Tap Prompt Fragments

Prompt fragments let you teach the tap generator about a specific data source — its conventions, rate limits, preferred libraries, required env vars — without having to re-type the same hints into every tap description. Once a fragment is configured, its content is automatically appended to the LLM system prompt whenever the user’s text mentions the fragment’s key or any of its aliases (case-insensitive, word-boundary match). Fragments are per-tenant, stored in MongoDB ({env}-tap-prompt), and cached in memory with write-invalidation. No new dependencies and no schema changes — they piggyback on the same infrastructure as tap configs.

​

Where they apply

A matching fragment is injected into every AI flow that touches a tap or discovery: If a key appears in any of those texts, the fragment’s content is appended to a ## User-provided context block at the end of the system prompt.

​

Managing fragments

Fragments live under Configuration → Taps. The Configuration page itself has three sub-tabs:

1. Environment — tenant name, version, trial/hosted status, current AI provider summary.
2. AI Providers — AI Primary, CodeGen, and Embedding provider settings plus shared API keys.
3. Taps — the Prompt Fragments list.

​

Each fragment has

• Key (required, unique) — the primary match keyword, e.g. AWS, Polygon, Stripe. Matched case-insensitively with \b boundaries so AI won’t accidentally match email or Gmail.
• Aliases (optional, comma-separated) — additional match keywords. A single AWS fragment can also match S3, EC2, Lambda, boto3, etc.
• Content (required) — the extra system-prompt text. Typically 2-6 sentences covering library choice, env-var names, rate limits, pagination style, and gotchas.
• Enabled (default on) — unchecking keeps the fragment in storage but stops it from matching.

​

Top-of-page actions

• Create Fragment — opens an inline form. A Suggest button on the Content field asks the LLM to draft a fragment from the key + aliases you’ve entered (useful as a starting point; edit before saving).
• Load Examples — seeds a starter set of 4 fragments (AWS, Polygon, Stripe, SEC EDGAR). Keys that already exist are skipped. Confirm / Cancel inline — no browser popup.
• Export — downloads the fragment list as a pretty-printed JSON file (datris-tap-prompts-{YYYY-MM-DD}.json).
• Import — upload a JSON file in the same shape. Each fragment is POSTed individually; invalid entries are skipped. Existing keys are overwritten (create-or-update).

​

Writing good fragments

Keep them dense and actionable:

• Lead with the preferred library and the exact env var names the generator should use. Example: Use the stripe Python SDK (pip install stripe). Set stripe.api_key = os.environ.get("STRIPE_API_KEY").
• State rate limits explicitly so the generator can add throttling up front. Example: Polygon.io free tier is 5 requests per second. Throttle with time.sleep(0.25) or a ThreadPoolExecutor with max_workers=3.
• Note required headers or auth quirks. Example: SEC EDGAR requires a User-Agent header identifying the requester (e.g. "CompanyName contact@email"). Rate limit: 10 requests per second.
• Never include secrets or long examples. A fragment over ~2000 characters triggers a soft warning — multiple matching fragments can crowd the LLM context.

​

Injection preview in the tap wizard

After Generate Script or a Brainstorm reply, any matching fragment keys appear as chips under the description:

Extra context applied: AWS Polygon

Click a chip to jump to the Taps sub-tab for that fragment. This makes it easy to see what the LLM saw, and catch cases where a fragment matched when it shouldn’t have (or failed to match when it should have).

​

HTTP API

The same storage is exposed via REST for scripting and tenant migrations. See Taps API for field-by-field request/response shapes.

​

Performance

The injector caches matched fragments in a per-tenant ConcurrentHashMap with a 60s TTL as a safety net. Writes through the API (create / update / delete) invalidate immediately, so UI edits take effect on the next LLM call without restart. With zero fragments configured the hot path returns in microseconds — the tap/discovery flows pay no measurable cost.

​

Multi-tenant

Fragments are fully tenant-scoped. Each tenant’s fragments live in their own {env}-tap-prompt MongoDB collection and their own injector cache entry. A fragment configured on one tenant never leaks into another’s prompts.