537aebc302
- Change prompt to reflect new output format: title, type, subtype, domain, content - Remove slug/path generation responsibility from LLM — pipeline now handles it - Wikilinks change from [[slug|Display Name]] to [[Display Name]] only - LLM no longer includes frontmatter or paths in output docs(schema): update LLM output format and wikilink convention for Level 3 - Specify JSON schema: title, type, subtype, domain, content fields - Remove frontmatter requirements from schema output (handled by pipeline) - Simplify wikilink format to [[Display Name]] — no slug or pipe - Pipeline now responsible for slug generation and frontmatter construction These changes shift slug/frontmatter generation from LLM to pipeline, reducing cognitive load on the model and improving control over output. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
64 lines
2.5 KiB
Go
64 lines
2.5 KiB
Go
// ingestion/internal/pipeline/prompt.go
|
|
package pipeline
|
|
|
|
import (
|
|
"fmt"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/mathiasbq/hyperguild/ingestion/internal/wiki"
|
|
)
|
|
|
|
const systemPrompt = `You are a wiki agent. Read the source material and produce structured wiki pages following the schema provided.
|
|
|
|
Output ONLY a valid JSON array — no markdown fences, no other text before or after.
|
|
Each element must have exactly these fields:
|
|
"title" — exact page title (e.g. "FinBERT", "Ryan Singer", "Shape Up")
|
|
"type" — exactly one of: "source", "concept", "entity"
|
|
"subtype" — for source: article|pdf|book|video|note|project; for entity: person|company|tool|model|framework|technology; omit for concept
|
|
"domain" — one of the domains in the schema (omit if none fits)
|
|
"content" — Markdown body only — NO frontmatter, NO path, NO slug
|
|
|
|
Wikilinks in content: [[Display Name]] — just the display name, no slug, no pipe separator.
|
|
Only link to pages listed in the inventory or pages you are creating in this response.`
|
|
|
|
// BuildPrompt constructs the user prompt for a single chunk.
|
|
func BuildPrompt(schema, source, content string, inventory map[wiki.PageType][]wiki.Entry) string {
|
|
var sb strings.Builder
|
|
|
|
fmt.Fprintf(&sb, "Today's date is %s.\n\n", time.Now().UTC().Format("2006-01-02"))
|
|
|
|
sb.WriteString("## Schema\n\n")
|
|
sb.WriteString(schema)
|
|
sb.WriteString("\n\n")
|
|
|
|
sb.WriteString("## Existing wiki pages\n\n")
|
|
sb.WriteString("Reference these pages by display name only — [[Display Name]] — in your content.\n\n")
|
|
|
|
for _, pt := range []wiki.PageType{wiki.PageTypeConcept, wiki.PageTypeEntity, wiki.PageTypeSource} {
|
|
entries := inventory[pt]
|
|
label := strings.ToUpper(string(pt)[:1]) + string(pt)[1:]
|
|
if len(entries) == 0 {
|
|
fmt.Fprintf(&sb, "%s — (none yet)\n\n", label)
|
|
continue
|
|
}
|
|
fmt.Fprintf(&sb, "%s:\n", label)
|
|
for _, e := range entries {
|
|
fmt.Fprintf(&sb, " - %s\n", e.Title)
|
|
}
|
|
sb.WriteString("\n")
|
|
}
|
|
|
|
sb.WriteString("## Non-negotiable rules\n\n")
|
|
sb.WriteString("1. Output ONLY a valid JSON array — no prose, no fences.\n")
|
|
sb.WriteString("2. Fields: title, type, subtype (if applicable), domain (if applicable), content.\n")
|
|
sb.WriteString("3. Wikilinks: [[Display Name]] — no slug, no pipe. The pipeline handles slugs.\n")
|
|
sb.WriteString("4. Section links must match their section type (Related Concepts → concepts only, etc.).\n")
|
|
sb.WriteString("5. One source page per book — if inventory shows it exists, return it as an UPDATE.\n\n")
|
|
|
|
fmt.Fprintf(&sb, "## Source: %s\n\n", source)
|
|
sb.WriteString(content)
|
|
|
|
return sb.String()
|
|
}
|