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

# Cosmetic ingredient manufacturer discovery

> Resolve ingredient aliases into manufacturers and distributors, such as cosmetic-grade squalane suppliers, in a cited shortlist and CSV with DeepResearch.

**Example question:** Who manufactures cosmetic-grade sodium hyaluronate, squalane and ectoin for the European market?

**You get:** A shortlist and CSV linking each ingredient to candidate products, companies, manufacturer or distributor roles, and supporting pages.

**Start with:** Ingredient names and aliases; required grade; target market; whether distributors should be included.

## Run with DeepResearch

Set `VALYU_API_KEY` in your environment, then run this illustrative request. Change the question and CSV fields for your own task. The CSV fields below describe the requested output, not a saved result.

<Accordion title="Run the research request">
  ```bash cURL theme={null}
  curl --fail-with-body https://api.valyu.ai/v1/deepresearch/tasks \
    -H "x-api-key: $VALYU_API_KEY" \
    -H "Content-Type: application/json" \
    --data-binary @- <<'JSON'
  {
    "query": "Identify up to three manufacturer candidates each for cosmetic-grade sodium hyaluronate, squalane and ectoin serving the European market. Use original company product pages and technical documentation. Distinguish manufacturers from distributors and role not stated. Record the exact product, identifier, grade and supporting source passage. Do not infer manufacturing ownership, stock availability or formulation suitability. Return one row per ingredient-product-company pair; retain uncertain matches explicitly.",
    "mode": "standard",
    "research_strategy": "Prefer company product specifications and manufacturer statements over marketplace listings. Search in relevant languages, but preserve original names and identifier spellings. Cite every row; mark missing or inaccessible evidence.",
    "report_format": "A concise evidence table, comparison limits and unresolved questions.",
    "deliverables": [
      {
        "type": "csv",
        "description": "One row per evidence item with the requested fields and supporting source URL.",
        "columns": [
          "ingredient",
          "product_name",
          "identifier",
          "company",
          "company_role",
          "grade",
          "market",
          "evidence_excerpt",
          "source_url",
          "accessed_date",
          "unresolved_match"
        ]
      }
    ]
  }
  JSON
  ```
</Accordion>

Save the returned `deepresearch_id`. Poll [Get status](/api-reference/endpoint/deepresearch-status) until the task completes, then read the report and download the CSV from `deliverables`.

## How it works

1. Search each ingredient with grade, manufacturer and local-language variants. Keep trade names separate from chemical identities.

2. Read original product pages and technical documents. Record whether the company explicitly calls itself the manufacturer, a distributor, or neither.

3. Produce one row per ingredient-product-company relationship. Preserve competing matches and missing identifiers instead of merging them.

To build the workflow inside your own agent, use [Search](/search/quickstart) to find sources and [Contents](/guides/content-extraction) to read selected pages. Keep the CSV fields above as your extraction schema.

## Check the result

Check every product-company relationship against the source. Verify grades and aliases; a similar trade name is not a match. Supplier claims are not independent tests of ingredient performance.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.