> ## Documentation Index
> Fetch the complete documentation index at: https://guide.omnia-voice.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Corpora
> Index your documents so an agent can answer from them mid-call.
A **corpus** is a searchable collection of your documents. Link one to an agent
and the agent gains a search tool it can call during a conversation — grounding
its answers in your material rather than in its prompt.
This is how you give an agent knowledge. An older `knowledgeBases` field still
exists on the agent payload for legacy integrations, but it is deprecated — use
corpora.
Corpora are created and managed **in the dashboard**, under
[**Corpora**](https://dashboard.omnia-voice.com/dashboard/corpus). There is no
API-key endpoint for creating one — the management routes authenticate with
your dashboard session. What *is* automatic is the search: once a corpus is
linked, the agent queries it on its own during calls.
## What you can put in one
Three kinds of source:
Upload a document. Up to **4 MB** each.
Paste content directly. Up to 4 MB.
Give a page address and it is fetched and indexed.
### Supported file types
| Group | Extensions |
| ------------- | -------------------------------------------------------------------------------------------------------- |
| Documents | `.pdf` `.docx` `.odt` |
| Spreadsheets | `.xlsx` `.csv` `.ods` |
| Web & markup | `.html` `.htm` `.xml` `.sgml` |
| Text & notes | `.txt` `.md` `.mdx` `.markdown` `.rst` `.log` `.tex` `.latex` |
| Data & config | `.json` `.yaml` `.yml` `.toml` `.css` `.ini` `.conf` `.env` `.properties` |
| Images | `.jpg` `.jpeg` `.png` `.webp` `.svg` |
| Code | `.js` `.ts` `.py` `.php` `.rb` `.java` `.c` `.cpp` `.h` `.go` `.rs` `.swift` `.dart` `.sh` `.bat` `.ps1` |
**PowerPoint and legacy Office formats are not supported.** Export `.pptx` /
`.ppt` slides to PDF, save `.doc` as `.docx` or PDF, and `.xls` as `.xlsx` or
`.csv`. Uploading one of these returns an explanatory error rather than
failing silently.
## Indexing
Adding a source does not make it searchable immediately. Each one moves through:
| Status | Meaning |
| ------------ | ---------------------------------------------- |
| `PENDING` | Queued, not started |
| `PROCESSING` | Being extracted and indexed |
| `PROCESSED` | Searchable |
| `FAILED` | Something went wrong — `errorMessage` explains |
| `SKIPPED` | Nothing indexable was found in it |
URL sources are fetched in the background, so they sit in `PENDING` briefly
before processing begins. Large PDFs take longest.
Test only once every source shows `PROCESSED`. An agent asked about content
that is still indexing will correctly say it cannot find it — which looks like
a broken agent but is the system telling the truth.
## Linking a corpus to an agent
Include corpus IDs in the agent payload, or use the agent page in the dashboard:
```json theme={null}
{
"name": "Front Desk",
"corpora": ["cor_abc123", "cor_def456"],
"kbSearchAnnouncement": "Let me look that up for you.",
"config": { }
}
```
The agent automatically gains a tool named `search_` — you do not
create or configure it. Its description tells the model to reach for it whenever
a caller asks something that corpus might answer.
### Covering the pause
Retrieval takes a moment, and silence on a phone call feels far longer than it
is. `kbSearchAnnouncement` is spoken **verbatim** immediately before the search:
```json theme={null}
{ "kbSearchAnnouncement": "Hetkinen, katson asiaa." }
```
Write it in whatever language your agent speaks — it is not translated. Maximum
300 characters, though one short sentence is the right length.
## How search behaves during a call
The agent sends the caller's question, and passages come back ranked. By default
it retrieves **8** passages; the model may request up to 12.
That default is deliberately generous. On real PDFs the passage containing the
actual answer — a row in a pricing table, say — often ranks tenth or lower,
because generic introductory text matches the query more strongly. Returning
more passages means the answer is present in context for the model to find.
## Writing documents that retrieve well
Retrieval returns passages, not whole files. What survives being lifted out of
context:
* **Put the answer next to the question.** A heading phrased as a question with
the answer directly beneath is close to ideal.
* **Keep related facts together.** A price three paragraphs away from the product
name may come back without it.
* **Prefer several small documents** over one large one — chunk boundaries fall
in kinder places.
* **Avoid cross-references.** "See section 4.2" is meaningless once a passage is
read on its own.
Tables in PDFs are the most common disappointment. A table that reads clearly
to a human frequently flattens into unusable text when extracted. If specific
numbers matter, state them in a sentence as well as showing the table.
## Corpora and workspaces
A corpus belongs to a workspace and can be linked to any number of agents in it.
Update the documents once and every agent using it answers from the new version —
there is no per-agent copy to keep in sync.
The `corpora` field on the agent payload.
Let the agent act, not just recall.