上传带追踪的文件 - 以编程方式使用文档

使用 @traceable 装饰器或 traceable 包装器进行追踪时，LangSmith支持上传二进制文件（如图片、音频、视频、PDF和CSV）以及追踪。这在使用多模态输入或输出的LLM管道时特别有用。

在 Python 和 TypeScript SDK中，您可以通过指定每个文件的MIME类型和二进制内容来向追踪添加附件。本页面解释如何使用 Attachment 类型在Python中以及 Uint8Array / ArrayBuffer 在TypeScript中定义和追踪附件。

Python

在 Python SDK中，您可以使用 Attachment 类型向追踪添加文件。每个 Attachment requires:

- mime_type (str)：文件的MIME类型（例如， "image/png").
- data (bytes | Path)：文件的二进制内容或文件路径。

您还可以使用以下形式的元组定义附件 (mime_type, data) 以方便使用。

提供文件数据有两种方式：

- 自己加载字节并直接传递它们（适用于所有环境），或者
- 传递一个 Path 对象并通过设置让SDK读取文件，在您的 dangerously_allow_filesystem=True 上设置 @traceable decorator.

使用 @traceable 装饰函数，并包含您的 Attachment 实例作为参数。以下示例演示了两种方法：手动将文件字节加载到 Attachment中，以及传递一个带有 Path 的对象 dangerously_allow_filesystem=True:

from langsmith import traceable
from langsmith.schemas import Attachment
from pathlib import Path


# Must set dangerously_allow_filesystem to True if you want to use file paths
@traceable(dangerously_allow_filesystem=True)
def trace_with_attachments(
    val: int,
    text: str,
    image: Attachment,
    audio: Attachment,
    video: Attachment,
    pdf: Attachment,
    csv: Attachment,
):
    return f"Processed: {val}, {text}, {len(image.data)}, {len(audio.data)}, {len(video.data)}, {len(pdf.data), {len(csv.data)}}"

# Helper function to load files as bytes
def load_file(file_path: str) -> bytes:
    with open(file_path, "rb") as f:
        return f.read()

# Load files and create attachments
image_data = load_file("my_image.png")
audio_data = load_file("my_mp3.mp3")
video_data = load_file("my_video.mp4")
pdf_data = load_file("my_document.pdf")

image_attachment = Attachment(mime_type="image/png", data=image_data)
audio_attachment = Attachment(mime_type="audio/mpeg", data=audio_data)
video_attachment = Attachment(mime_type="video/mp4", data=video_data)
pdf_attachment = ("application/pdf", pdf_data) # Can just define as tuple of (mime_type, data)
csv_attachment = Attachment(mime_type="text/csv", data=Path(os.getcwd()) / "my_csv.csv")

# Define other parameters
val = 42
text = "Hello, world!"

# Call the function with traced attachments
result = trace_with_attachments(
    val=val,
    text=text,
    image=image_attachment,
    audio=audio_attachment,
    video=video_attachment,
    pdf=pdf_attachment,
    csv=csv_attachment,
)

TypeScript

在 TypeScript SDK中，您可以使用 Uint8Array or ArrayBuffer 作为数据类型向追踪添加附件。每个附件的MIME类型在 extractAttachments:

- Uint8Array中指定：用于直接处理二进制数据。
- ArrayBuffer：表示固定长度的二进制数据，您可以将其转换为 Uint8Array 按需使用。

在TypeScript SDK中， extractAttachments 函数是 traceable 配置中的可选参数。当调用追踪包装的函数时，它会从输入中提取二进制数据（例如图片、音频文件），并与其他追踪数据一起记录，指定其MIME类型。

使用 traceable 包装您的函数，并在 extractAttachments 选项。签名是：

type AttachmentData = Uint8Array | ArrayBuffer;
type Attachments = Record<string, [string, AttachmentData]>;

extractAttachments?: (
    ...args: Parameters
) => [Attachments | undefined, KVMap];

以下示例展示了一个完整实现：

const traceableWithAttachments = traceable(
    (
        val: number,
        text: string,
        attachment: Uint8Array,
        attachment2: ArrayBuffer,
        attachment3: Uint8Array,
        attachment4: ArrayBuffer,
        attachment5: Uint8Array,
    ) =>
        `Processed: ${val}, ${text}, ${attachment.length}, ${attachment2.byteLength}, ${attachment3.length}, ${attachment4.byteLength}, ${attachment5.byteLength}`,
    {
        name: "traceWithAttachments",
        extractAttachments: (
            val: number,
            text: string,
            attachment: Uint8Array,
            attachment2: ArrayBuffer,
            attachment3: Uint8Array,
            attachment4: ArrayBuffer,
            attachment5: Uint8Array,
        ) => [
            {
                "image inputs": ["image/png", attachment],
                "mp3 inputs": ["audio/mpeg", new Uint8Array(attachment2)],
                "video inputs": ["video/mp4", attachment3],
                "pdf inputs": ["application/pdf", new Uint8Array(attachment4)],
                "csv inputs": ["text/csv", new Uint8Array(attachment5)],
            },
            { val, text },
        ],
    }
);

const fs = Deno // or Node.js fs module
const image = await fs.readFile("my_image.png"); // Uint8Array
const mp3Buffer = await fs.readFile("my_mp3.mp3");
const mp3ArrayBuffer = mp3Buffer.buffer; // Convert to ArrayBuffer
const video = await fs.readFile("my_video.mp4"); // Uint8Array
const pdfBuffer = await fs.readFile("my_document.pdf");
const pdfArrayBuffer = pdfBuffer.buffer; // Convert to ArrayBuffer
const csv = await fs.readFile("test-vals.csv"); // Uint8Array

// Define example parameters
const val = 42;
const text = "Hello, world!";

// Call traceableWithAttachments with the files
const result = await traceableWithAttachments(
    val, text, image, mp3ArrayBuffer, video, pdfArrayBuffer, csv
);

Python

TypeScript

相关