"maxDocuments": 123,
"maxDocumentBytes": 123,
"relevantDocumentTypes": {
"include": {
"mimeTypes": [
"<string>"
]
},
"exclude": {
"mimeTypes": [
"<string>"
]
}
},
"startUrls": [
"<string>"
],
"maxDepth": 123
},
"crawl": {
"maxDocuments": 123,
"maxDocumentBytes": 123,
"relevantDocumentTypes": {
"include": {
"mimeTypes": [
"<string>"
]
},
"exclude": {
"mimeTypes": [
"<string>"
]
}
},
"startUrls": [
"<string>"
],
"maxDepth": 123
},
"upload": {
"documentIds": [
"<string>"
]
}
}'{
"corpusId": "<string>",
"sourceId": "<string>",
"created": "2023-11-07T05:31:56Z",
"name": "<string>",
"description": "<string>",
"stats": {
"status": "SOURCE_STATUS_UNSPECIFIED",
"lastUpdated": "2023-11-07T05:31:56Z",
"numDocs": 123
},
"loadSpec": {
"maxDocuments": 123,
"maxDocumentBytes": 123,
"relevantDocumentTypes": {
"include": {
"mimeTypes": [
"<string>"
]
},
"exclude": {
"mimeTypes": [
"<string>"
]
}
},
"startUrls": [
"<string>"
],
"maxDepth": 123
},
"crawl": {
"maxDocuments": 123,
"maxDocumentBytes": 123,
"relevantDocumentTypes": {
"include": {
"mimeTypes": [
"<string>"
]
},
"exclude": {
"mimeTypes": [
"<string>"
]
}
},
"startUrls": [
"<string>"
],
"maxDepth": 123
},
"upload": {
"documentIds": [
"<string>"
]
}
}Authorizations
API key
Path Parameters
Body
A source of documents for building a corpus. A source defines where documents are pulled from.
The id of this source's corpus.
The unique ID of this source.
When this source was created.
The name of this source.
A description of this source.
The current stats for this source.
The current status of this source, indicating whether it affects queries.
SOURCE_STATUS_UNSPECIFIED, SOURCE_STATUS_INITIALIZING, SOURCE_STATUS_READY, SOURCE_STATUS_UPDATING When this source last finished contributing contents to its corpus.
The number of documents in this source. This includes both loaded documents and derived documents.
DEPRECATED. Prefer setting crawl instead. If either crawl or upload is set, this field will be ignored.
The maximum number of documents to ingest.
The maximum size of an individual document in bytes.
The types of documents to keep. Any documents surfaced during loading that don't match this filter will be discarded. If not set, Ultravox will choose a default that includes types known to provide real value.
Mime types must be in this set to be kept.
The mime types in this set.
The list of start URLs for crawling. If max_depth is 1, only these URLs will be fetched. Otherwise, links from these urls will be followed up to the max_depth.
The maximum depth of links to traverse. Use 1 to only fetch the startUrls, 2 to fetch the startUrls and documents directly linked from them, 3 to additionally fetch documents linked from those (excluding anything already seen), etc.
Allows loading documents by crawling the web.
The maximum number of documents to ingest.
The maximum size of an individual document in bytes.
The types of documents to keep. Any documents surfaced during loading that don't match this filter will be discarded. If not set, Ultravox will choose a default that includes types known to provide real value.
Mime types must be in this set to be kept.
The mime types in this set.
The list of start URLs for crawling. If max_depth is 1, only these URLs will be fetched. Otherwise, links from these urls will be followed up to the max_depth.
The maximum depth of links to traverse. Use 1 to only fetch the startUrls, 2 to fetch the startUrls and documents directly linked from them, 3 to additionally fetch documents linked from those (excluding anything already seen), etc.
Response
A source of documents for building a corpus. A source defines where documents are pulled from.
The id of this source's corpus.
The unique ID of this source.
When this source was created.
The name of this source.
A description of this source.
The current stats for this source.
The current status of this source, indicating whether it affects queries.
SOURCE_STATUS_UNSPECIFIED, SOURCE_STATUS_INITIALIZING, SOURCE_STATUS_READY, SOURCE_STATUS_UPDATING When this source last finished contributing contents to its corpus.
The number of documents in this source. This includes both loaded documents and derived documents.
DEPRECATED. Prefer setting crawl instead. If either crawl or upload is set, this field will be ignored.
The maximum number of documents to ingest.
The maximum size of an individual document in bytes.
The types of documents to keep. Any documents surfaced during loading that don't match this filter will be discarded. If not set, Ultravox will choose a default that includes types known to provide real value.
Mime types must be in this set to be kept.
The mime types in this set.
The list of start URLs for crawling. If max_depth is 1, only these URLs will be fetched. Otherwise, links from these urls will be followed up to the max_depth.
The maximum depth of links to traverse. Use 1 to only fetch the startUrls, 2 to fetch the startUrls and documents directly linked from them, 3 to additionally fetch documents linked from those (excluding anything already seen), etc.
Allows loading documents by crawling the web.
The maximum number of documents to ingest.
The maximum size of an individual document in bytes.
The types of documents to keep. Any documents surfaced during loading that don't match this filter will be discarded. If not set, Ultravox will choose a default that includes types known to provide real value.
Mime types must be in this set to be kept.
The mime types in this set.
The list of start URLs for crawling. If max_depth is 1, only these URLs will be fetched. Otherwise, links from these urls will be followed up to the max_depth.
The maximum depth of links to traverse. Use 1 to only fetch the startUrls, 2 to fetch the startUrls and documents directly linked from them, 3 to additionally fetch documents linked from those (excluding anything already seen), etc.
curl --request POST \
--url https://api.ultravox.ai/api/corpora/{corpus_id}/sources \
--header 'Content-Type: application/json' \
--header 'X-API-Key: <api-key>' \
--data '{
"corpusId": "<string>",
"sourceId": "<string>",
"created": "2023-11-07T05:31:56Z",
"name": "<string>",
"description": "<string>",
"stats": {
"status": "SOURCE_STATUS_UNSPECIFIED",
"lastUpdated": "2023-11-07T05:31:56Z",
"numDocs": 123
},
"loadSpec": {
"maxDocuments": 123,
"maxDocumentBytes": 123,
"relevantDocumentTypes": {
"include": {
"mimeTypes": [
"<string>"
]
},
"exclude": {
"mimeTypes": [
"<string>"
]
}
},
"startUrls": [
"<string>"
],
"maxDepth": 123
},
"crawl": {
"maxDocuments": 123,
"maxDocumentBytes": 123,
"relevantDocumentTypes": {
"include": {
"mimeTypes": [
"<string>"
]
},
"exclude": {
"mimeTypes": [
"<string>"
]
}
},
"startUrls": [
"<string>"
],
"maxDepth": 123
},
"upload": {
"documentIds": [
"<string>"
]
}
}'{
"corpusId": "<string>",
"sourceId": "<string>",
"created": "2023-11-07T05:31:56Z",
"name": "<string>",
"description": "<string>",
"stats": {
"status": "SOURCE_STATUS_UNSPECIFIED",
"lastUpdated": "2023-11-07T05:31:56Z",
"numDocs": 123
},
"loadSpec": {
"maxDocuments": 123,
"maxDocumentBytes": 123,
"relevantDocumentTypes": {
"include": {
"mimeTypes": [
"<string>"
]
},
"exclude": {
"mimeTypes": [
"<string>"
]
}
},
"startUrls": [
"<string>"
],
"maxDepth": 123
},
"crawl": {
"maxDocuments": 123,
"maxDocumentBytes": 123,
"relevantDocumentTypes": {
"include": {
"mimeTypes": [
"<string>"
]
},
"exclude": {
"mimeTypes": [
"<string>"
]
}
},
"startUrls": [
"<string>"
],
"maxDepth": 123
},
"upload": {
"documentIds": [
"<string>"
]
}
}