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

# Send conversation with interaction traces

You can use this endpoint to send the full conversation between the user and the AI system. This approach allows to send interactions (with their traces) in a single request. This endpoint is designed for sending data asynchronously in bulk once conversations are completed.

<ParamField body="conversation" type="object" required>
  The conversation an user is having with an LLM based assistant.

  <Expandable title="conversation properties">
    <ParamField path="interactions" type="object[]" required>
      The interaction to send to the nebuly platform.

      <Expandable title="properties">
        <ParamField path="input" type="string" initialValue="input" required>
          The user input in the interaction.
        </ParamField>

        <ParamField path="output" type="string" initialValue="output" required>
          The LLM output in the interaction (the text shown to the user as assistant response).
        </ParamField>

        <ParamField path="time_start" type="string" initialValue="2024-01-01" required>
          The start time of the call to the LLM. You can approximate this to the time when the user sends the interaction. The accepted format is the `ISO 8601`.

          Example: `2023-12-07T15:00:00.000Z`
        </ParamField>

        <ParamField path="time_end" type="string" initialValue="2024-01-01" required>
          The end time of the call to the LLM. This is when the user receives the full answer from the model. The accepted format is the `ISO 8601`.

          Example: `2023-12-07T15:00:00.000Z`
        </ParamField>

        <ParamField path="tags" type="dict<string, string>">
          Tag user interactions by adding key-value pairs using this parameter. Each key represents the tag name, and the corresponding value is the tag value.

          For example, if you want to tag an interaction with the model version used to reply to user input, provide it as an argument for nebuly\_tags, e.g. `{"version" => "v1.0.0"}`. You have the flexibility to define custom tags, making them available as potential filters on the Nebuly platform.
        </ParamField>

        <ParamField path="feedback_actions" type="object[]">
          A list of feedback actions provided by the end-user during or after the interaction.

          Each object in the array can contain:

          * `slug`: (string) – the type of action. Accepted values include:
            * `thumbs_up`
            * `thumbs_down`
            * `copy_input`
            * `copy_output`
            * `paste`
            * `comment`
            * `regenerate`
            * `edit`
            * `rating`
          * `text`: (string, optional) – textual feedback associated with the action (if applicable).
          * `value`: (number, optional) – only used for the `rating` action to capture a numerical score.

          **Example:**

          ```json theme={null}
          "feedback_actions": [
              {
              "slug": "thumbs_up",
              "text": "Very helpful response!"
              },
              {
              "slug": "comment",
              "text": "Can you explain more about this?"
              },
              {
              "slug": "rating",
              "value": 4,
              "text": "Pretty good!"
              },
              {
              "slug": "regenerate"
              }
          ]
          ```
        </ParamField>

        <ParamField body="trace" type="object[]">
          The full trace of your LLM agent or chain. There are two kind of steps that can compose a trace:

          <Tabs>
            <Tab title="LLMTrace">
              The intermediate call to an LLM.

              <Expandable title="properties">
                <ParamField path="model" type="string" required>
                  The LLM used.
                </ParamField>

                <ParamField path="messages" type="object[]">
                  A list of messages from the conversation so far, following the same format used by OpenAI Chat Completion endpoints.

                  Each message has two required fields:

                  * `role`: the role of who is sending the message. Possible values are: **system**, **user**, **assistant**, **tool**.
                  * `content`: the content of the message.

                  The messages in the list should be ordered according to the conversation's sequence, from the oldest message to the most recent.
                  Example:

                  ```
                  "messages": [
                      {
                          "role": "system",
                          "content: "This is a system prompt"
                      },
                      {
                          "role": "user",
                          "content": "user input 1"
                      },
                      {
                          "role": "assistant",
                          "content": "assistant response 1"
                      },
                      {
                          "role": "user",
                          "content": "user input"
                      }
                  ]
                  ```
                </ParamField>

                <ParamField path="output" type="string" initialValue="output" required>
                  The LLM output message.
                </ParamField>

                <ParamField path="input_tokens" type="integer">
                  The number of input tokens.
                </ParamField>

                <ParamField path="output_tokens" type="integer">
                  The number of output tokens.
                </ParamField>
              </Expandable>
            </Tab>

            <Tab title="RetrievalTrace">
              The intermediate call to a retriever tool (vector db) or agent tool (function calling).

              <Expandable title="properties">
                <ParamField path="source" type="string" initialValue="rag source name" required>
                  The type of data source used, e.g. db\_reader\_tool or vector\_db.
                </ParamField>

                <ParamField path="input" type="string" initialValue="input" required>
                  The query to the RAG source.
                </ParamField>

                <ParamField path="outputs" type="string[]" required>
                  The RAG source output. It is presented in list format to accommodate multiple outputs for a single query.
                </ParamField>
              </Expandable>
            </Tab>

            <Tab title="EmbeddingTrace">
              Embedding trace details for an LLM.

              <Expandable title="properties">
                <ParamField path="model" type="string" required>
                  The model used for embedding.
                </ParamField>

                <ParamField path="input" type="string" required>
                  The input text to be embedded.
                  Example:

                  ```
                  "input": "Text to be embedded"
                  ```
                </ParamField>

                <ParamField path="input_tokens" type="integer">
                  The number of input tokens.
                  Example:

                  ```
                  "input_tokens": 10
                  ```
                </ParamField>
              </Expandable>
            </Tab>
          </Tabs>
        </ParamField>
      </Expandable>
    </ParamField>

    <ParamField path="end_user" type="string" required>
      An id or username uniquely identifying the end-user. We recommend hashing their username or email address, in order to avoid sending us any identifying information.
    </ParamField>
  </Expandable>
</ParamField>