> ## Documentation Index
> Fetch the complete documentation index at: https://docs.anonalabs.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Documents
> Upload files into a space so their content becomes searchable memory.
A document is parsed, split into chunks, and stored as memory, so the same
[Retrieve](/api-reference/retrieve) and [Reason](/api-reference/reason) calls surface
file content alongside anything you recorded conversationally.
| Category | Formats | How it is extracted |
| ------------------ | ------------------------ | ------------------------- |
| Documents | PDF, DOCX, DOC | Text extraction |
| Office | PPTX, PPT, XLSX, XLS | Text and table extraction |
| Web and plain text | HTML, TXT, Markdown, CSV | Direct parsing |
| Images | JPG, PNG | OCR |
| Audio | MP3, WAV | Transcription |
## Upload files
```http theme={null}
POST /v1/spaces/{space_id}/documents
Authorization: Bearer anona_live_YOUR_KEY
Content-Type: multipart/form-data
```
| Form field | Type | Required | Description |
| ------------ | ------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------- |
| `files` | file(s) | Yes | One or more files to upload. |
| `tags` | string | No | Comma-separated tags applied to every file, so retrieval can scope to them later. Tags starting with `anona:` are reserved and rejected with `422`. |
| `user_id` | string | No | End user these documents belong to. See [Scoping](/api-reference/retrieve#scoping-within-a-space). |
| `agent_id` | string | No | Owning agent. |
| `session_id` | string | No | Owning session. |
| `strategy` | string | No | How the file is retained. Defaults to storing it as retrieval chunks; pass a named strategy to override. |
If you use scoping, upload with the same scope you retrieve with. Scoped search
is strict, so a document uploaded **without** `user_id` is not returned to a
search **with** one: it is only reachable from an unscoped search.
| Limit | Value |
| ----------------- | ----- |
| Files per request | 20 |
| Size per file | 25 MB |
| Total per request | 50 MB |
Ingestion is always asynchronous. The call returns immediately with a `job_ids` list;
poll each with the [job status](/api-reference/memories#job-status) endpoint. When a job
reaches `completed`, that file's content is searchable.
**Response** `202 Accepted`
```json theme={null}
{
"job_ids": ["job_conv_7f1a", "job_conv_7f1b"]
}
```
```bash cURL theme={null}
curl -X POST https://api.anonalabs.com/v1/spaces/customer-support-bot/documents \
-H "Authorization: Bearer anona_live_YOUR_KEY" \
-F "files=@handbook.pdf" \
-F "tags=hr,policy" \
-F "user_id=alice"
```
```python Python SDK theme={null}
job = client.upload_file(
space_id="customer-support-bot",
file="handbook.pdf",
tags=["hr", "policy"],
)
print(job["job_ids"]) # poll each with client.get_job(...)
```
Parsing and embedding a document is billed on completion, not at upload. Larger files
and richer formats, such as scanned PDFs and audio, cost more because more content is
processed.
## List documents
```http theme={null}
GET /v1/spaces/{space_id}/documents?limit=100&offset=0
Authorization: Bearer anona_live_YOUR_KEY
```
| Query parameter | Type | Description |
| --------------- | ------- | ----------------------------------------- |
| `limit` | integer | Maximum results. Defaults to 100. |
| `offset` | integer | Pagination offset. |
| `q` | string | Optional substring filter on document id. |
**Response** `200 OK`
```json theme={null}
{
"documents": [
{
"document_id": "file_9c2f1a",
"source": "file",
"created_at": "2026-07-22T10:30:00Z",
"updated_at": "2026-07-22T10:30:04Z",
"text_length": 18240,
"memory_count": 37,
"tags": ["hr", "policy"]
}
],
"total": 1,
"limit": 100,
"offset": 0
}
```
`memory_count` is how many searchable memories were extracted from the document.
### What counts as a document
This list contains everything ingested into the space, not only uploaded files. Storing
a memory with `POST /v1/record` also creates a document row, so `source` tells you which
is which.
| `source` | Meaning |
| -------- | ------------------------------------------------------------------------------------------------------------------------------- |
| `file` | Uploaded through this endpoint. |
| `custom` | You passed your own `document_id` on a write, deliberately grouping content under it. |
| `memory` | Created implicitly by a write that supplied no `document_id`. It holds a single stored memory rather than an uploaded document. |
To group your writes into meaningful documents, such as a conversation, a ticket, or a
session, pass your own `document_id` when recording. Reusing an id replaces that
document's memories, which is how you keep a document current.
The dashboard's Documents tab hides `memory` rows by default for this reason, with a
toggle to show everything ingested.
```python theme={null}
docs = client.list_documents(space_id="customer-support-bot")
```
## Get a document
```http theme={null}
GET /v1/spaces/{space_id}/documents/{document_id}
Authorization: Bearer anona_live_YOUR_KEY
```
Returns the document's metadata and ingestion status, in the same shape as one item in
the list above.
## Delete a document
Removes the document and every memory extracted from it.
```http theme={null}
DELETE /v1/spaces/{space_id}/documents/{document_id}
Authorization: Bearer anona_live_YOUR_KEY
```
```python theme={null}
client.delete_document(space_id="customer-support-bot", document_id="file_9c2f1a")
```
**Response** `204 No Content`.
## Error responses
| Status | Code | Cause |
| ------ | ------------------ | -------------------------------------------- |
| 400 | `too_many_files` | More than 20 files in one request. |
| 401 | `unauthorized` | Missing or invalid API key. |
| 403 | `forbidden` | The space is not owned by your organization. |
| 413 | `file_too_large` | A single file exceeds 25 MB. |
| 413 | `upload_too_large` | The total upload exceeds 50 MB. |
| 429 | `rate_limited` | Credit quota or rate limit exceeded. |
See the full [error reference](/api-reference/errors).
## Next steps
Search across recorded memory and uploaded documents.
Record memories and poll ingestion jobs.