Parallel Data Enrichment

1---2name: parallel-data-enrichment3description: "Bulk data enrichment. Adds web-sourced fields (CEO names, funding, contact info) to lists of companies, people, or products. Use for enriching CSV files or inline data. Supports multi-turn: pass --previous-interaction-id from a prior research or enrichment to carry context forward."4user-invocable: true5argument-hint: <file or entities> with <fields to add>6compatibility: Requires parallel-cli and internet access.7allowed-tools: Bash(parallel-cli:*)8metadata:9  author: parallel10---11 12# Data Enrichment13 14Enrich: $ARGUMENTS15 16## Before starting17 18Inform the user that enrichment may take several minutes depending on the number of rows and fields requested.19 20## Step 1: Start the enrichment21 22Use ONE of these command patterns (substitute user's actual data):23 24For inline data:25 26```bash27parallel-cli enrich run --data '[{"company": "Google"}, {"company": "Microsoft"}]' --intent "CEO name and founding year" --target "output.csv" --no-wait --json28```29 30For CSV file:31 32```bash33parallel-cli enrich run --source-type csv --source "input.csv" --target "output.csv" --source-columns '[{"name": "company", "description": "Company name"}]' --intent "CEO name and founding year" --no-wait --json34```35 36If this is a **follow-up** to a previous research or enrichment task where you know the `interaction_id`, add context chaining:37 38```bash39parallel-cli enrich run --data '...' --intent "..." --target "output.csv" --no-wait --json --previous-interaction-id "$INTERACTION_ID"40```41 42By chaining `interaction_id` values across requests, each follow-up automatically has the full context of prior turns — so you can enrich entities discovered in earlier research without restating what was already found.43 44**IMPORTANT:** Always include `--no-wait` so the command returns immediately instead of blocking.45 46Parse the output to extract the `taskgroup_id`, `interaction_id`, and monitoring URL. Immediately tell the user:47- Enrichment has been kicked off48- The monitoring URL where they can track progress49 50Tell them they can background the polling step to continue working while it runs.51 52## Step 2: Poll for results53 54```bash55parallel-cli enrich poll "$TASKGROUP_ID" --timeout 540 --output "/tmp/$TARGET"56```57 58Use the same target filename from step 1. The `--target` flag on `enrich run` does not carry over to the poll — you must pass `--output` here to save the results.59 60Important:61- Use `--timeout 540` (9 minutes) to stay within tool execution limits62 63### If the poll times out64 65Enrichment of large datasets can take longer than 9 minutes. If the poll exits without completing:661. Tell the user the enrichment is still running server-side672. Re-run the same `parallel-cli enrich poll` command to continue waiting68 69## Response format70 71**After step 1:** Share the monitoring URL (for tracking progress).72 73**After step 2:**741. Report number of rows enriched752. Preview first few rows of the output CSV763. Tell user the full path to the output CSV file774. Share the `interaction_id` and tell the user they can ask follow-up questions that build on this enrichment78 79Do NOT re-share the monitoring URL after completion — the results are in the output file.80 81**Remember the `interaction_id`** — if the user asks a follow-up question that relates to this enrichment, use it as `--previous-interaction-id` in the next research or enrichment command.82 83## Setup84 85If `parallel-cli` is not found, install and authenticate:86 87```bash88curl -fsSL https://parallel.ai/install.sh | bash89```90 91If unable to install that way, install via pipx instead:92 93```bash94pipx install "parallel-web-tools[cli]"95pipx ensurepath96```97 98Then authenticate:99 100```bash101parallel-cli login102```103 104Or set an API key: `export PARALLEL_API_KEY="your-key"`