> ## Documentation Index
> Fetch the complete documentation index at: https://docs.galtea.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Create Inference Result Batch

> Create a batch of inference results in a session.

## Returns

Returns a list of [InferenceResult](/concepts/product/version/session/inference-result) objects.

## Example

```python theme={"system"}
inference_result = galtea.inference_results.create_batch(
    session_id=session_id,
    conversation_turns=[
        {"role": "user", "content": "Hi"},
        {"role": "assistant", "content": "Hello!"},
    ],
)
```

## Parameters

<ResponseField name="session_id" type="string" optional>
  The session ID to log the inference results to.

  <Note>Instead of a `session_id`, you can reference an existing session by its own conversation id (see the section below). Provide exactly one of the two.</Note>
</ResponseField>

<Accordion title="Log to an existing session by your own conversation ID">
  If you already created the session via the [sessions API](/sdk/api/session/service) with your own `custom_id`, reference it here with `session_custom_id` plus a `version_id` or `product_id` to append inference results to it. If no matching session exists, the call returns a `400` error — create it first via the sessions API.

  <ResponseField name="session_custom_id" type="string" optional>
    Your own conversation id, as an alternative to `session_id`. Galtea finds an existing session with this id (per version); the session is not created here. Requires `version_id` or `product_id`.
  </ResponseField>

  <ResponseField name="version_id" type="string" optional>
    The version the session is anchored to when using `session_custom_id`. If both anchors are given, `version_id` wins and `product_id` is ignored.
  </ResponseField>

  <ResponseField name="product_id" type="string" optional>
    Product anchor used when no `version_id` is given with `session_custom_id`: Galtea finds the session with this custom id under the product (across its versions).
  </ResponseField>

  <Note>If no session matches the `session_custom_id` and anchor, the call returns a `400` error. Create the session first via the [sessions API](/sdk/api/session/service).</Note>
</Accordion>

<ResponseField name="conversation_turns" type="list[dict]" required>
  A list of dictionaries, where each dictionary represents a **conversation turn** with `role` and `content` keys as mandatory and an optional `retrieval_context` key.
  The `role` key can only have these values: `user` or `assistant`.

  <Note>
    The `retrieval_context` key is optional and can be sent to our platform if you have used it when calling your AI product.
    For this reason, it only makes sense to send it when we have a message with role `assistant`.
    When set, Galtea also records it as a `RETRIEVER` trace on that turn's inference result.
  </Note>

  <Warning>
    Maximum batch size recommended: **100 turns**. For longer conversations, split into
    multiple batches or use the individual `create()` method.
  </Warning>
</ResponseField>

<ResponseField name="conversation_simulator_version" type="string" optional>
  The version of Galtea's conversation simulator used to generate the user messages. This should only be provided when logging a conversation that was generated using the simulator. This parameter helps with traceability and analytics for conversations created through Galtea's simulation capabilities.
</ResponseField>