pi-knowledge 0.11.0 → 0.12.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +11 -0
- package/README.md +8 -7
- package/dist/src/embedding/provider.d.ts +12 -0
- package/dist/src/embedding/provider.js +46 -5
- package/dist/src/engine.d.ts +3 -1
- package/dist/src/engine.js +64 -20
- package/dist/src/indexer/chunker.d.ts +1 -1
- package/dist/src/indexer/chunker.js +2 -2
- package/dist/src/indexer/embedding-safe-chunks.d.ts +5 -0
- package/dist/src/indexer/embedding-safe-chunks.js +215 -0
- package/dist/src/indexer/html.d.ts +1 -0
- package/dist/src/indexer/html.js +49 -0
- package/dist/src/model-worker-client.d.ts +4 -0
- package/dist/src/model-worker-client.js +17 -1
- package/dist/src/model-worker.js +63 -15
- package/dist/src/storage/sqlite.d.ts +1 -0
- package/dist/src/storage/sqlite.js +3 -0
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,16 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## [0.12.0] - 2026-10-19
|
|
4
|
+
|
|
5
|
+
### Added
|
|
6
|
+
- Added embedding-safe chunk finalization for add, update, URL, inline-text, and JSONL import paths. Local inputs use the existing model worker tokenizer; OpenAI-compatible inputs use the configured complete-input character cap.
|
|
7
|
+
- Added `knowledge_doctor` action `reindex_for_embedding_budget` for KBs created before the current chunk input policy.
|
|
8
|
+
- Added dependency-free structured HTML normalization for URL sources, preserving headings, paragraphs, lists, tables, and entities for heading-aware chunking.
|
|
9
|
+
|
|
10
|
+
### Fixed
|
|
11
|
+
- Prevented local and OpenAI-compatible embedding inputs from silently discarding oversized multilingual or context-enriched chunk tails.
|
|
12
|
+
- Kept the model worker startup single-flight and Node strip-only compatible while reusing it for batched tokenizer measurement.
|
|
13
|
+
|
|
3
14
|
## [0.11.0] - 2026-09-23
|
|
4
15
|
|
|
5
16
|
### Added
|
package/README.md
CHANGED
|
@@ -23,7 +23,8 @@ Unlike `pi-memory` (which manages the agent's own notes), `pi-knowledge` indexes
|
|
|
23
23
|
|
|
24
24
|
- **Local-first project memory**: stores indexes under `~/.pi/knowledge/`; no project files are modified.
|
|
25
25
|
- **Hybrid retrieval**: lexical-anchored BM25 + semantic vectors + normalized weighted score fusion, with semantic mode for vector-only conceptual recall.
|
|
26
|
-
- **Code-aware indexing**: recursive AST chunking for
|
|
26
|
+
- **Code- and document-aware indexing**: recursive AST chunking for supported code, heading-aware Markdown chunks, and an embedding-safe finalizer that preserves oversized multilingual tails without adding a heavy document runtime.
|
|
27
|
+
- **Structured URL indexing**: preserves HTML headings, paragraphs, lists, tables, and entities as lightweight Markdown-like text without a browser, Docling runtime, or new dependency.
|
|
27
28
|
- **Lightweight symbol lookup**: indexes functions, methods, classes, interfaces, types, variables, route-like handlers, Markdown headings, config keys, and env vars for exact agent lookup.
|
|
28
29
|
- **Better agent answers**: adaptive context windows, diversity reranking, optional cross-encoder reranking, and diagnostics.
|
|
29
30
|
- **Large-project stability**: persisted indexing progress, capped batches, streaming vector scans, and stuck-job detection.
|
|
@@ -144,8 +145,8 @@ Mode selection contract:
|
|
|
144
145
|
|
|
145
146
|
Search results use balanced diversity reranking by default so near-duplicate chunks from the same file do not dominate the top results. Diversity scoring considers lexical overlap, same-file line proximity, overlapping adaptive windows, available embedding-vector similarity, file-level interleaving, and a small KB trust multiplier that favors ready file/directory sources over stale, URL, or imported text sources. In `adaptive` mode, code chunks with AST metadata can prefer same-parent/sibling chunks inside the same bounded file window; this is metadata-driven context expansion, not caller/callee analysis. Use `diversity: "off"` only when raw ranking order is needed for diagnostics. Agents can request search diagnostics to inspect mode fallback, selected profile, applied search tuning, ranking coverage, path/source/test boosts, adjusted scores, and provenance such as chunk id, chunk hash, match reason, stale flag, source freshness, and adaptive `source_chunk_ids` where available.
|
|
146
147
|
|
|
147
|
-
For best search quality, rebuild or update existing knowledge bases after upgrading. New indexes use contextual retrieval units: embeddings and FTS include file path, file type, Markdown heading breadcrumbs, and AST-derived code structure such as symbol names, scopes, parent symbols, and signatures while returned results keep the original chunk text readable.
|
|
148
|
-
Symbol/config/heading metadata
|
|
148
|
+
For best search quality, rebuild or update existing knowledge bases after upgrading. New indexes use contextual retrieval units: embeddings and FTS include file path, file type, Markdown heading breadcrumbs, and AST-derived code structure such as symbol names, scopes, parent symbols, and signatures while returned results keep the original chunk text readable. Before embedding, the complete contextual input is checked against the active provider budget; only oversized chunks are split again along structural boundaries.
|
|
149
|
+
Symbol/config/heading metadata and embedding-safe chunk boundaries are rebuilt during `knowledge_update`. `knowledge_doctor` reports `reindex_for_embedding_budget` for older KBs: file, directory, and URL sources can use `knowledge_update`; imported or inline-text sources should be re-imported or re-added from the original source.
|
|
149
150
|
|
|
150
151
|
## Embedding Configuration
|
|
151
152
|
|
|
@@ -170,9 +171,9 @@ export PI_KNOWLEDGE_EMBEDDING_BASE_URL=http://127.0.0.1:8080/v1
|
|
|
170
171
|
# Set PI_KNOWLEDGE_EMBEDDING_API_KEY or OPENAI_API_KEY only if your endpoint requires bearer auth.
|
|
171
172
|
```
|
|
172
173
|
|
|
173
|
-
API embedding failures are surfaced by default so configuration and context-window problems are visible. To explicitly allow query-time local fallback after API failures, set `PI_KNOWLEDGE_EMBEDDING_API_FALLBACK=local`; indexing/import/update document batches still fail instead of creating mixed-provider vector files.
|
|
174
|
+
API embedding failures are surfaced by default so configuration and context-window problems are visible. To explicitly allow query-time local fallback after API failures, set `PI_KNOWLEDGE_EMBEDDING_API_FALLBACK=local`; indexing/import/update document batches still fail instead of creating mixed-provider vector files. Inputs are never silently truncated.
|
|
174
175
|
|
|
175
|
-
|
|
176
|
+
OpenAI-compatible embedding inputs use a 20000-character complete-input safety cap by default. Indexing splits oversized chunks before HTTP requests; direct oversized query/document calls fail explicitly. Adjust the cap with `PI_KNOWLEDGE_EMBEDDING_MAX_CHARS` when the remote model has a different context window. Changing the cap changes embedding compatibility and requires `knowledge_update`.
|
|
176
177
|
|
|
177
178
|
For self-hosted servers with smaller request limits, set `PI_KNOWLEDGE_EMBEDDING_BATCH_SIZE` to the maximum number of chunk inputs the server accepts per embedding request.
|
|
178
179
|
|
|
@@ -231,8 +232,8 @@ All data is stored globally at `~/.pi/knowledge/` under Pi or `~/.omp/knowledge/
|
|
|
231
232
|
- **Reset**: delete the active knowledge directory to start fresh
|
|
232
233
|
- **Override**: set `PI_KNOWLEDGE_DIR` or `OMP_KNOWLEDGE_DIR`
|
|
233
234
|
- **Project safety**: pi-knowledge is read-only on indexed directories — no files are created or modified in your project
|
|
234
|
-
- **Updates**:
|
|
235
|
-
- **Symbol
|
|
235
|
+
- **Updates**: schema migrations run automatically, but index-time behavior changes are not applied to existing vectors at startup. `knowledge_doctor` reports actionable reindex requirements without loading the embedding model.
|
|
236
|
+
- **Symbol and chunk-policy indexes**: `knowledge.db` stores lightweight symbol/config/heading metadata plus an embedding input policy version. File, directory, and URL KBs with retained source paths can rebuild them with `knowledge_update`; imported portable KBs and inline text KBs should be re-imported or re-added because they intentionally do not store an active local source manifest.
|
|
236
237
|
|
|
237
238
|
## Development
|
|
238
239
|
|
|
@@ -12,24 +12,35 @@ export interface EmbeddingConfig {
|
|
|
12
12
|
pooling: "mean";
|
|
13
13
|
normalize: true;
|
|
14
14
|
}
|
|
15
|
+
export interface EmbeddingInputMeasurement {
|
|
16
|
+
counts: number[];
|
|
17
|
+
maximum: number;
|
|
18
|
+
preferredMaximum: number;
|
|
19
|
+
unit: "tokens" | "characters";
|
|
20
|
+
}
|
|
15
21
|
export declare const CURRENT_EMBEDDING_MODEL = "multilingual-e5-small";
|
|
16
22
|
export declare const DEFAULT_LOCAL_EMBEDDING_MODEL = "multilingual-e5-small";
|
|
17
23
|
export declare const DEFAULT_OPENAI_EMBEDDING_MODEL = "text-embedding-3-small";
|
|
18
24
|
export declare const DEFAULT_OPENAI_BASE_URL = "https://api.openai.com/v1";
|
|
25
|
+
export declare const LOCAL_EMBEDDING_MAX_TOKENS = 512;
|
|
26
|
+
export declare const LOCAL_EMBEDDING_PREFERRED_TOKENS = 448;
|
|
19
27
|
export declare const DEFAULT_API_MAX_EMBED_CHARS = 20000;
|
|
20
28
|
export declare function resolveEmbeddingConfig(env?: NodeJS.ProcessEnv): EmbeddingConfig;
|
|
21
29
|
export declare function embeddingConfigLabel(config: EmbeddingConfig): string;
|
|
22
30
|
export declare function embeddingSignature(config: EmbeddingConfig, dimension: number): string;
|
|
23
31
|
export declare function dispose(): Promise<void>;
|
|
24
32
|
export declare function prepareForShutdown(): Promise<void>;
|
|
33
|
+
export declare function measureEmbeddingInputs(texts: string[], prefix: EmbeddingPrefix, config: EmbeddingConfig, signal?: AbortSignal): Promise<EmbeddingInputMeasurement>;
|
|
25
34
|
export declare function embedTextsWithConfig(texts: string[], prefix: EmbeddingPrefix, signal?: AbortSignal, options?: {
|
|
26
35
|
allowApiFallback?: boolean;
|
|
36
|
+
inputValidated?: boolean;
|
|
27
37
|
}): Promise<{
|
|
28
38
|
vectors: Float32Array[];
|
|
29
39
|
config: EmbeddingConfig;
|
|
30
40
|
}>;
|
|
31
41
|
export declare function embedTexts(texts: string[], prefix: EmbeddingPrefix, signal?: AbortSignal, options?: {
|
|
32
42
|
allowApiFallback?: boolean;
|
|
43
|
+
inputValidated?: boolean;
|
|
33
44
|
}): Promise<Float32Array[]>;
|
|
34
45
|
export declare function embedQueryWithConfig(text: string, signal?: AbortSignal): Promise<{
|
|
35
46
|
vector: Float32Array;
|
|
@@ -37,3 +48,4 @@ export declare function embedQueryWithConfig(text: string, signal?: AbortSignal)
|
|
|
37
48
|
}>;
|
|
38
49
|
export declare function embedQuery(text: string, signal?: AbortSignal): Promise<Float32Array>;
|
|
39
50
|
export declare function embedDocuments(texts: string[], signal?: AbortSignal): Promise<Float32Array[]>;
|
|
51
|
+
export declare function embedValidatedDocuments(texts: string[], signal?: AbortSignal): Promise<Float32Array[]>;
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import { createHash } from "node:crypto";
|
|
2
|
-
import { embedInModelWorker } from "../model-worker-client.js";
|
|
2
|
+
import { embedInModelWorker, measureEmbeddingInputInModelWorker } from "../model-worker-client.js";
|
|
3
3
|
let disposeTimer = null;
|
|
4
4
|
let disposePromise = null;
|
|
5
5
|
let activeRuns = 0;
|
|
@@ -9,6 +9,8 @@ export const CURRENT_EMBEDDING_MODEL = "multilingual-e5-small";
|
|
|
9
9
|
export const DEFAULT_LOCAL_EMBEDDING_MODEL = "multilingual-e5-small";
|
|
10
10
|
export const DEFAULT_OPENAI_EMBEDDING_MODEL = "text-embedding-3-small";
|
|
11
11
|
export const DEFAULT_OPENAI_BASE_URL = "https://api.openai.com/v1";
|
|
12
|
+
export const LOCAL_EMBEDDING_MAX_TOKENS = 512;
|
|
13
|
+
export const LOCAL_EMBEDDING_PREFERRED_TOKENS = 448;
|
|
12
14
|
export const DEFAULT_API_MAX_EMBED_CHARS = 20_000;
|
|
13
15
|
const IDLE_TIMEOUT_MS = Number(process.env.PI_KNOWLEDGE_EMBEDDING_IDLE_MS ?? 30_000);
|
|
14
16
|
const ENABLE_NATIVE_IDLE_DISPOSE = process.env.PI_KNOWLEDGE_ENABLE_NATIVE_IDLE_DISPOSE === "true";
|
|
@@ -141,11 +143,41 @@ export async function prepareForShutdown() {
|
|
|
141
143
|
function applyEmbeddingPrefix(text, prefix, config) {
|
|
142
144
|
return config.prefixes === "on" ? `${prefix}: ${text}` : text;
|
|
143
145
|
}
|
|
146
|
+
export async function measureEmbeddingInputs(texts, prefix, config, signal) {
|
|
147
|
+
if (signal?.aborted)
|
|
148
|
+
throw new Error("Cancelled");
|
|
149
|
+
if (config.provider === "openai") {
|
|
150
|
+
return {
|
|
151
|
+
counts: texts.map((text) => applyEmbeddingPrefix(text, prefix, config).length),
|
|
152
|
+
maximum: config.maxChars,
|
|
153
|
+
preferredMaximum: Math.max(1, Math.floor(config.maxChars * 0.875)),
|
|
154
|
+
unit: "characters",
|
|
155
|
+
};
|
|
156
|
+
}
|
|
157
|
+
beginRun();
|
|
158
|
+
try {
|
|
159
|
+
const measurement = await measureEmbeddingInputInModelWorker(texts, prefix, config.prefixes, signal);
|
|
160
|
+
return {
|
|
161
|
+
...measurement,
|
|
162
|
+
preferredMaximum: Math.max(1, Math.floor(measurement.maximum * 0.875)),
|
|
163
|
+
unit: "tokens",
|
|
164
|
+
};
|
|
165
|
+
}
|
|
166
|
+
finally {
|
|
167
|
+
endRun();
|
|
168
|
+
}
|
|
169
|
+
}
|
|
170
|
+
async function assertEmbeddingInputsWithinBudget(texts, prefix, config, signal) {
|
|
171
|
+
const measurement = await measureEmbeddingInputs(texts, prefix, config, signal);
|
|
172
|
+
for (let index = 0; index < measurement.counts.length; index++) {
|
|
173
|
+
const count = measurement.counts[index];
|
|
174
|
+
if (count !== undefined && count > measurement.maximum) {
|
|
175
|
+
throw new Error(`${config.provider} embedding ${prefix} input ${index + 1} is ${count} ${measurement.unit}; maximum is ${measurement.maximum}. Split the input before embedding.`);
|
|
176
|
+
}
|
|
177
|
+
}
|
|
178
|
+
}
|
|
144
179
|
async function embedViaAPI(texts, prefix, config, signal) {
|
|
145
|
-
const safeTexts = texts.map((text) =>
|
|
146
|
-
const embeddingText = applyEmbeddingPrefix(text, prefix, config);
|
|
147
|
-
return embeddingText.length > config.maxChars ? embeddingText.slice(0, config.maxChars) : embeddingText;
|
|
148
|
-
});
|
|
180
|
+
const safeTexts = texts.map((text) => applyEmbeddingPrefix(text, prefix, config));
|
|
149
181
|
const apiKey = cleanEnv(process.env.PI_KNOWLEDGE_EMBEDDING_API_KEY) ?? cleanEnv(process.env.OPENAI_API_KEY);
|
|
150
182
|
if (!config.baseUrl)
|
|
151
183
|
throw new Error("OpenAI embedding base URL is not configured");
|
|
@@ -169,7 +201,10 @@ async function embedViaAPI(texts, prefix, config, signal) {
|
|
|
169
201
|
export async function embedTextsWithConfig(texts, prefix, signal, options = {}) {
|
|
170
202
|
const config = resolveEmbeddingConfig();
|
|
171
203
|
let actualConfig = config;
|
|
204
|
+
let inputValidated = options.inputValidated === true;
|
|
172
205
|
if (config.provider === "openai") {
|
|
206
|
+
if (!inputValidated)
|
|
207
|
+
await assertEmbeddingInputsWithinBudget(texts, prefix, config, signal);
|
|
173
208
|
if (signal?.aborted)
|
|
174
209
|
throw new Error("Cancelled");
|
|
175
210
|
try {
|
|
@@ -182,8 +217,11 @@ export async function embedTextsWithConfig(texts, prefix, signal, options = {})
|
|
|
182
217
|
throw error;
|
|
183
218
|
console.warn(`pi-knowledge: embedding API failed; falling back to local model because PI_KNOWLEDGE_EMBEDDING_API_FALLBACK=local (${error instanceof Error ? error.message : String(error)})`);
|
|
184
219
|
actualConfig = localEmbeddingConfig(config.maxChars, config.prefixes);
|
|
220
|
+
inputValidated = false;
|
|
185
221
|
}
|
|
186
222
|
}
|
|
223
|
+
if (!inputValidated)
|
|
224
|
+
await assertEmbeddingInputsWithinBudget(texts, prefix, actualConfig, signal);
|
|
187
225
|
beginRun();
|
|
188
226
|
try {
|
|
189
227
|
return { vectors: await embedInModelWorker(texts, prefix, actualConfig.prefixes, signal), config: actualConfig };
|
|
@@ -205,3 +243,6 @@ export async function embedQuery(text, signal) {
|
|
|
205
243
|
export async function embedDocuments(texts, signal) {
|
|
206
244
|
return embedTexts(texts, "passage", signal, { allowApiFallback: false });
|
|
207
245
|
}
|
|
246
|
+
export async function embedValidatedDocuments(texts, signal) {
|
|
247
|
+
return embedTexts(texts, "passage", signal, { allowApiFallback: false, inputValidated: true });
|
|
248
|
+
}
|
package/dist/src/engine.d.ts
CHANGED
|
@@ -58,7 +58,7 @@ export interface DoctorIssue {
|
|
|
58
58
|
kb_name?: string;
|
|
59
59
|
message: string;
|
|
60
60
|
action: string;
|
|
61
|
-
action_code?: "run_update" | "rebuild_kb" | "wait_for_indexing" | "review_skipped_scope" | "rebuild_vectors" | "check_source" | "none";
|
|
61
|
+
action_code?: "run_update" | "rebuild_kb" | "wait_for_indexing" | "review_skipped_scope" | "rebuild_vectors" | "reindex_for_embedding_budget" | "check_source" | "none";
|
|
62
62
|
}
|
|
63
63
|
export interface DoctorReport {
|
|
64
64
|
health_score: number;
|
|
@@ -97,6 +97,8 @@ export interface SymbolSearchResponse {
|
|
|
97
97
|
total_count: number;
|
|
98
98
|
has_more: boolean;
|
|
99
99
|
}
|
|
100
|
+
export declare const CURRENT_URL_STRUCTURE_POLICY = 1;
|
|
101
|
+
export declare const CURRENT_EMBEDDING_INPUT_POLICY = 2;
|
|
100
102
|
export interface IndexPlan {
|
|
101
103
|
source_type: "file" | "directory" | "text" | "url";
|
|
102
104
|
scannable_files: number;
|
package/dist/src/engine.js
CHANGED
|
@@ -1,9 +1,11 @@
|
|
|
1
1
|
import { existsSync, readFileSync, renameSync, rmSync, statSync } from "node:fs";
|
|
2
2
|
import { join, resolve } from "node:path";
|
|
3
3
|
import { diagnoseKB } from "./diagnostics/health.js";
|
|
4
|
-
import { dispose as disposeEmbedding, embedDocuments, embeddingConfigLabel, embeddingSignature, embedQueryWithConfig, prepareForShutdown as prepareEmbeddingForShutdown, resolveEmbeddingConfig, } from "./embedding/provider.js";
|
|
4
|
+
import { dispose as disposeEmbedding, embedDocuments, embeddingConfigLabel, embeddingSignature, embedQueryWithConfig, embedValidatedDocuments, prepareForShutdown as prepareEmbeddingForShutdown, resolveEmbeddingConfig, } from "./embedding/provider.js";
|
|
5
5
|
import { openVectorReader, openVectorWriter } from "./embedding/vectors.js";
|
|
6
|
-
import { addSkippedScanEntry, analyzeIndexableContent, buildChunkEmbeddingText, chunkFile, chunkIdentityHash, createSkippedScanStats, isReadableTextFile, isSupportedDocumentFile, iterateScannableFiles, preTokenizeForFTS, summarizeSkippedScan, } from "./indexer/chunker.js";
|
|
6
|
+
import { addSkippedScanEntry, analyzeIndexableContent, buildChunkEmbeddingText, chunkFile, chunkIdentityHash, chunkMarkdown, createSkippedScanStats, isReadableTextFile, isSupportedDocumentFile, iterateScannableFiles, preTokenizeForFTS, summarizeSkippedScan, } from "./indexer/chunker.js";
|
|
7
|
+
import { finalizeChunksForEmbedding } from "./indexer/embedding-safe-chunks.js";
|
|
8
|
+
import { htmlToStructuredMarkdown } from "./indexer/html.js";
|
|
7
9
|
import { extractSymbols } from "./indexer/symbols.js";
|
|
8
10
|
import { shutdownModelWorker } from "./model-worker-client.js";
|
|
9
11
|
import { searchBM25 } from "./search/bm25.js";
|
|
@@ -13,8 +15,10 @@ import { hasAnyLexicalEvidence, hasEnoughLexicalEvidence, normalizeFileTypeFilte
|
|
|
13
15
|
import { disposeReranker, prepareRerankerForShutdown, rerank } from "./search/reranker.js";
|
|
14
16
|
import { resolveSearchTuning, summarizeSearchTuning, } from "./search/tuning.js";
|
|
15
17
|
import { searchVectorFile } from "./search/vector.js";
|
|
16
|
-
import { countSymbols, createKB, deleteChunksByIds, deleteKB, deleteSymbolsByKB, finishIndexingJob, getChunkById, getChunkCount, getChunksByFile, getFileCount, getKB, getKBByName, getSymbolCount, insertChunks, insertSymbols, iterateChunkIdsByKB, iterateChunksByKB, listKBs, openDatabase, searchSymbols, startIndexingJob, updateIndexingJob, updateKBCounts, updateKBEmbeddingMetadata, updateKBStatus, } from "./storage/sqlite.js";
|
|
18
|
+
import { countSymbols, createKB, deleteChunksByIds, deleteKB, deleteSymbolsByKB, finishIndexingJob, getChunkById, getChunkCount, getChunksByFile, getFileCount, getKB, getKBByName, getSymbolCount, insertChunks, insertSymbols, iterateChunkIdsByKB, iterateChunksByKB, listKBs, openDatabase, searchSymbols, startIndexingJob, updateIndexingJob, updateKBCounts, updateKBEmbeddingMetadata, updateKBSourceOptions, updateKBStatus, } from "./storage/sqlite.js";
|
|
17
19
|
export { CURRENT_EMBEDDING_MODEL } from "./embedding/provider.js";
|
|
20
|
+
export const CURRENT_URL_STRUCTURE_POLICY = 1;
|
|
21
|
+
export const CURRENT_EMBEDDING_INPUT_POLICY = 2;
|
|
18
22
|
const DEFAULT_INDEX_EMBED_BATCH_SIZE = 64;
|
|
19
23
|
const VECTOR_REDUNDANCY_WEIGHT = 0.35;
|
|
20
24
|
function resolveIndexEmbedBatchSize(env = process.env) {
|
|
@@ -66,14 +70,17 @@ function toScanOptions(options = {}) {
|
|
|
66
70
|
};
|
|
67
71
|
}
|
|
68
72
|
function serializeAddOptions(options = {}) {
|
|
69
|
-
const normalized = {
|
|
73
|
+
const normalized = {
|
|
74
|
+
embedding_input_policy: CURRENT_EMBEDDING_INPUT_POLICY,
|
|
75
|
+
url_structure_policy: CURRENT_URL_STRUCTURE_POLICY,
|
|
76
|
+
};
|
|
70
77
|
if (options.include_suggested_text === true)
|
|
71
78
|
normalized.include_suggested_text = true;
|
|
72
79
|
if (options.include_paths && options.include_paths.length > 0)
|
|
73
80
|
normalized.include_paths = options.include_paths;
|
|
74
81
|
if (options.exclude_paths && options.exclude_paths.length > 0)
|
|
75
82
|
normalized.exclude_paths = options.exclude_paths;
|
|
76
|
-
return
|
|
83
|
+
return JSON.stringify(normalized);
|
|
77
84
|
}
|
|
78
85
|
function parseAddOptions(raw) {
|
|
79
86
|
if (!raw)
|
|
@@ -94,6 +101,18 @@ function parseAddOptions(raw) {
|
|
|
94
101
|
return {};
|
|
95
102
|
}
|
|
96
103
|
}
|
|
104
|
+
function storedSourcePolicyVersion(raw, key) {
|
|
105
|
+
if (!raw)
|
|
106
|
+
return undefined;
|
|
107
|
+
try {
|
|
108
|
+
const parsed = JSON.parse(raw);
|
|
109
|
+
const version = parsed[key];
|
|
110
|
+
return typeof version === "number" && Number.isInteger(version) ? version : undefined;
|
|
111
|
+
}
|
|
112
|
+
catch {
|
|
113
|
+
return undefined;
|
|
114
|
+
}
|
|
115
|
+
}
|
|
97
116
|
function planDirectoryScan(dirPath, options = {}, signal) {
|
|
98
117
|
const skipped = createSkippedScanStats();
|
|
99
118
|
let files = 0;
|
|
@@ -452,14 +471,10 @@ async function chunkUrl(source, signal) {
|
|
|
452
471
|
if (!res.ok)
|
|
453
472
|
throw new Error(`Fetch failed: ${res.status}`);
|
|
454
473
|
const html = await res.text();
|
|
455
|
-
|
|
456
|
-
|
|
457
|
-
|
|
458
|
-
|
|
459
|
-
.replace(/&[a-z]+;/gi, " ")
|
|
460
|
-
.replace(/\s+/g, " ")
|
|
461
|
-
.trim();
|
|
462
|
-
return chunkFile(text, source);
|
|
474
|
+
throwIfAborted(signal);
|
|
475
|
+
const text = htmlToStructuredMarkdown(html);
|
|
476
|
+
const structuredChunks = chunkMarkdown(text, source, "html");
|
|
477
|
+
return structuredChunks.length > 0 ? structuredChunks : chunkFile(text, source);
|
|
463
478
|
}
|
|
464
479
|
function normalizeExtractedText(text) {
|
|
465
480
|
return Array.isArray(text) ? text.join("\n\n") : text;
|
|
@@ -772,7 +787,7 @@ export class KnowledgeEngine {
|
|
|
772
787
|
throw new Error("Cancelled");
|
|
773
788
|
const batch = pendingChunks.splice(0, embeddingBatchSize);
|
|
774
789
|
reportProgress(`Embedding batch of ${batch.length}`, processedFiles, totalFiles);
|
|
775
|
-
const vectors = await
|
|
790
|
+
const vectors = await embedValidatedDocuments(batch.map((chunk) => buildChunkEmbeddingText(chunk)), signal);
|
|
776
791
|
if (signal?.aborted)
|
|
777
792
|
throw new Error("Cancelled");
|
|
778
793
|
assertEmbeddingBatchSize(vectors, batch.length, "add");
|
|
@@ -784,7 +799,8 @@ export class KnowledgeEngine {
|
|
|
784
799
|
reportProgress("Stored batch", processedFiles, totalFiles);
|
|
785
800
|
};
|
|
786
801
|
const addChunks = async (chunks, processedFiles, totalFiles) => {
|
|
787
|
-
|
|
802
|
+
const finalizedChunks = await finalizeChunksForEmbedding(chunks, embeddingConfig, signal);
|
|
803
|
+
pendingChunks.push(...finalizedChunks);
|
|
788
804
|
while (pendingChunks.length >= embeddingBatchSize) {
|
|
789
805
|
await flushPending(processedFiles, totalFiles);
|
|
790
806
|
}
|
|
@@ -1016,7 +1032,7 @@ export class KnowledgeEngine {
|
|
|
1016
1032
|
unchanged_chunks: unchanged,
|
|
1017
1033
|
});
|
|
1018
1034
|
onProgress?.(message);
|
|
1019
|
-
const newVectors = await
|
|
1035
|
+
const newVectors = await embedValidatedDocuments(batch.map((c) => buildChunkEmbeddingText(c)), signal);
|
|
1020
1036
|
if (signal?.aborted)
|
|
1021
1037
|
throw new Error("Cancelled");
|
|
1022
1038
|
assertEmbeddingBatchSize(newVectors, batch.length, "update");
|
|
@@ -1043,7 +1059,8 @@ export class KnowledgeEngine {
|
|
|
1043
1059
|
onProgress?.(storedMessage);
|
|
1044
1060
|
};
|
|
1045
1061
|
const processChunks = async (chunks) => {
|
|
1046
|
-
|
|
1062
|
+
const finalizedChunks = await finalizeChunksForEmbedding(chunks, embeddingConfig, signal);
|
|
1063
|
+
for (const chunk of finalizedChunks) {
|
|
1047
1064
|
scannedChunks++;
|
|
1048
1065
|
const existing = reusableHashes.get(chunk.content_hash);
|
|
1049
1066
|
if (existing && existing.length > 0) {
|
|
@@ -1231,6 +1248,7 @@ export class KnowledgeEngine {
|
|
|
1231
1248
|
insertSymbols(this.db, kb.id, stagedSymbols);
|
|
1232
1249
|
updateKBEmbeddingMetadata(this.db, kb.id, embeddingModel, finalEmbeddingDimension === undefined ? null : embeddingSignature(embeddingConfig, finalEmbeddingDimension), finalEmbeddingDimension ?? null);
|
|
1233
1250
|
updateKBCounts(this.db, kb.id, finalChunkCount, getFileCount(this.db, kb.id));
|
|
1251
|
+
updateKBSourceOptions(this.db, kb.id, serializeAddOptions(parseAddOptions(kb.source_options)));
|
|
1234
1252
|
updateKBStatus(this.db, kb.id, "ready");
|
|
1235
1253
|
const skippedReadySuffix = latestSkippedTotal > 0 ? `, skipped ${latestSkippedTotal} (${latestSkippedSummary})` : "";
|
|
1236
1254
|
const readyMessage = `Ready: +${addedCount} -${idsToRemove.length} =${unchanged}${skippedReadySuffix}`;
|
|
@@ -1752,6 +1770,30 @@ export class KnowledgeEngine {
|
|
|
1752
1770
|
if (this.db) {
|
|
1753
1771
|
for (const kb of kbs) {
|
|
1754
1772
|
throwIfAborted(signal);
|
|
1773
|
+
if ((kb.status === "ready" || kb.status === "stale") &&
|
|
1774
|
+
(storedSourcePolicyVersion(kb.source_options, "embedding_input_policy") ?? 0) < CURRENT_EMBEDDING_INPUT_POLICY) {
|
|
1775
|
+
const canUpdate = kb.source_path !== null && kb.source_type !== "text";
|
|
1776
|
+
issues.push({
|
|
1777
|
+
severity: "warning",
|
|
1778
|
+
kb_name: kb.name,
|
|
1779
|
+
message: "This KB predates embedding-safe chunk limits, so oversized chunk tails may be missing from vector retrieval.",
|
|
1780
|
+
action: canUpdate
|
|
1781
|
+
? "Run knowledge_update to re-chunk oversized inputs with the current embedding budget."
|
|
1782
|
+
: "Re-add inline text or re-import the original source to rebuild chunks with the current embedding budget.",
|
|
1783
|
+
action_code: "reindex_for_embedding_budget",
|
|
1784
|
+
});
|
|
1785
|
+
}
|
|
1786
|
+
if (kb.source_type === "url" &&
|
|
1787
|
+
(kb.status === "ready" || kb.status === "stale") &&
|
|
1788
|
+
(storedSourcePolicyVersion(kb.source_options, "url_structure_policy") ?? 0) < CURRENT_URL_STRUCTURE_POLICY) {
|
|
1789
|
+
issues.push({
|
|
1790
|
+
severity: "warning",
|
|
1791
|
+
kb_name: kb.name,
|
|
1792
|
+
message: "This URL KB predates structure-preserving HTML normalization.",
|
|
1793
|
+
action: "Run knowledge_update to rebuild URL headings, sections, lists, tables, and entities.",
|
|
1794
|
+
action_code: "run_update",
|
|
1795
|
+
});
|
|
1796
|
+
}
|
|
1755
1797
|
if (kb.status === "ready" && kb.chunk_count > 0 && getSymbolCount(this.db, kb.id) === 0) {
|
|
1756
1798
|
issues.push({
|
|
1757
1799
|
severity: "info",
|
|
@@ -1879,7 +1921,7 @@ export class KnowledgeEngine {
|
|
|
1879
1921
|
added_chunks: inserted,
|
|
1880
1922
|
});
|
|
1881
1923
|
onProgress?.(message);
|
|
1882
|
-
const vectors = await
|
|
1924
|
+
const vectors = await embedValidatedDocuments(batch.map((chunk) => buildChunkEmbeddingText(chunk)), signal);
|
|
1883
1925
|
throwIfAborted(signal);
|
|
1884
1926
|
assertEmbeddingBatchSize(vectors, batch.length, "import");
|
|
1885
1927
|
persistEmbeddingMetadata(this.db, kb.id, embeddingConfig, vectors);
|
|
@@ -1915,6 +1957,7 @@ export class KnowledgeEngine {
|
|
|
1915
1957
|
name: header.name,
|
|
1916
1958
|
description: header.description,
|
|
1917
1959
|
source_type: "text",
|
|
1960
|
+
source_options: serializeAddOptions(),
|
|
1918
1961
|
embedding_model: embeddingConfigLabel(embeddingConfig),
|
|
1919
1962
|
});
|
|
1920
1963
|
updateKBStatus(this.db, kb.id, "indexing");
|
|
@@ -1934,9 +1977,10 @@ export class KnowledgeEngine {
|
|
|
1934
1977
|
const imported = JSON.parse(line);
|
|
1935
1978
|
const chunk = importedChunkToInsert(imported);
|
|
1936
1979
|
chunk.content_tokenized = preTokenizeForFTS(buildChunkEmbeddingText(chunk));
|
|
1937
|
-
|
|
1980
|
+
const finalizedChunks = await finalizeChunksForEmbedding([chunk], embeddingConfig, signal);
|
|
1981
|
+
pendingChunks.push(...finalizedChunks);
|
|
1938
1982
|
pendingSymbols.push(...extractSymbols(imported.content, imported.file_path, imported.file_type));
|
|
1939
|
-
|
|
1983
|
+
while (pendingChunks.length >= embeddingBatchSize)
|
|
1940
1984
|
await flushPending();
|
|
1941
1985
|
}
|
|
1942
1986
|
if (!header)
|
|
@@ -50,7 +50,7 @@ export declare function chunkIdentityHash(opts: {
|
|
|
50
50
|
metadataJson: string;
|
|
51
51
|
}): string;
|
|
52
52
|
export declare function buildChunkEmbeddingText(chunk: Pick<ChunkInsert, "content" | "file_path" | "file_type" | "metadata_json">): string;
|
|
53
|
-
export declare function chunkMarkdown(content: string, filePath: string): Omit<ChunkInsert, "kb_id">[];
|
|
53
|
+
export declare function chunkMarkdown(content: string, filePath: string, fileType?: string): Omit<ChunkInsert, "kb_id">[];
|
|
54
54
|
export declare function chunkText(content: string, filePath: string): Omit<ChunkInsert, "kb_id">[];
|
|
55
55
|
export declare function isCodeFileType(fileType: string): boolean;
|
|
56
56
|
export declare function analyzeIndexableContent(content: string, filePath: string, fileType?: string): Promise<{
|
|
@@ -397,7 +397,7 @@ function makeChunk(content, filePath, fileType, startLine, endLine, metadata = {
|
|
|
397
397
|
};
|
|
398
398
|
return { ...chunk, content_tokenized: preTokenizeForFTS(buildChunkEmbeddingText(chunk)) };
|
|
399
399
|
}
|
|
400
|
-
export function chunkMarkdown(content, filePath) {
|
|
400
|
+
export function chunkMarkdown(content, filePath, fileType = "markdown") {
|
|
401
401
|
const lines = content.split("\n");
|
|
402
402
|
const chunks = [];
|
|
403
403
|
const headingStack = [];
|
|
@@ -410,7 +410,7 @@ export function chunkMarkdown(content, filePath) {
|
|
|
410
410
|
function pushMarkdownChunk(text, start, end) {
|
|
411
411
|
if (text.trim().length < 50)
|
|
412
412
|
return;
|
|
413
|
-
chunks.push(makeChunk(text.trim(), filePath,
|
|
413
|
+
chunks.push(makeChunk(text.trim(), filePath, fileType, start, end, {
|
|
414
414
|
heading: currentHeading,
|
|
415
415
|
breadcrumb: currentBreadcrumb(),
|
|
416
416
|
}));
|
|
@@ -0,0 +1,5 @@
|
|
|
1
|
+
import type { EmbeddingConfig } from "../embedding/provider.ts";
|
|
2
|
+
import type { ChunkInsert } from "../storage/sqlite.ts";
|
|
3
|
+
type IndexableChunk = Omit<ChunkInsert, "kb_id">;
|
|
4
|
+
export declare function finalizeChunksForEmbedding(chunks: IndexableChunk[], config: EmbeddingConfig, signal?: AbortSignal): Promise<IndexableChunk[]>;
|
|
5
|
+
export {};
|
|
@@ -0,0 +1,215 @@
|
|
|
1
|
+
import { LOCAL_EMBEDDING_PREFERRED_TOKENS, measureEmbeddingInputs } from "../embedding/provider.js";
|
|
2
|
+
import { buildChunkEmbeddingText, chunkIdentityHash, preTokenizeForFTS } from "./chunker.js";
|
|
3
|
+
const SENTENCE_BOUNDARIES = {
|
|
4
|
+
"。": true,
|
|
5
|
+
"!": true,
|
|
6
|
+
"?": true,
|
|
7
|
+
".": true,
|
|
8
|
+
"!": true,
|
|
9
|
+
"?": true,
|
|
10
|
+
";": true,
|
|
11
|
+
";": true,
|
|
12
|
+
};
|
|
13
|
+
function throwIfAborted(signal) {
|
|
14
|
+
if (signal?.aborted)
|
|
15
|
+
throw new Error("Cancelled");
|
|
16
|
+
}
|
|
17
|
+
function compareOrder(left, right) {
|
|
18
|
+
if (left.rootIndex !== right.rootIndex)
|
|
19
|
+
return left.rootIndex - right.rootIndex;
|
|
20
|
+
const length = Math.min(left.order.length, right.order.length);
|
|
21
|
+
for (let index = 0; index < length; index++) {
|
|
22
|
+
if (left.order[index] !== right.order[index])
|
|
23
|
+
return left.order[index] - right.order[index];
|
|
24
|
+
}
|
|
25
|
+
return left.order.length - right.order.length;
|
|
26
|
+
}
|
|
27
|
+
function nearestStringBoundary(content, desired, boundary, minimum) {
|
|
28
|
+
const before = content.lastIndexOf(boundary, desired);
|
|
29
|
+
if (before >= minimum)
|
|
30
|
+
return before + boundary.length;
|
|
31
|
+
const after = content.indexOf(boundary, desired);
|
|
32
|
+
if (after >= 0 && after <= content.length - minimum)
|
|
33
|
+
return after + boundary.length;
|
|
34
|
+
return undefined;
|
|
35
|
+
}
|
|
36
|
+
function nearestCharacterBoundary(content, desired, minimum, predicate) {
|
|
37
|
+
for (let offset = 0; offset < content.length; offset++) {
|
|
38
|
+
const before = desired - offset;
|
|
39
|
+
if (before >= minimum && predicate(content[before]))
|
|
40
|
+
return before + 1;
|
|
41
|
+
const after = desired + offset;
|
|
42
|
+
if (after < content.length - minimum && predicate(content[after]))
|
|
43
|
+
return after + 1;
|
|
44
|
+
if (before < minimum && after >= content.length - minimum)
|
|
45
|
+
break;
|
|
46
|
+
}
|
|
47
|
+
return undefined;
|
|
48
|
+
}
|
|
49
|
+
function safeCodeUnitBoundary(content, index) {
|
|
50
|
+
if (index <= 0 || index >= content.length)
|
|
51
|
+
return index;
|
|
52
|
+
const previous = content.charCodeAt(index - 1);
|
|
53
|
+
const next = content.charCodeAt(index);
|
|
54
|
+
return previous >= 0xd800 && previous <= 0xdbff && next >= 0xdc00 && next <= 0xdfff ? index - 1 : index;
|
|
55
|
+
}
|
|
56
|
+
function chooseSplitIndex(content, units, measurement) {
|
|
57
|
+
const estimatedParts = Math.max(2, Math.ceil(units / measurement.preferredMaximum));
|
|
58
|
+
const desired = Math.max(1, Math.floor(content.length / estimatedParts));
|
|
59
|
+
const minimum = Math.max(1, Math.min(64, Math.floor(content.length * 0.1)));
|
|
60
|
+
const structuralBoundary = nearestStringBoundary(content, desired, "\n\n", minimum) ??
|
|
61
|
+
nearestStringBoundary(content, desired, "\n", minimum) ??
|
|
62
|
+
nearestCharacterBoundary(content, desired, minimum, (character) => SENTENCE_BOUNDARIES[character] === true) ??
|
|
63
|
+
nearestCharacterBoundary(content, desired, minimum, (character) => /\s/u.test(character));
|
|
64
|
+
const splitIndex = safeCodeUnitBoundary(content, structuralBoundary ?? desired);
|
|
65
|
+
if (splitIndex <= 0 || splitIndex >= content.length) {
|
|
66
|
+
throw new Error(`Unable to split oversized embedding input containing ${content.length} characters`);
|
|
67
|
+
}
|
|
68
|
+
return splitIndex;
|
|
69
|
+
}
|
|
70
|
+
function lineCount(content) {
|
|
71
|
+
let count = 0;
|
|
72
|
+
for (const character of content) {
|
|
73
|
+
if (character === "\n")
|
|
74
|
+
count++;
|
|
75
|
+
}
|
|
76
|
+
return count;
|
|
77
|
+
}
|
|
78
|
+
function rebuildChunk(chunk, content, startLine, endLine) {
|
|
79
|
+
const rebuilt = {
|
|
80
|
+
...chunk,
|
|
81
|
+
content,
|
|
82
|
+
content_hash: chunkIdentityHash({
|
|
83
|
+
content,
|
|
84
|
+
filePath: chunk.file_path,
|
|
85
|
+
fileType: chunk.file_type,
|
|
86
|
+
startLine,
|
|
87
|
+
endLine,
|
|
88
|
+
metadataJson: chunk.metadata_json,
|
|
89
|
+
}),
|
|
90
|
+
content_tokenized: "",
|
|
91
|
+
start_line: startLine,
|
|
92
|
+
end_line: endLine,
|
|
93
|
+
};
|
|
94
|
+
return { ...rebuilt, content_tokenized: preTokenizeForFTS(buildChunkEmbeddingText(rebuilt)) };
|
|
95
|
+
}
|
|
96
|
+
function unsplittableEmbeddingContext(piece, measurement) {
|
|
97
|
+
return new Error(`Embedding context for ${piece.chunk.file_path}:${piece.chunk.start_line}-${piece.chunk.end_line} exceeds ${measurement.maximum} ${measurement.unit} and cannot be split safely`);
|
|
98
|
+
}
|
|
99
|
+
function splitPiece(piece, units, measurement) {
|
|
100
|
+
const content = piece.chunk.content;
|
|
101
|
+
if ([...content].length < 2)
|
|
102
|
+
throw unsplittableEmbeddingContext(piece, measurement);
|
|
103
|
+
const splitIndex = chooseSplitIndex(content, units, measurement);
|
|
104
|
+
const leftRaw = content.slice(0, splitIndex);
|
|
105
|
+
const rightRaw = content.slice(splitIndex);
|
|
106
|
+
const left = leftRaw.trim();
|
|
107
|
+
const right = rightRaw.trim();
|
|
108
|
+
if (!left || !right || left === content || right === content) {
|
|
109
|
+
throw unsplittableEmbeddingContext(piece, measurement);
|
|
110
|
+
}
|
|
111
|
+
const leftLeadingLines = lineCount(leftRaw.slice(0, leftRaw.indexOf(left)));
|
|
112
|
+
const rightLeadingLines = lineCount(rightRaw.slice(0, rightRaw.indexOf(right)));
|
|
113
|
+
const leftStart = piece.chunk.start_line + leftLeadingLines;
|
|
114
|
+
const leftEnd = leftStart + lineCount(left);
|
|
115
|
+
const rightStart = piece.chunk.start_line + lineCount(leftRaw) + rightLeadingLines;
|
|
116
|
+
const rightEnd = rightStart + lineCount(right);
|
|
117
|
+
return [
|
|
118
|
+
{
|
|
119
|
+
chunk: rebuildChunk(piece.chunk, left, leftStart, leftEnd),
|
|
120
|
+
rootIndex: piece.rootIndex,
|
|
121
|
+
order: [...piece.order, 0],
|
|
122
|
+
},
|
|
123
|
+
{
|
|
124
|
+
chunk: rebuildChunk(piece.chunk, right, rightStart, rightEnd),
|
|
125
|
+
rootIndex: piece.rootIndex,
|
|
126
|
+
order: [...piece.order, 1],
|
|
127
|
+
},
|
|
128
|
+
];
|
|
129
|
+
}
|
|
130
|
+
function withPartMetadata(chunk, part, partCount) {
|
|
131
|
+
let metadata = {};
|
|
132
|
+
try {
|
|
133
|
+
const parsed = JSON.parse(chunk.metadata_json);
|
|
134
|
+
if (parsed && typeof parsed === "object" && !Array.isArray(parsed))
|
|
135
|
+
metadata = parsed;
|
|
136
|
+
}
|
|
137
|
+
catch {
|
|
138
|
+
metadata = {};
|
|
139
|
+
}
|
|
140
|
+
const metadataJson = JSON.stringify({ ...metadata, chunk_part: part, chunk_part_count: partCount });
|
|
141
|
+
const rebuilt = { ...chunk, metadata_json: metadataJson, content_tokenized: "" };
|
|
142
|
+
rebuilt.content_hash = chunkIdentityHash({
|
|
143
|
+
content: rebuilt.content,
|
|
144
|
+
filePath: rebuilt.file_path,
|
|
145
|
+
fileType: rebuilt.file_type,
|
|
146
|
+
startLine: rebuilt.start_line,
|
|
147
|
+
endLine: rebuilt.end_line,
|
|
148
|
+
metadataJson,
|
|
149
|
+
});
|
|
150
|
+
rebuilt.content_tokenized = preTokenizeForFTS(buildChunkEmbeddingText(rebuilt));
|
|
151
|
+
return rebuilt;
|
|
152
|
+
}
|
|
153
|
+
function isProvablySafeLocalAsciiInput(text, config) {
|
|
154
|
+
if (config.provider !== "local")
|
|
155
|
+
return false;
|
|
156
|
+
const prefixLength = config.prefixes === "on" ? "passage: ".length : 0;
|
|
157
|
+
if (text.length + prefixLength + 2 > LOCAL_EMBEDDING_PREFERRED_TOKENS)
|
|
158
|
+
return false;
|
|
159
|
+
for (let index = 0; index < text.length; index++) {
|
|
160
|
+
if (text.charCodeAt(index) > 0x7f)
|
|
161
|
+
return false;
|
|
162
|
+
}
|
|
163
|
+
return true;
|
|
164
|
+
}
|
|
165
|
+
export async function finalizeChunksForEmbedding(chunks, config, signal) {
|
|
166
|
+
if (chunks.length === 0)
|
|
167
|
+
return [];
|
|
168
|
+
let pending = chunks.map((chunk, rootIndex) => ({ chunk, rootIndex, order: [] }));
|
|
169
|
+
const accepted = [];
|
|
170
|
+
while (pending.length > 0) {
|
|
171
|
+
throwIfAborted(signal);
|
|
172
|
+
const piecesToMeasure = [];
|
|
173
|
+
const textsToMeasure = [];
|
|
174
|
+
for (const piece of pending) {
|
|
175
|
+
const text = buildChunkEmbeddingText(piece.chunk);
|
|
176
|
+
if (isProvablySafeLocalAsciiInput(text, config))
|
|
177
|
+
accepted.push(piece);
|
|
178
|
+
else {
|
|
179
|
+
piecesToMeasure.push(piece);
|
|
180
|
+
textsToMeasure.push(text);
|
|
181
|
+
}
|
|
182
|
+
}
|
|
183
|
+
if (piecesToMeasure.length === 0)
|
|
184
|
+
break;
|
|
185
|
+
const measurement = await measureEmbeddingInputs(textsToMeasure, "passage", config, signal);
|
|
186
|
+
if (measurement.counts.length !== piecesToMeasure.length) {
|
|
187
|
+
throw new Error(`Embedding input measurement returned ${measurement.counts.length} counts for ${piecesToMeasure.length} chunks`);
|
|
188
|
+
}
|
|
189
|
+
const next = [];
|
|
190
|
+
for (let index = 0; index < piecesToMeasure.length; index++) {
|
|
191
|
+
const piece = piecesToMeasure[index];
|
|
192
|
+
const units = measurement.counts[index];
|
|
193
|
+
if (units === undefined)
|
|
194
|
+
throw new Error(`Missing embedding input measurement for chunk ${index}`);
|
|
195
|
+
if (units <= measurement.maximum)
|
|
196
|
+
accepted.push(piece);
|
|
197
|
+
else
|
|
198
|
+
next.push(...splitPiece(piece, units, measurement));
|
|
199
|
+
}
|
|
200
|
+
pending = next;
|
|
201
|
+
}
|
|
202
|
+
accepted.sort(compareOrder);
|
|
203
|
+
const partCounts = new Map();
|
|
204
|
+
for (const piece of accepted)
|
|
205
|
+
partCounts.set(piece.rootIndex, (partCounts.get(piece.rootIndex) ?? 0) + 1);
|
|
206
|
+
const partIndexes = new Map();
|
|
207
|
+
return accepted.map((piece) => {
|
|
208
|
+
const partCount = partCounts.get(piece.rootIndex) ?? 1;
|
|
209
|
+
if (partCount === 1)
|
|
210
|
+
return piece.chunk;
|
|
211
|
+
const part = (partIndexes.get(piece.rootIndex) ?? 0) + 1;
|
|
212
|
+
partIndexes.set(piece.rootIndex, part);
|
|
213
|
+
return withPartMetadata(piece.chunk, part, partCount);
|
|
214
|
+
});
|
|
215
|
+
}
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
export declare function htmlToStructuredMarkdown(html: string): string;
|
|
@@ -0,0 +1,49 @@
|
|
|
1
|
+
const HTML_ENTITIES = {
|
|
2
|
+
amp: "&",
|
|
3
|
+
apos: "'",
|
|
4
|
+
gt: ">",
|
|
5
|
+
lt: "<",
|
|
6
|
+
nbsp: " ",
|
|
7
|
+
quot: '"',
|
|
8
|
+
ndash: "–",
|
|
9
|
+
mdash: "—",
|
|
10
|
+
hellip: "…",
|
|
11
|
+
};
|
|
12
|
+
function decodeHtmlEntity(entity) {
|
|
13
|
+
if (!entity.startsWith("#"))
|
|
14
|
+
return HTML_ENTITIES[entity.toLowerCase()] ?? `&${entity};`;
|
|
15
|
+
const hexadecimal = entity[1]?.toLowerCase() === "x";
|
|
16
|
+
const digits = entity.slice(hexadecimal ? 2 : 1);
|
|
17
|
+
const codePoint = Number.parseInt(digits, hexadecimal ? 16 : 10);
|
|
18
|
+
if (!digits ||
|
|
19
|
+
!Number.isInteger(codePoint) ||
|
|
20
|
+
codePoint <= 0 ||
|
|
21
|
+
codePoint > 0x10ffff ||
|
|
22
|
+
(codePoint >= 0xd800 && codePoint <= 0xdfff)) {
|
|
23
|
+
return `&${entity};`;
|
|
24
|
+
}
|
|
25
|
+
return String.fromCodePoint(codePoint);
|
|
26
|
+
}
|
|
27
|
+
export function htmlToStructuredMarkdown(html) {
|
|
28
|
+
return html
|
|
29
|
+
.replace(/<!--[\s\S]*?-->/g, "")
|
|
30
|
+
.replace(/<(script|style|noscript|template|svg)\b[^>]*>[\s\S]*?(?:<\/\1\s*>|$)/gi, "")
|
|
31
|
+
.replace(/<h([1-6])\b[^>]*>/gi, (_tag, level) => `\n\n${"#".repeat(Number(level))} `)
|
|
32
|
+
.replace(/<\/h[1-6]\s*>/gi, "\n\n")
|
|
33
|
+
.replace(/<li\b[^>]*>/gi, "\n- ")
|
|
34
|
+
.replace(/<\/li\s*>/gi, "\n")
|
|
35
|
+
.replace(/<br\s*\/?\s*>/gi, "\n")
|
|
36
|
+
.replace(/<(th|td)\b[^>]*>/gi, " | ")
|
|
37
|
+
.replace(/<\/(th|td)\s*>/gi, "")
|
|
38
|
+
.replace(/<tr\b[^>]*>/gi, "\n")
|
|
39
|
+
.replace(/<\/tr\s*>/gi, "\n")
|
|
40
|
+
.replace(/<\/?(?:address|article|aside|blockquote|div|dl|dt|dd|fieldset|figcaption|figure|footer|form|header|hr|main|nav|ol|p|section|table|tbody|thead|tfoot|ul)\b[^>]*>/gi, "\n\n")
|
|
41
|
+
.replace(/<[^>]+>/g, "")
|
|
42
|
+
.replace(/&(#(?:x[0-9a-f]+|\d+)|[a-z][a-z0-9]+);/gi, (_match, entity) => decodeHtmlEntity(entity))
|
|
43
|
+
.replace(/\r\n?/g, "\n")
|
|
44
|
+
.split("\n")
|
|
45
|
+
.map((line) => line.replace(/[\t\f\v ]+/g, " ").trim())
|
|
46
|
+
.join("\n")
|
|
47
|
+
.replace(/\n{3,}/g, "\n\n")
|
|
48
|
+
.trim();
|
|
49
|
+
}
|
|
@@ -3,6 +3,10 @@ export declare function validateModelWorkerNodePath(nodePath: string): string;
|
|
|
3
3
|
export declare function resolveModelWorkerNodePath(): string;
|
|
4
4
|
export declare function configureModelWorkerNodePath(nodePath?: string): string;
|
|
5
5
|
export declare function embedInModelWorker(texts: string[], prefix: "query" | "passage", prefixesOrSignal?: "on" | "off" | AbortSignal, signal?: AbortSignal): Promise<Float32Array[]>;
|
|
6
|
+
export declare function measureEmbeddingInputInModelWorker(texts: string[], prefix: "query" | "passage", prefixes: "on" | "off", signal?: AbortSignal): Promise<{
|
|
7
|
+
counts: number[];
|
|
8
|
+
maximum: number;
|
|
9
|
+
}>;
|
|
6
10
|
export interface RerankWorkerCandidate {
|
|
7
11
|
chunkId: string;
|
|
8
12
|
content: string;
|
|
@@ -187,8 +187,8 @@ function isWorkerResponse(message) {
|
|
|
187
187
|
return !("error" in message) || message.error === undefined || typeof message.error === "string";
|
|
188
188
|
}
|
|
189
189
|
class ModelWorkerTransport {
|
|
190
|
-
child;
|
|
191
190
|
pending = new Map();
|
|
191
|
+
child;
|
|
192
192
|
stderrTail = "";
|
|
193
193
|
exited = false;
|
|
194
194
|
terminalError = null;
|
|
@@ -397,6 +397,22 @@ export async function embedInModelWorker(texts, prefix, prefixesOrSignal, signal
|
|
|
397
397
|
return new Float32Array(vector);
|
|
398
398
|
});
|
|
399
399
|
}
|
|
400
|
+
export async function measureEmbeddingInputInModelWorker(texts, prefix, prefixes, signal) {
|
|
401
|
+
const result = await getWorker().request({ type: "measure_embedding_input", texts, prefix, prefixes }, signal);
|
|
402
|
+
if (typeof result !== "object" ||
|
|
403
|
+
result === null ||
|
|
404
|
+
!("counts" in result) ||
|
|
405
|
+
!Array.isArray(result.counts) ||
|
|
406
|
+
result.counts.length !== texts.length ||
|
|
407
|
+
!result.counts.every((count) => typeof count === "number" && Number.isInteger(count) && count >= 0) ||
|
|
408
|
+
!("maximum" in result) ||
|
|
409
|
+
typeof result.maximum !== "number" ||
|
|
410
|
+
!Number.isInteger(result.maximum) ||
|
|
411
|
+
result.maximum <= 0) {
|
|
412
|
+
throw new Error("Invalid embedding input measurement from worker");
|
|
413
|
+
}
|
|
414
|
+
return { counts: result.counts, maximum: result.maximum };
|
|
415
|
+
}
|
|
400
416
|
export async function rerankInModelWorker(query, candidates, topK, reranker, signal) {
|
|
401
417
|
const result = await getWorker().request({ type: "rerank", query, candidates, topK, reranker }, signal);
|
|
402
418
|
if (!Array.isArray(result))
|
package/dist/src/model-worker.js
CHANGED
|
@@ -4,6 +4,7 @@ import { DEFAULT_RERANKER_REMOTE_HOST, DEFAULT_RERANKER_REMOTE_PATH_TEMPLATE, is
|
|
|
4
4
|
import { rerankWithSingleRawLogit } from "./search/reranker-logits.js";
|
|
5
5
|
import { getDefaultKnowledgeDir } from "./storage/sqlite.js";
|
|
6
6
|
let embeddingPipeline = null;
|
|
7
|
+
let embeddingPipelinePromise = null;
|
|
7
8
|
let rerankerPipeline = null;
|
|
8
9
|
function getModelCacheDir() {
|
|
9
10
|
return process.env.PI_KNOWLEDGE_MODEL_CACHE_DIR ?? join(getDefaultKnowledgeDir(), "models");
|
|
@@ -24,15 +25,24 @@ function configureEmbeddingTransformersEnv(env) {
|
|
|
24
25
|
async function loadEmbeddingPipeline() {
|
|
25
26
|
if (embeddingPipeline)
|
|
26
27
|
return embeddingPipeline;
|
|
27
|
-
|
|
28
|
-
|
|
29
|
-
|
|
30
|
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
28
|
+
if (embeddingPipelinePromise)
|
|
29
|
+
return embeddingPipelinePromise;
|
|
30
|
+
embeddingPipelinePromise = (async () => {
|
|
31
|
+
const { pipeline, env } = await import("@huggingface/transformers");
|
|
32
|
+
configureEmbeddingTransformersEnv(env);
|
|
33
|
+
const createPipeline = pipeline;
|
|
34
|
+
return (await createPipeline("feature-extraction", "Xenova/multilingual-e5-small", {
|
|
35
|
+
quantized: true,
|
|
36
|
+
dtype: "fp32",
|
|
37
|
+
}));
|
|
38
|
+
})();
|
|
39
|
+
try {
|
|
40
|
+
embeddingPipeline = await embeddingPipelinePromise;
|
|
41
|
+
return embeddingPipeline;
|
|
42
|
+
}
|
|
43
|
+
finally {
|
|
44
|
+
embeddingPipelinePromise = null;
|
|
45
|
+
}
|
|
36
46
|
}
|
|
37
47
|
async function loadRerankerPipeline(config) {
|
|
38
48
|
const key = rerankerCacheKey(config);
|
|
@@ -81,6 +91,34 @@ async function handleEmbed(request) {
|
|
|
81
91
|
}
|
|
82
92
|
return vectors;
|
|
83
93
|
}
|
|
94
|
+
function embeddingMaximumTokens(tokenizer) {
|
|
95
|
+
const configured = tokenizer.model_max_length;
|
|
96
|
+
return typeof configured === "number" && Number.isInteger(configured) && configured > 0 && configured <= 1_000_000
|
|
97
|
+
? configured
|
|
98
|
+
: 512;
|
|
99
|
+
}
|
|
100
|
+
async function handleMeasureEmbeddingInput(request) {
|
|
101
|
+
const pipe = await loadEmbeddingPipeline();
|
|
102
|
+
const texts = request.texts.map((text) => applyEmbeddingPrefix(text, request.prefix, request.prefixes));
|
|
103
|
+
const tokenized = pipe.tokenizer(texts, {
|
|
104
|
+
add_special_tokens: true,
|
|
105
|
+
truncation: false,
|
|
106
|
+
padding: false,
|
|
107
|
+
return_tensor: false,
|
|
108
|
+
});
|
|
109
|
+
const inputIds = tokenized.input_ids;
|
|
110
|
+
let counts;
|
|
111
|
+
if (texts.length === 1 && inputIds.every((token) => typeof token === "number")) {
|
|
112
|
+
counts = [inputIds.length];
|
|
113
|
+
}
|
|
114
|
+
else if (inputIds.every((tokens) => Array.isArray(tokens))) {
|
|
115
|
+
counts = inputIds.map((tokens) => tokens.length);
|
|
116
|
+
}
|
|
117
|
+
else {
|
|
118
|
+
counts = texts.map((text) => pipe.tokenizer.encode(text, { add_special_tokens: true }).length);
|
|
119
|
+
}
|
|
120
|
+
return { counts, maximum: embeddingMaximumTokens(pipe.tokenizer) };
|
|
121
|
+
}
|
|
84
122
|
async function handleRerank(request) {
|
|
85
123
|
const pipe = await loadRerankerPipeline(request.reranker);
|
|
86
124
|
const results = [];
|
|
@@ -110,17 +148,23 @@ function parseWorkerRequest(message) {
|
|
|
110
148
|
}
|
|
111
149
|
if (!("type" in message))
|
|
112
150
|
throw new Error("Invalid worker request type");
|
|
113
|
-
if (message.type === "embed") {
|
|
151
|
+
if (message.type === "embed" || message.type === "measure_embedding_input") {
|
|
114
152
|
if (!("texts" in message) || !isStringArray(message.texts))
|
|
115
|
-
throw new Error("Invalid
|
|
153
|
+
throw new Error("Invalid embedding texts");
|
|
116
154
|
if (!("prefix" in message) || (message.prefix !== "query" && message.prefix !== "passage")) {
|
|
117
|
-
throw new Error("Invalid
|
|
155
|
+
throw new Error("Invalid embedding prefix");
|
|
118
156
|
}
|
|
119
157
|
const prefixes = "prefixes" in message && (message.prefixes === "on" || message.prefixes === "off") ? message.prefixes : "on";
|
|
120
158
|
if ("prefixes" in message && message.prefixes !== "on" && message.prefixes !== "off") {
|
|
121
|
-
throw new Error("Invalid
|
|
159
|
+
throw new Error("Invalid embedding prefix strategy");
|
|
122
160
|
}
|
|
123
|
-
return {
|
|
161
|
+
return {
|
|
162
|
+
id: message.id,
|
|
163
|
+
type: message.type,
|
|
164
|
+
texts: message.texts,
|
|
165
|
+
prefix: message.prefix,
|
|
166
|
+
prefixes,
|
|
167
|
+
};
|
|
124
168
|
}
|
|
125
169
|
if (message.type === "rerank") {
|
|
126
170
|
if (!("query" in message) || typeof message.query !== "string")
|
|
@@ -151,7 +195,11 @@ async function handleRequestMessage(message) {
|
|
|
151
195
|
requestId = message.id;
|
|
152
196
|
}
|
|
153
197
|
const request = parseWorkerRequest(message);
|
|
154
|
-
const result = request.type === "embed"
|
|
198
|
+
const result = request.type === "embed"
|
|
199
|
+
? await handleEmbed(request)
|
|
200
|
+
: request.type === "measure_embedding_input"
|
|
201
|
+
? await handleMeasureEmbeddingInput(request)
|
|
202
|
+
: await handleRerank(request);
|
|
155
203
|
return { id: request.id, result };
|
|
156
204
|
}
|
|
157
205
|
catch (error) {
|
|
@@ -87,6 +87,7 @@ export declare function listKBs(db: Database.Database): KnowledgeBase[];
|
|
|
87
87
|
export declare function deleteKB(db: Database.Database, id: string): void;
|
|
88
88
|
export declare function updateKBStatus(db: Database.Database, id: string, status: KnowledgeBase["status"]): void;
|
|
89
89
|
export declare function updateKBCounts(db: Database.Database, id: string, chunkCount: number, fileCount: number): void;
|
|
90
|
+
export declare function updateKBSourceOptions(db: Database.Database, id: string, sourceOptions: string): void;
|
|
90
91
|
export declare function updateKBEmbeddingMetadata(db: Database.Database, id: string, embeddingModel: string, embeddingSignature: string | null, embeddingDimension: number | null): void;
|
|
91
92
|
export declare function startIndexingJob(db: Database.Database, kbId: string, operation: IndexingJob["operation"], message: string): void;
|
|
92
93
|
export declare function updateIndexingJob(db: Database.Database, kbId: string, progress: {
|
|
@@ -355,6 +355,9 @@ export function updateKBStatus(db, id, status) {
|
|
|
355
355
|
export function updateKBCounts(db, id, chunkCount, fileCount) {
|
|
356
356
|
db.prepare("UPDATE knowledge_bases SET chunk_count = ?, file_count = ?, updated_at = ? WHERE id = ?").run(chunkCount, fileCount, Date.now(), id);
|
|
357
357
|
}
|
|
358
|
+
export function updateKBSourceOptions(db, id, sourceOptions) {
|
|
359
|
+
db.prepare("UPDATE knowledge_bases SET source_options = ?, updated_at = ? WHERE id = ?").run(sourceOptions, Date.now(), id);
|
|
360
|
+
}
|
|
358
361
|
export function updateKBEmbeddingMetadata(db, id, embeddingModel, embeddingSignature, embeddingDimension) {
|
|
359
362
|
db.prepare(`UPDATE knowledge_bases
|
|
360
363
|
SET embedding_model = ?, embedding_signature = ?, embedding_dimension = ?, updated_at = ?
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "pi-knowledge",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.12.0",
|
|
4
4
|
"description": "Local-first RAG knowledge base for Pi and OMP coding agents with hybrid code/doc search, reranking, diagnostics, and large-project indexing",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|