When you trace with the @traceable decorator or traceable wrapper, LangSmith supports uploading binary files (such as images, audio, videos, PDFs, and CSVs) alongside your traces. This is particularly useful when working with LLM pipelines using multimodal inputs or outputs.
In both the Python and TypeScript SDKs, you can add attachments to your traces by specifying the MIME type and binary content of each file. This page explains how to define and trace attachments using the Attachment type in Python and Uint8Array / ArrayBuffer in TypeScript.
Python
In the Python SDK, you can use the Attachment type to add files to your traces. Each Attachment requires:
mime_type (str): The MIME type of the file (e.g., "image/png").data (bytes | Path): The binary content of the file, or the file path.
You can also define an attachment with a tuple of the form (mime_type, data) for convenience.
There are two ways to provide file data:
-
Load the bytes yourself and pass them directly (works in all environments), or
-
Pass a
Path object and let the SDK read the file by setting dangerously_allow_filesystem=True on your @traceable decorator.
The dangerously_allow_filesystem flag exists as a safeguard for server and multi-tenant environments, where user-controlled input could influence a file path. In a trusted environment (a local script or a controlled pipeline where you own the file paths), it is safe to enable.
Decorate a function with @traceable and include your Attachment instances as arguments. The following example demonstrates both approaches: loading file bytes manually into an Attachment, and passing a Path object with dangerously_allow_filesystem=True:
from langsmith import traceable
from langsmith.schemas import Attachment
from pathlib import Path
import os
# 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
In the TypeScript SDK, you can add attachments to traces by using Uint8Array or ArrayBuffer as data types. Each attachment’s MIME type is specified within extractAttachments:
Uint8Array: Useful for handling binary data directly.ArrayBuffer: Represents fixed-length binary data, which you can convert to Uint8Array as needed.
In the TypeScript SDK, the extractAttachments function is an optional parameter in the traceable configuration. When the traceable-wrapped function is invoked, it extracts binary data (e.g., images, audio files) from your inputs and logs them alongside other trace data, specifying their MIME types.
You cannot directly pass in a file path in the TypeScript SDK, because accessing local files is not supported in all runtime environments.
traceable and include your attachments within the extractAttachments option. The signature is:
type AttachmentData = Uint8Array | ArrayBuffer;
type Attachments = Record<string, [string, AttachmentData]>;
extractAttachments?: (
...args: Parameters<Func>
) => [Attachments | undefined, KVMap];
import { traceable } from "langsmith/traceable";
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
);
