How do I specify which columns to embed?

Use the `columns` parameter with a list of column names or indices. The columns are concatenated in order to form the text that gets embedded. Unlisted columns can still be included as metadata.

Does it handle CSV files with different delimiters?

Yes. Set the `delimiter` parameter to any single character (comma, tab, pipe, semicolon). Tab-separated files (.tsv) are auto-detected.

What happens with missing values?

Missing values are skipped during text concatenation. You can alternatively set `missing_value_placeholder` to replace blanks with a default string like 'N/A'.

data

CSV
Embeddings
Converter

Convert CSV files into vector embeddings by selecting and combining columns into text representations. Supports header mapping, custom delimiters, and batch processing for large datasets.

Max file size: 1 GB

Estimated: 1-5 sec per 1000 rows

2 input formats

How It Works

Upload a CSV file or provide a URL.

Column headers are parsed and mapped to embedding fields.

Selected columns are concatenated into a text representation per row.

Each row's text is embedded using the selected model.

Embeddings are returned with row identifiers and metadata.

Code Examples

import os, requests

API = "https://api.mixpeek.com"
H = {"Authorization": f"Bearer {os.environ['MIXPEEK_API_KEY']}",
     "X-Namespace": os.environ["NAMESPACE_ID"]}

# 1. a bucket, with a schema that declares the field you will send
bucket = requests.post(f"{API}/v1/buckets", headers=H, json={
    "bucket_name": "csv-inputs",
    "bucket_schema": {"properties": {"csv": {"type": "text"}}},
}).json()

# 2. land the file as an object. the URL goes in data, on the blob
requests.post(f"{API}/v1/buckets/{bucket['bucket_id']}/objects", headers=H, json={
    "key_prefix": "run-1",
    "blobs": [{"property": "csv", "type": "text",
               "data": "https://example.com/rows.csv"}],
})

# 3. a collection over that bucket, running the extractor
collection = requests.post(f"{API}/v1/collections", headers=H, json={
    "collection_name": "csv-to-embeddings",
    "source": {"type": "bucket", "bucket_ids": [bucket["bucket_id"]]},
    "feature_extractor": {"feature_extractor_name": "text_extractor", "version": "v1"},
}).json()

# 4. run extraction over the bucket
requests.post(f"{API}/v1/buckets/{bucket['bucket_id']}/batches", headers=H, json={
    "collection_ids": [collection["collection_id"]],
    "auto_submit": True,
})

# 5. read the output
docs = requests.get(
    f"{API}/v1/collections/{collection['collection_id']}/documents", headers=H
).json()
print(docs)

Use Cases

Embed product catalogs exported from e-commerce platforms

Create vector indexes from CRM data exports

Build semantic search over spreadsheet data

Enable AI-powered queries on analytics data

Supported Input Formats

CSV

TSV

Quick Info

Categorydata

Max File Size1 GB

Est. Time1-5 sec per 1000 rows

Extractorstructured-data-descriptor

Processing millions of files?

Run this as a managed pipeline over your whole library, no infrastructure to build or maintain. Talk to us about processing at scale.

Run it over a library

Mixpeek runs this conversion as a pipeline over a whole library in your object storage, with the output landing as queryable documents. It is not a single-file converter.

Frequently Asked Questions

Related Converters

JSON

Embeddings

JSON to Embeddings

Convert JSON objects and arrays into semantic vector embeddings. Supports nested structures, field selection, and configurable serialization strategies for optimal embedding quality.

Text