# Input data types

Engram accepts three types of input content when storing memories:

| Type            | Description                                        | Use case                              |
| --------------- | -------------------------------------------------- | ------------------------------------- |
| `string`        | Raw text (one or more strings)                     | Free-form notes, agent observations   |
| `conversation`  | Multi-turn messages with roles                     | Chat transcripts, agent conversations |
| `pre_extracted` | Already-structured items, each with a target topic | When you've done your own extraction  |

You pass one of these three shapes as the first argument to `client.memories.add()`. Exactly one content type is used per call.

## String

Send raw text and let Engram's [pipeline](pipelines.md) extract structured memories from it. `content` is an array, so you can send multiple unrelated strings in one call — each becomes its own pipeline input.

```python
client.memories.add("The user prefers dark mode and uses VS Code.", user_id=test_user_id)
```

## Conversation

Send multi-turn messages with roles for chat transcripts and agent conversations. The pipeline uses conversation-aware extraction to pull memories from the dialogue.

Messages follow the OpenAI Chat Completions format: `role` is one of `user`, `assistant`, `system`, `tool`, or `developer`. Tool calls (`tool_calls`, `tool_call_id`, `name`) are supported. The server normalizes `tool` → `user` and `developer` → `system` internally.

```python
client.memories.add(
    [
        {"role": "user", "content": "I just moved to Berlin."},
        {"role": "assistant", "content": "Welcome to Berlin!"},
        {"role": "user", "content": "I prefer specialty coffee."},
    ],
    user_id=test_user_id,
)
```

## Pre-extracted

Send already-structured items when you've done your own extraction. Each item carries its target topic and bypasses the LLM extraction step — it still flows through the transform and commit stages.

```python
from engram import PreExtractedInput, PreExtractedItem

client.memories.add(
    PreExtractedInput(items=[
        PreExtractedItem(content="User prefers dark mode", topic="UserKnowledge"),
        PreExtractedItem(content="User works in Python", topic="UserKnowledge"),
    ]),
    user_id=test_user_id,
)
```

## Questions and feedback

Have a question or feedback? Here's how to reach us.

::::card-grid
:::card{title="Community Forum" href="https://forum.weaviate.io/c/support" icon="messages-square"}
Ask questions and connect with other developers on our **Community forum**.
:::

:::card{title="Support" href="/guides/support-overview" icon="life-buoy"}
Weaviate Cloud user or customer? Find the right channel on the **Support page**.
:::
::::

## Related pages

- [Agents](./agents-index.md)
- [AI-assisted Weaviate code generation](./ai-assisted-vibe-coding-index.md)
- [APIs](./apis-index.md)
- [Authorization and authentication](./authorization-and-authentication-index.md)
- [Benchmarks](./benchmarks-index.md)
- [Best practices](./best-practices-index.md)
- [Client libraries](./clients-index.md)
- [Client Libraries / SDKs](./client-libraries-index.md)
- [Cloud](./cloud-index.md)
- [Cloud account management](./cloud-account-management-index.md)

# Agent Instructions

This portal answers questions programmatically. To receive a synthesized,
source-cited answer instead of crawling page by page, append the `?ask=`
query parameter to any page URL on this site:

    /guides/quickstart?ask=how+do+I+authenticate

Optional parameters:

- `&goal=<what-you-are-trying-to-do>` steers the answer toward your
  objective (e.g. `&goal=write+a+python+client`).
- `&version=<label>` scopes the answer to a mounted version when the
  portal publishes more than one.

The response is `text/markdown`: the answer followed by a `# Sources` list
of the portal pages it was grounded in. Status codes are the contract:

- `200` — the answer; `402` — the portal owner’s plan or answer credits are
  exhausted (surface this to your operator; do NOT retry); `429` — you are
  rate-limited; back off for the `Retry-After` seconds; `503` — the answer
  lane is temporarily unavailable; fall back to crawling the `.md` pages.

For the full corpus map read `llms.txt` at the site root; for the tool
surface (search + page fetch as MCP tools) see `/mcp`.