curl -X GET 'https://api.anyformat.ai/v3/workflows/0686bb97-8c30-70f0-8000-97669e000eb8/knowledge/search?query=termination+notice&limit=5' \
-H 'Authorization: Bearer YOUR_API_KEY'
import requests
workflow_id = "0686bb97-8c30-70f0-8000-97669e000eb8"
url = f"https://api.anyformat.ai/v3/workflows/{workflow_id}/knowledge/search"
headers = {"Authorization": "Bearer YOUR_API_KEY"}
hits = requests.get(url, headers=headers, params={"query": "termination notice", "limit": 5}).json()
for hit in hits:
print(hit["path"], hit["rank"], hit["snippet"])
[
{
"path": "2026-07/meridian-msa.md",
"folder": "2026-07",
"title": "Meridian MSA",
"page_count": 3,
"snippet": "Either Party may terminate upon ninety (90) days' notice.",
"rank": 4.2,
"block_id": "p2_b4",
"content_url": "https://static.anyformat.ai/customers/.../body.md?X-Amz-Signature=..."
}
]
{
"error": "Knowledge base not enabled",
"detail": "This workflow has no knowledge base. Add a knowledge node. New completed runs then ingest documents; index earlier processed documents from the app's Knowledge tab.",
"error_code": "KNOWLEDGE_NOT_ENABLED",
"retryable": false
}
Knowledge
Search
Rank a workflow’s knowledge corpus by relevance to a query
GET
/
v3
/
workflows
/
{workflow_id}
/
knowledge
/
search
curl -X GET 'https://api.anyformat.ai/v3/workflows/0686bb97-8c30-70f0-8000-97669e000eb8/knowledge/search?query=termination+notice&limit=5' \
-H 'Authorization: Bearer YOUR_API_KEY'
import requests
workflow_id = "0686bb97-8c30-70f0-8000-97669e000eb8"
url = f"https://api.anyformat.ai/v3/workflows/{workflow_id}/knowledge/search"
headers = {"Authorization": "Bearer YOUR_API_KEY"}
hits = requests.get(url, headers=headers, params={"query": "termination notice", "limit": 5}).json()
for hit in hits:
print(hit["path"], hit["rank"], hit["snippet"])
[
{
"path": "2026-07/meridian-msa.md",
"folder": "2026-07",
"title": "Meridian MSA",
"page_count": 3,
"snippet": "Either Party may terminate upon ninety (90) days' notice.",
"rank": 4.2,
"block_id": "p2_b4",
"content_url": "https://static.anyformat.ai/customers/.../body.md?X-Amz-Signature=..."
}
]
{
"error": "Knowledge base not enabled",
"detail": "This workflow has no knowledge base. Add a knowledge node. New completed runs then ingest documents; index earlier processed documents from the app's Knowledge tab.",
"error_code": "KNOWLEDGE_NOT_ENABLED",
"retryable": false
}
Rate limit tier: general, 600 requests/min. See Rate limits.
Ranks a workflow’s knowledge corpus by relevance to
query — for a topic-style question such as “where is termination discussed”, not an exact string, a count, or a sum. For an answer with citations, use Ask; for the full tree, use List.
Each hit carries a relevance rank (higher first), a block_id, a content_url and a snippet: the text of the document’s best-matching block, up to 600 characters, with no highlight markers. Ranking is full-text search over the document’s blocks, headings and title, and rank is that score for the best block. It is relevance, not match count — a document matching the query term fewer times can still outrank one matching it more, and a document matching no query term is not returned.
block_id is the anchor of that best block, the same block_id that Read content and Ask citations use. content_url is a presigned GET URL of the document’s whole body text, valid for 15 minutes; possession of the URL is read permission until it expires. Both are null on an older snapshot, and content_url is also null when the document changed after the snapshot was published.
Requires a knowledge base
Same requirement asask: the workflow needs a knowledge node, or this returns 409 KNOWLEDGE_NOT_ENABLED. 409 KNOWLEDGE_NOT_READY means no usable snapshot has ever been published. Unlike ask, search is never billed, so 402 cannot occur here.
Folder
folder narrows ranking to one top-level source folder — the first path segment (e.g. contracts), not a nested path. Omitting it merges every folder’s statistics into one corpus-wide ranking. An unrecognized folder name is a 404.
Query length
query is 1 to 512 characters.
Limit
limit caps the number of hits, 1 to 50, default 10.
Errors
| Status | error_code | Meaning |
|---|---|---|
400 | VALIDATION_ERROR | query was empty or over 512 characters, or limit was outside 1 to 50. |
404 | NOT_FOUND | Unknown workflow, one belonging to another organization, or folder names no folder in this corpus. |
409 | KNOWLEDGE_NOT_ENABLED | The workflow has no Knowledge node. Do not retry: add the node first. |
409 | KNOWLEDGE_NOT_READY | No knowledge snapshot has ever been published for this workflow. Wait if indexing is in progress. |
409 | KNOWLEDGE_UNSUPPORTED_SNAPSHOT_FORMAT | The published snapshot is in a format this deployment no longer reads. Permanent until an operator republishes it. |
504 | GATEWAY_TIMEOUT | The search exceeded the agent’s own time ceiling. Retry. |
curl -X GET 'https://api.anyformat.ai/v3/workflows/0686bb97-8c30-70f0-8000-97669e000eb8/knowledge/search?query=termination+notice&limit=5' \
-H 'Authorization: Bearer YOUR_API_KEY'
import requests
workflow_id = "0686bb97-8c30-70f0-8000-97669e000eb8"
url = f"https://api.anyformat.ai/v3/workflows/{workflow_id}/knowledge/search"
headers = {"Authorization": "Bearer YOUR_API_KEY"}
hits = requests.get(url, headers=headers, params={"query": "termination notice", "limit": 5}).json()
for hit in hits:
print(hit["path"], hit["rank"], hit["snippet"])
[
{
"path": "2026-07/meridian-msa.md",
"folder": "2026-07",
"title": "Meridian MSA",
"page_count": 3,
"snippet": "Either Party may terminate upon ninety (90) days' notice.",
"rank": 4.2,
"block_id": "p2_b4",
"content_url": "https://static.anyformat.ai/customers/.../body.md?X-Amz-Signature=..."
}
]
{
"error": "Knowledge base not enabled",
"detail": "This workflow has no knowledge base. Add a knowledge node. New completed runs then ingest documents; index earlier processed documents from the app's Knowledge tab.",
"error_code": "KNOWLEDGE_NOT_ENABLED",
"retryable": false
}
Authorizations
API key issued from app.anyformat.ai/api-key. Send as Authorization: Bearer <key>.
Path Parameters
Query Parameters
Search query. 1 to 512 characters.
Required string length:
1 - 512Narrows to one top-level source folder (the first path segment, not a nested path). 404s when no such folder exists in this corpus.
Max hits to return, 1 to 50.
Required range:
1 <= x <= 50Response
Successful Response
Document path inside the workflow's corpus.
Parent folder of path.
Document title.
Page count of the source document.
The text of the best-matching block, up to 600 characters.
Full-text search score of the best-matching block; higher ranks first.
Anchor of the best-matching block, the block_id that read_knowledge content and citations use. Null on an older snapshot.
Presigned GET URL of the document's body text, valid for 900 seconds. Possession of the URL is read permission until it expires. Null on an older snapshot, or when the document changed after the snapshot was published.