rony-chat-bot/internal/portfolio/chunker_test.go

156 lines
3.8 KiB
Go
Raw Permalink Normal View History

package portfolio
import (
"strings"
"testing"
)
func TestSplitMarkdownSections(t *testing.T) {
cases := []struct {
name string
input string
wantCount int
wantHeading []string
}{
{
name: "frontmatter only",
input: `---
title: "Foo"
tags: ["go"]
---
# Foo
Body of foo.`,
wantCount: 2,
wantHeading: []string{"frontmatter", "Foo"},
},
{
name: "no frontmatter, multiple H2s",
input: `# Title
intro paragraph
## Description
description body
## Tech stack
- Go
- SQLite`,
wantCount: 3,
wantHeading: []string{"Title", "Description", "Tech stack"},
},
{
name: "H3 stays under parent H2",
input: `# T
## Section
content
### H3 detail
H3 content stays here`,
wantCount: 1, // T has no body → dropped; H3 content folds into Section
wantHeading: []string{"Section"},
},
{
name: "drop empty section",
input: `## X
ok
## Empty
## Y
content`,
wantCount: 2,
wantHeading: []string{"X", "Y"},
},
{
name: "long H2 sub-splits",
input: "## Long\n" + strings.Repeat("a ", 800),
wantCount: 2, // 2 sub-splits of Long
},
}
for _, c := range cases {
t.Run(c.name, func(t *testing.T) {
got := SplitMarkdownSections(c.input, DefaultChunkerConfig())
if len(got) != c.wantCount {
t.Errorf("got %d chunks, want %d. Headings: %v", len(got), c.wantCount, headings(got))
}
if c.wantHeading != nil {
if !equalSlice(headings(got), c.wantHeading) {
t.Errorf("headings = %v, want %v", headings(got), c.wantHeading)
}
}
})
}
}
func headings(sections []section) []string {
out := make([]string, len(sections))
for i, s := range sections {
out[i] = s.Heading
}
return out
}
func equalSlice(a, b []string) bool {
if len(a) != len(b) {
return false
}
for i := range a {
if a[i] != b[i] {
return false
}
}
return true
feat(rag): hybrid retrieval, reference documents, and vendor sampling Answers were short, sometimes in the wrong language, and occasionally about projects that do not exist. Measured on a 20-question battery against the real corpus in both Spanish and English, this takes grounded content from 3/10 to 9/10 and language matching from 7/10 to 10/10. Retrieval - Fuse FTS5 keyword search with dense vectors via Reciprocal Rank Fusion. Both halves are load-bearing: the corpus is English and visitors ask in Spanish, so the meaningful words score zero. "paga" appears 0 times in a document that says "Payments: Stripe" — the question "¿Con qué se paga en la tienda de ropa?" retrieved nothing at all. Embeddings put all three of that project's chunks on top. RRF ranks by agreement rather than comparing a BM25 score against a cosine, quantities with no shared scale. - internal/embed: OpenAI-compatible embeddings client, unit-normalised so a dot product is the cosine. Reorders by the response `index` field. - Store a content hash beside each vector and skip rows where it no longer matches the chunk. Chunk ids survive body edits, so without this an edited document keeps serving embeddings that describe text that is gone — reproduced live by changing a payment provider and watching the old one keep coming back. - Degrade to keyword-only when the embedder is down instead of failing. Reference documents that are not projects - Index `.mdx` alongside `.md`, and split sources into projects (announced in the catalogue) and reference material (retrievable, never listed). A CV is what someone deciding whether to hire actually reads, and it was unreachable while it lived only in the Astro site — but filing it under projects made the bot list "cv" as one of Victor's works. - Skip each directory's README. `data/projects/README.md` was being indexed, so the catalogue injected into every prompt announced "README" and "README.es" as projects of Victor's. - Exclude frontmatter from retrieval. It is dense metadata in a very short chunk, which makes it a magnet for short queries: a CV's `location:` field answered "¿Dónde ha trabajado Victor?" with a city instead of a work history. - Split oversized sections at `###` before falling back to byte offsets. A CV's Experience section is a list of jobs, and size-splitting cut one mid-word, stranding the employer's name in the previous chunk. Prompt and sampling - Inject the full project catalogue every turn. Top-K search returns the best matching sections, so "list every project" cannot be answered from retrieval alone, and a small model asked to enumerate from partial hits invents the rest. ~10 tokens per project; this is what stopped the invented names. - Wire the sampling parameters the model authors publish (top_k, top_p, min_p, repeat_penalty, presence_penalty) through config to llama.cpp. Leaving them at llama.cpp's defaults produced 16-token stub answers. - Localised system prompt selected by detected language. The English prompt plus "reply in the user's language" answered 1/5 Spanish questions in Spanish; few-shot examples fixed the language but got copied verbatim into real answers. - Fold compaction's system notes into the leading system message. Gemma's chat template rejects a system message that is not first, and the whole request failed with HTTP 400 the moment compaction fired. Configuration and docs - context_size 4096, down from 8192. The largest prompt this bot ever built over 20 real requests was 1255 tokens, compaction starts at ~3070, and the cut saved 212 MB resident with zero truncations and identical throughput. - Correct the RAM figures throughout. They were measured with a GPU absorbing llama.cpp's buffers; on a GPU-less VPS those come out of system RAM, which is 1.1 GB more for qwen2.5-3b and 2.8 GB more for granite. Both READMEs still started gemma-3-1b while the config defaulted to qwen, and neither started the embedder at all. Measured on the 2-core, 8 GB CPU-only target: 3.64 GB LLM + 0.91 GB embedder + 0.02 GB bot, 21.0 tok/s steady state. Known and unfixed, so they are not re-filed as new bugs: the model reads dates out of the CV correctly but does the arithmetic on them wrong, and "¿Dónde ha trabajado Victor?" still answers with projects rather than employers, though "¿En qué empresas ha trabajado?" works. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-30 21:45:37 +00:00
}
// An oversized section made of H3 entries (a CV's Experience list, a FAQ)
// must split per entry, not per byte. Size-splitting used to cut a job entry
// mid-word and strand the employer name in the previous chunk.
func TestSubSplitPrefersH3BoundariesOverByteOffsets(t *testing.T) {
body := "### Metrimex — Frontend Developer\n\n#### Jul 2024 Jun 2026\n\n" +
strings.Repeat("Built an access-control app for physical sites. ", 12) +
"\n\n### Didcom — Android Developer\n\n#### Jul 2023 Jul 2024\n\n" +
strings.Repeat("Built an Android app for an on-demand ride-sharing service. ", 12) +
"\n\n### Teknol — Software Developer\n\n#### Jun 2016 Jan 2017\n\n" +
strings.Repeat("Maintained an internal tool. ", 12)
got := subSplit([]section{{Heading: "Experience", Body: body}}, 400, 40)
if len(got) != 3 {
t.Fatalf("got %d chunks, want one per job:\n%+v", len(got), got)
}
for i, want := range []string{"Metrimex", "Didcom", "Teknol"} {
if !strings.Contains(got[i].Heading, want) {
t.Errorf("chunk %d heading = %q, want it to name %s", i, got[i].Heading, want)
}
if !strings.HasPrefix(got[i].Body, "### "+want) {
t.Errorf("chunk %d body should start at its own heading, got %.40q", i, got[i].Body)
}
}
// No chunk may begin mid-sentence — that is the defect this replaces.
for i, s := range got {
if strings.HasPrefix(s.Body, "... ") {
t.Errorf("chunk %d still starts with a byte-split continuation: %.40q", i, s.Body)
}
}
}
// A long section with no H3 structure still falls back to size splitting.
func TestSubSplitFallsBackToSizeWithoutH3(t *testing.T) {
body := strings.Repeat("plain prose with no subheadings at all. ", 40)
got := subSplit([]section{{Heading: "Description", Body: body}}, 300, 30)
if len(got) < 2 {
t.Fatalf("expected the oversized section to be split, got %d", len(got))
}
for _, s := range got {
if s.Heading != "Description" {
t.Errorf("size-split chunk changed heading to %q", s.Heading)
}
}
}