Why attach metadata to RAG chunks?

Metadata lets your vector store filter and re-rank beyond pure similarity — for example restricting retrieval to a category, date range, or document type. Rich metadata improves precision and powers hybrid search.

Where does my API key go?

It stays in your browser tab and is sent directly to OpenAI or Anthropic with the request you trigger. It is never stored, logged, or routed through any Gera server, and refreshing the tab clears it.

What does the output look like?

A single JSON object containing the fields you selected — typically title, summary, keywords (an array), category, and an inferred date. It is valid JSON ready to merge into your chunk's metadata field before upsert.

Which fields should I generate?

Title and keywords help recall; category enables filtering; summary is useful for re-ranking or display. Generate only the fields your retrieval layer actually uses to keep token cost and noise down.

Will the date always be accurate?

The model infers a date only if the text mentions one or implies a clear timeframe; otherwise it returns null. Never treat an inferred date as authoritative for compliance-sensitive data — verify against the source.

RAG Document Metadata Tagger (BYO-key)

Good retrieval is rarely about embeddings alone. The metadata you attach to each chunk — title, category, keywords, date — is what lets a vector store filter and re-rank results instead of returning the nearest-but-irrelevant neighbour. This tool generates that metadata for you, using your own OpenAI or Anthropic key, and hands back clean JSON to drop into your ingestion pipeline.

How it works

Choose a provider and model, paste your API key, and drop in a document chunk. Select which fields you want — title, summary, keywords, category, date. The tool sends one direct request from your browser asking the model to return a strict JSON object with exactly those fields. The response is parsed, validated, and shown as formatted JSON you can copy verbatim into the metadata field of your upsert call.

Your key never reaches a Gera server — it is held only in the tab and sent straight to the provider (with the official direct-browser-access header for Anthropic). Refreshing clears it.

Using the output

Merge the JSON into each chunk’s metadata before calling your vector DB’s upsert (Pinecone, Weaviate, Qdrant, pgvector, etc.).
Use category and date as filter predicates at query time to narrow the candidate set.
Keep keywords for hybrid (dense + sparse) search or BM25 boosting.

Tips

Cheaper, faster models (gpt-4o-mini, claude-3-5-haiku) are usually plenty for short tagging tasks and minimise cost.
Generate only the fields your retrieval layer uses — every extra field is tokens spent and noise stored.
Tag at the chunk level, not the whole document, so per-chunk filtering stays meaningful.