pi-knowledge 0.10.1 → 0.11.0
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 +12 -0
- package/README.md +7 -4
- package/dist/index.js +2 -1
- package/dist/src/embedding/provider.d.ts +2 -0
- package/dist/src/embedding/provider.js +32 -12
- package/dist/src/engine.d.ts +1 -1
- package/dist/src/engine.js +27 -10
- package/dist/src/model-worker-client.d.ts +1 -1
- package/dist/src/model-worker-client.js +4 -2
- package/dist/src/model-worker.js +12 -2
- package/dist/src/search/tuning.d.ts +1 -1
- package/dist/src/search/tuning.js +1 -1
- package/docs/configuration.md +7 -4
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,17 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## [0.11.0] - 2026-09-23
|
|
4
|
+
|
|
5
|
+
### Added
|
|
6
|
+
- Added `PI_KNOWLEDGE_EMBEDDING_PREFIXES=on|off` so OpenAI-compatible and local embeddings can preserve or omit `query: ` / `passage: ` input prefixes while keeping default E5 behavior compatible with existing KB signatures (#18).
|
|
7
|
+
- Added `semantic_hybrid` search mode for vector-backed weighted fusion without the default hybrid lexical-evidence gate, giving semantic and multilingual queries an explicit recall-oriented path while preserving `hybrid` precision defaults (#17).
|
|
8
|
+
|
|
9
|
+
## [0.10.2] - 2026-09-19
|
|
10
|
+
|
|
11
|
+
### Fixed
|
|
12
|
+
- Allowed OpenAI-compatible embedding endpoints to run without an API key and added `PI_KNOWLEDGE_EMBEDDING_API_KEY` as an embedding-specific bearer token override (#15).
|
|
13
|
+
- Added `PI_KNOWLEDGE_EMBEDDING_BATCH_SIZE` so self-hosted embedding servers can use request batch sizes below the default 64 chunk limit (#16).
|
|
14
|
+
|
|
3
15
|
## [0.10.1] - 2026-09-10
|
|
4
16
|
|
|
5
17
|
### Fixed
|
package/README.md
CHANGED
|
@@ -67,7 +67,7 @@ TUI rendering currently uses Pi's stable default tool rendering plus targeted re
|
|
|
67
67
|
- **Contextual Retrieval without remote chunk rewriting**: applies Anthropic's Contextual Retrieval insight locally by embedding file path, file type, Markdown breadcrumbs, and AST-derived code structure such as symbols, scope, parent symbol, and signatures with each chunk. This improves standalone chunk meaning without sending private source chunks to an LLM for context generation.
|
|
68
68
|
- **Hybrid retrieval with diagnosable scores**: combines lexical BM25 anchors and vectors with normalized weighted score fusion. RRF (Cormack et al. 2009) remains the baseline reference, but weighted fusion is used by default because project dogfood showed RRF compressed scores too much for ranking diagnostics.
|
|
69
69
|
- **MMR-style diversity**: uses Maximal Marginal Relevance ideas (Goldstein and Carbonell 1998), file interleaving, vector redundancy checks, and bounded adaptive-window overlap collapse so repeated README or same-file chunks do not dominate top results. Code KBs with AST metadata can also use same-parent/sibling structure during adaptive expansion.
|
|
70
|
-
- **Intent-aware and self-correcting agent UX**: mode selection (`auto`, `fast`, `semantic`, `hybrid`, `adaptive`, `deep`), ranking diagnostics, and `knowledge_doctor` turn retrieval failures into concrete next actions instead of silent bad answers.
|
|
70
|
+
- **Intent-aware and self-correcting agent UX**: mode selection (`auto`, `fast`, `semantic`, `semantic_hybrid`, `hybrid`, `adaptive`, `deep`), ranking diagnostics, and `knowledge_doctor` turn retrieval failures into concrete next actions instead of silent bad answers.
|
|
71
71
|
- **Confidence gating**: low-evidence hybrid matches can return zero results instead of unrelated chunks, reducing false confidence when the KB does not contain the answer.
|
|
72
72
|
|
|
73
73
|
This is intentionally not a heavy ColBERT-style late-interaction index yet (Khattab and Zaharia 2020). The current product chooses lightweight local embeddings, BM25, query-aware ranking, optional cross-encoder reranking, streamed vector scans, and health diagnostics for commercial usefulness with low setup cost.
|
|
@@ -125,6 +125,7 @@ omp install ./pi-knowledge
|
|
|
125
125
|
- `fast`: BM25 keyword search for exact symbols, commands, and identifiers.
|
|
126
126
|
- `semantic`: vector search for conceptual matches.
|
|
127
127
|
- `hybrid`: lexical-anchored BM25 + vector search with normalized weighted score fusion. It requires keyword evidence to avoid low-confidence semantic false positives.
|
|
128
|
+
- `semantic_hybrid`: vector search plus optional BM25 weighted fusion without the hybrid lexical-evidence gate; use explicitly for semantic/multilingual queries where lexical overlap is weak but fused scoring is still useful.
|
|
128
129
|
- `deep`: hybrid retrieval followed by cross-encoder reranking.
|
|
129
130
|
- `adaptive`: hybrid retrieval followed by query-time contextual window expansion around seed chunks. It keeps the matched seed, prefers nearby/query-relevant neighboring chunks, and collapses overlapping windows from the same file.
|
|
130
131
|
- `auto`: selects a primary mode from the query shape and retries alternate modes when results are empty or weak.
|
|
@@ -136,7 +137,7 @@ Mode selection contract:
|
|
|
136
137
|
|
|
137
138
|
- Start with `hybrid` for most project questions that contain useful lexical anchors.
|
|
138
139
|
- Use `fast` for exact symbols, filenames, commands, error codes, API names, config keys, or quoted strings.
|
|
139
|
-
- Use `semantic` when the query is conceptual
|
|
140
|
+
- Use `semantic` when the query is conceptual and exact terms may differ from indexed wording; use `semantic_hybrid` when weak lexical overlap should not block vector-backed fused results.
|
|
140
141
|
- Use `adaptive` when the answer needs nearby code, neighboring documentation sections, AST-related sibling methods where indexed, or enough context to make a safe edit.
|
|
141
142
|
- Use `deep` for high-stakes answers, ambiguous top results, or final verification when slower reranking is acceptable.
|
|
142
143
|
- If results are empty or weak but the KB should contain the answer, retry once with a different mode before concluding no answer exists.
|
|
@@ -166,13 +167,15 @@ For self-hosted OpenAI-compatible servers, set either `PI_KNOWLEDGE_EMBEDDING_BA
|
|
|
166
167
|
```bash
|
|
167
168
|
export PI_KNOWLEDGE_EMBEDDING=openai:Qwen3-Embedding-8B
|
|
168
169
|
export PI_KNOWLEDGE_EMBEDDING_BASE_URL=http://127.0.0.1:8080/v1
|
|
169
|
-
|
|
170
|
+
# Set PI_KNOWLEDGE_EMBEDDING_API_KEY or OPENAI_API_KEY only if your endpoint requires bearer auth.
|
|
170
171
|
```
|
|
171
172
|
|
|
172
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.
|
|
173
174
|
|
|
174
175
|
API embedding requests are capped at 20000 characters per input by default as a final context-window safety guard for OpenAI-compatible servers. Adjust this with `PI_KNOWLEDGE_EMBEDDING_MAX_CHARS` when your embedding model has a different context window; changing the cap changes embedding compatibility and requires `knowledge_update`.
|
|
175
176
|
|
|
177
|
+
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
|
+
|
|
176
179
|
Stored KB metadata includes the embedding model, vector dimension, and a non-secret embedding signature. If the current query embedding is incompatible with a KB's stored vectors, or if an older KB has no signature metadata, `knowledge_search` skips vector retrieval for that KB and reports a warning; run `knowledge_update` after changing embedding providers or upgrading older KBs.
|
|
177
180
|
|
|
178
181
|
## Configuration
|
|
@@ -183,7 +186,7 @@ Full configuration details are in [docs/configuration.md](docs/configuration.md)
|
|
|
183
186
|
|------|-----------------------|
|
|
184
187
|
| Storage path | `PI_KNOWLEDGE_DIR`, `OMP_KNOWLEDGE_DIR`, `PI_CODING_AGENT_DIR`, `OMP_CODING_AGENT_DIR`, `OMP_PROFILE` |
|
|
185
188
|
| Model worker and cache | `PI_KNOWLEDGE_MODEL_CACHE_DIR`, `PI_KNOWLEDGE_NODE_PATH` |
|
|
186
|
-
| Embedding provider | `PI_KNOWLEDGE_EMBEDDING`, `OPENAI_API_KEY`, `PI_KNOWLEDGE_EMBEDDING_BASE_URL`, `OPENAI_BASE_URL`, `PI_KNOWLEDGE_EMBEDDING_MAX_CHARS`, `PI_KNOWLEDGE_EMBEDDING_API_FALLBACK` |
|
|
189
|
+
| Embedding provider | `PI_KNOWLEDGE_EMBEDDING`, `PI_KNOWLEDGE_EMBEDDING_API_KEY`, `OPENAI_API_KEY`, `PI_KNOWLEDGE_EMBEDDING_BASE_URL`, `OPENAI_BASE_URL`, `PI_KNOWLEDGE_EMBEDDING_PREFIXES`, `PI_KNOWLEDGE_EMBEDDING_MAX_CHARS`, `PI_KNOWLEDGE_EMBEDDING_BATCH_SIZE`, `PI_KNOWLEDGE_EMBEDDING_API_FALLBACK` |
|
|
187
190
|
| Reranker provider | `PI_KNOWLEDGE_RERANKER`, `PI_KNOWLEDGE_RERANKER_REVISION`, `PI_KNOWLEDGE_RERANKER_DTYPE`, `PI_KNOWLEDGE_RERANKER_REMOTE_HOST`, `PI_KNOWLEDGE_RERANKER_REMOTE_PATH_TEMPLATE`, `PI_KNOWLEDGE_RERANKER_RAW_LOGITS`, `PI_KNOWLEDGE_RERANKER_API_ENDPOINT`, `PI_KNOWLEDGE_RERANKER_API_BASE_URL`, `PI_KNOWLEDGE_RERANKER_API_KEY`, `PI_KNOWLEDGE_RERANKER_API_FORMAT`, `PI_KNOWLEDGE_RERANKER_API_TIMEOUT_MS`, `PI_KNOWLEDGE_RERANKER_MAX_DOC_CHARS`, `PI_KNOWLEDGE_RERANKER_API_RESULTS_PATH`, `PI_KNOWLEDGE_RERANKER_API_INDEX_FIELD`, `PI_KNOWLEDGE_RERANKER_API_SCORE_FIELD`, `PI_KNOWLEDGE_RERANKER_API_SCORE_DIRECTION` |
|
|
188
191
|
| Native lifecycle | `PI_KNOWLEDGE_ENABLE_NATIVE_IDLE_DISPOSE`, `PI_KNOWLEDGE_EMBEDDING_IDLE_MS` |
|
|
189
192
|
| Runtime features | `PI_KNOWLEDGE_WATCH`, `PI_KNOWLEDGE_AUTO_INJECT`, `PI_KNOWLEDGE_STALE_INDEXING_MS`, `PI_KNOWLEDGE_OFFLINE`, `PI_KNOWLEDGE_SEARCH_PROFILE`, `PI_KNOWLEDGE_SEARCH_DEFAULT_LIMIT`, `PI_KNOWLEDGE_SNIPPET_MAX_LENGTH`, `PI_KNOWLEDGE_MIN_HYBRID_SCORE`, `PI_KNOWLEDGE_SEARCH_CANDIDATE_MIN`, `PI_KNOWLEDGE_SEARCH_CANDIDATE_MULTIPLIER`, `PI_KNOWLEDGE_ADAPTIVE_CONTEXT_LINES`, `PI_KNOWLEDGE_ADAPTIVE_MAX_CHARS`, `PI_KNOWLEDGE_ADAPTIVE_NEIGHBOR_TARGET`, `PI_KNOWLEDGE_DEEP_RERANK_CANDIDATES`, `PI_KNOWLEDGE_DEEP_RERANK_TOPK_MULTIPLIER` |
|
package/dist/index.js
CHANGED
|
@@ -364,7 +364,7 @@ export default function (pi) {
|
|
|
364
364
|
"Use knowledge_search to find relevant context before answering domain questions",
|
|
365
365
|
"Default to mode 'hybrid' for most project questions with useful lexical anchors; it fuses BM25 and semantic vectors but still requires keyword evidence",
|
|
366
366
|
"Use mode 'fast' for exact symbols, filenames, commands, error codes, API names, config keys, or quoted strings",
|
|
367
|
-
"Use mode 'semantic' for
|
|
367
|
+
"Use mode 'semantic' for pure vector search when exact terms may differ from indexed wording; use mode 'semantic_hybrid' when you want vector recall plus BM25/fusion scoring without the hybrid lexical evidence gate",
|
|
368
368
|
"Use mode 'adaptive' when the user needs surrounding implementation context, related nearby sections, or enough context to make a code change",
|
|
369
369
|
"Use mode 'deep' for high-stakes answers, ambiguous top results, or final verification where slower cross-encoder reranking is acceptable",
|
|
370
370
|
"Use profile 'low_token' for slow local models that need fewer, stricter, longer snippets; use profile 'precision' for identifiers/errors and 'recall' or 'long_context' for broad prose/document research",
|
|
@@ -378,6 +378,7 @@ export default function (pi) {
|
|
|
378
378
|
Type.Literal("fast"),
|
|
379
379
|
Type.Literal("semantic"),
|
|
380
380
|
Type.Literal("hybrid"),
|
|
381
|
+
Type.Literal("semantic_hybrid"),
|
|
381
382
|
Type.Literal("deep"),
|
|
382
383
|
Type.Literal("adaptive"),
|
|
383
384
|
Type.Literal("code"),
|
|
@@ -1,5 +1,6 @@
|
|
|
1
1
|
export type EmbeddingProvider = "local" | "openai";
|
|
2
2
|
export type EmbeddingPrefix = "query" | "passage";
|
|
3
|
+
export type EmbeddingPrefixStrategy = "on" | "off";
|
|
3
4
|
export interface EmbeddingConfig {
|
|
4
5
|
provider: EmbeddingProvider;
|
|
5
6
|
model: string;
|
|
@@ -7,6 +8,7 @@ export interface EmbeddingConfig {
|
|
|
7
8
|
maxChars: number;
|
|
8
9
|
queryPrefix: "query";
|
|
9
10
|
documentPrefix: "passage";
|
|
11
|
+
prefixes: EmbeddingPrefixStrategy;
|
|
10
12
|
pooling: "mean";
|
|
11
13
|
normalize: true;
|
|
12
14
|
}
|
|
@@ -13,13 +13,14 @@ export const DEFAULT_API_MAX_EMBED_CHARS = 20_000;
|
|
|
13
13
|
const IDLE_TIMEOUT_MS = Number(process.env.PI_KNOWLEDGE_EMBEDDING_IDLE_MS ?? 30_000);
|
|
14
14
|
const ENABLE_NATIVE_IDLE_DISPOSE = process.env.PI_KNOWLEDGE_ENABLE_NATIVE_IDLE_DISPOSE === "true";
|
|
15
15
|
const API_FALLBACK_TO_LOCAL = process.env.PI_KNOWLEDGE_EMBEDDING_API_FALLBACK === "local";
|
|
16
|
-
function localEmbeddingConfig(maxChars) {
|
|
16
|
+
function localEmbeddingConfig(maxChars, prefixes) {
|
|
17
17
|
return {
|
|
18
18
|
provider: "local",
|
|
19
19
|
model: DEFAULT_LOCAL_EMBEDDING_MODEL,
|
|
20
20
|
maxChars,
|
|
21
21
|
queryPrefix: "query",
|
|
22
22
|
documentPrefix: "passage",
|
|
23
|
+
prefixes,
|
|
23
24
|
pooling: "mean",
|
|
24
25
|
normalize: true,
|
|
25
26
|
};
|
|
@@ -65,6 +66,14 @@ function waitForNoActiveRuns() {
|
|
|
65
66
|
function providerInstanceHash(value) {
|
|
66
67
|
return createHash("sha256").update(value).digest("hex").slice(0, 12);
|
|
67
68
|
}
|
|
69
|
+
function resolveEmbeddingPrefixStrategy(env) {
|
|
70
|
+
const raw = cleanEnv(env.PI_KNOWLEDGE_EMBEDDING_PREFIXES)?.toLowerCase();
|
|
71
|
+
if (!raw)
|
|
72
|
+
return "on";
|
|
73
|
+
if (raw === "on" || raw === "off")
|
|
74
|
+
return raw;
|
|
75
|
+
throw new Error(`Unsupported embedding prefix strategy: ${raw}. Use PI_KNOWLEDGE_EMBEDDING_PREFIXES=on or off.`);
|
|
76
|
+
}
|
|
68
77
|
export function resolveEmbeddingConfig(env = process.env) {
|
|
69
78
|
const raw = cleanEnv(env.PI_KNOWLEDGE_EMBEDDING) ?? `local:${DEFAULT_LOCAL_EMBEDDING_MODEL}`;
|
|
70
79
|
const separator = raw.indexOf(":");
|
|
@@ -72,12 +81,13 @@ export function resolveEmbeddingConfig(env = process.env) {
|
|
|
72
81
|
const model = separator >= 0 ? raw.slice(separator + 1).trim() : "";
|
|
73
82
|
const maxCharsValue = Number(cleanEnv(env.PI_KNOWLEDGE_EMBEDDING_MAX_CHARS) ?? DEFAULT_API_MAX_EMBED_CHARS);
|
|
74
83
|
const maxChars = Number.isFinite(maxCharsValue) && maxCharsValue > 0 ? Math.trunc(maxCharsValue) : DEFAULT_API_MAX_EMBED_CHARS;
|
|
84
|
+
const prefixes = resolveEmbeddingPrefixStrategy(env);
|
|
75
85
|
if (provider === "local") {
|
|
76
86
|
const localModel = model || DEFAULT_LOCAL_EMBEDDING_MODEL;
|
|
77
87
|
if (localModel !== DEFAULT_LOCAL_EMBEDDING_MODEL) {
|
|
78
88
|
throw new Error(`Unsupported local embedding model: ${localModel}`);
|
|
79
89
|
}
|
|
80
|
-
return localEmbeddingConfig(maxChars);
|
|
90
|
+
return localEmbeddingConfig(maxChars, prefixes);
|
|
81
91
|
}
|
|
82
92
|
if (provider === "openai") {
|
|
83
93
|
return {
|
|
@@ -87,6 +97,7 @@ export function resolveEmbeddingConfig(env = process.env) {
|
|
|
87
97
|
maxChars,
|
|
88
98
|
queryPrefix: "query",
|
|
89
99
|
documentPrefix: "passage",
|
|
100
|
+
prefixes,
|
|
90
101
|
pooling: "mean",
|
|
91
102
|
normalize: true,
|
|
92
103
|
};
|
|
@@ -98,7 +109,7 @@ export function embeddingConfigLabel(config) {
|
|
|
98
109
|
}
|
|
99
110
|
export function embeddingSignature(config, dimension) {
|
|
100
111
|
const base = config.baseUrl ? `:base-sha256=${providerInstanceHash(config.baseUrl)}` : "";
|
|
101
|
-
|
|
112
|
+
const parts = [
|
|
102
113
|
`${config.provider}:${config.model}${base}`,
|
|
103
114
|
`dim=${dimension}`,
|
|
104
115
|
`apiMax=${config.provider === "openai" ? config.maxChars : "none"}`,
|
|
@@ -106,7 +117,10 @@ export function embeddingSignature(config, dimension) {
|
|
|
106
117
|
`normalize=${config.normalize}`,
|
|
107
118
|
`q=${config.queryPrefix}`,
|
|
108
119
|
`d=${config.documentPrefix}`,
|
|
109
|
-
]
|
|
120
|
+
];
|
|
121
|
+
if (config.prefixes === "off")
|
|
122
|
+
parts.push("prefixes=off");
|
|
123
|
+
return parts.join(":");
|
|
110
124
|
}
|
|
111
125
|
export async function dispose() {
|
|
112
126
|
clearIdleTimer();
|
|
@@ -124,18 +138,24 @@ export async function prepareForShutdown() {
|
|
|
124
138
|
clearIdleTimer();
|
|
125
139
|
await waitForNoActiveRuns();
|
|
126
140
|
}
|
|
141
|
+
function applyEmbeddingPrefix(text, prefix, config) {
|
|
142
|
+
return config.prefixes === "on" ? `${prefix}: ${text}` : text;
|
|
143
|
+
}
|
|
127
144
|
async function embedViaAPI(texts, prefix, config, signal) {
|
|
128
|
-
const
|
|
129
|
-
|
|
130
|
-
|
|
131
|
-
|
|
132
|
-
|
|
145
|
+
const safeTexts = texts.map((text) => {
|
|
146
|
+
const embeddingText = applyEmbeddingPrefix(text, prefix, config);
|
|
147
|
+
return embeddingText.length > config.maxChars ? embeddingText.slice(0, config.maxChars) : embeddingText;
|
|
148
|
+
});
|
|
149
|
+
const apiKey = cleanEnv(process.env.PI_KNOWLEDGE_EMBEDDING_API_KEY) ?? cleanEnv(process.env.OPENAI_API_KEY);
|
|
133
150
|
if (!config.baseUrl)
|
|
134
151
|
throw new Error("OpenAI embedding base URL is not configured");
|
|
135
152
|
const endpoint = new URL("embeddings", `${config.baseUrl.replace(/\/+$/, "")}/`);
|
|
153
|
+
const headers = { "Content-Type": "application/json" };
|
|
154
|
+
if (apiKey)
|
|
155
|
+
headers.Authorization = `Bearer ${apiKey}`;
|
|
136
156
|
const res = await fetch(endpoint, {
|
|
137
157
|
method: "POST",
|
|
138
|
-
headers
|
|
158
|
+
headers,
|
|
139
159
|
body: JSON.stringify({ input: safeTexts, model: config.model }),
|
|
140
160
|
signal,
|
|
141
161
|
});
|
|
@@ -161,12 +181,12 @@ export async function embedTextsWithConfig(texts, prefix, signal, options = {})
|
|
|
161
181
|
if (!API_FALLBACK_TO_LOCAL || !options.allowApiFallback)
|
|
162
182
|
throw error;
|
|
163
183
|
console.warn(`pi-knowledge: embedding API failed; falling back to local model because PI_KNOWLEDGE_EMBEDDING_API_FALLBACK=local (${error instanceof Error ? error.message : String(error)})`);
|
|
164
|
-
actualConfig = localEmbeddingConfig(config.maxChars);
|
|
184
|
+
actualConfig = localEmbeddingConfig(config.maxChars, config.prefixes);
|
|
165
185
|
}
|
|
166
186
|
}
|
|
167
187
|
beginRun();
|
|
168
188
|
try {
|
|
169
|
-
return { vectors: await embedInModelWorker(texts, prefix, signal), config: actualConfig };
|
|
189
|
+
return { vectors: await embedInModelWorker(texts, prefix, actualConfig.prefixes, signal), config: actualConfig };
|
|
170
190
|
}
|
|
171
191
|
finally {
|
|
172
192
|
endRun();
|
package/dist/src/engine.d.ts
CHANGED
|
@@ -3,7 +3,7 @@ import { createSkippedScanStats } from "./indexer/chunker.ts";
|
|
|
3
3
|
import { type RankingDiagnostics } from "./search/ranking.ts";
|
|
4
4
|
import { type SearchProfile, type SearchTuningSummary } from "./search/tuning.ts";
|
|
5
5
|
import { type KnowledgeBase, type KnowledgeSymbol } from "./storage/sqlite.ts";
|
|
6
|
-
export type SearchMode = "auto" | "fast" | "semantic" | "hybrid" | "deep" | "adaptive" | "code" | "config" | "docs" | "errors" | "decision";
|
|
6
|
+
export type SearchMode = "auto" | "fast" | "semantic" | "hybrid" | "semantic_hybrid" | "deep" | "adaptive" | "code" | "config" | "docs" | "errors" | "decision";
|
|
7
7
|
export interface SearchOptions {
|
|
8
8
|
mode?: SearchMode;
|
|
9
9
|
profile?: SearchProfile;
|
package/dist/src/engine.js
CHANGED
|
@@ -15,8 +15,18 @@ import { resolveSearchTuning, summarizeSearchTuning, } from "./search/tuning.js"
|
|
|
15
15
|
import { searchVectorFile } from "./search/vector.js";
|
|
16
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";
|
|
17
17
|
export { CURRENT_EMBEDDING_MODEL } from "./embedding/provider.js";
|
|
18
|
-
const
|
|
18
|
+
const DEFAULT_INDEX_EMBED_BATCH_SIZE = 64;
|
|
19
19
|
const VECTOR_REDUNDANCY_WEIGHT = 0.35;
|
|
20
|
+
function resolveIndexEmbedBatchSize(env = process.env) {
|
|
21
|
+
const raw = env.PI_KNOWLEDGE_EMBEDDING_BATCH_SIZE?.trim();
|
|
22
|
+
if (!raw)
|
|
23
|
+
return DEFAULT_INDEX_EMBED_BATCH_SIZE;
|
|
24
|
+
const value = Number(raw);
|
|
25
|
+
if (!Number.isFinite(value))
|
|
26
|
+
return DEFAULT_INDEX_EMBED_BATCH_SIZE;
|
|
27
|
+
const batchSize = Math.trunc(value);
|
|
28
|
+
return batchSize > 0 ? batchSize : DEFAULT_INDEX_EMBED_BATCH_SIZE;
|
|
29
|
+
}
|
|
20
30
|
function isCancellationError(error) {
|
|
21
31
|
return error instanceof Error && error.message === "Cancelled";
|
|
22
32
|
}
|
|
@@ -704,6 +714,7 @@ export class KnowledgeEngine {
|
|
|
704
714
|
throw new Error(`Knowledge base "${name}" already exists. Use knowledge_update to refresh it, or knowledge_remove before adding a replacement.`);
|
|
705
715
|
}
|
|
706
716
|
const embeddingConfig = resolveEmbeddingConfig();
|
|
717
|
+
const embeddingBatchSize = resolveIndexEmbedBatchSize();
|
|
707
718
|
const kb = createKB(db, {
|
|
708
719
|
name,
|
|
709
720
|
source_path: isDir || isFile ? resolvedSource : isUrl ? source : undefined,
|
|
@@ -759,7 +770,7 @@ export class KnowledgeEngine {
|
|
|
759
770
|
return;
|
|
760
771
|
if (signal?.aborted)
|
|
761
772
|
throw new Error("Cancelled");
|
|
762
|
-
const batch = pendingChunks.splice(0,
|
|
773
|
+
const batch = pendingChunks.splice(0, embeddingBatchSize);
|
|
763
774
|
reportProgress(`Embedding batch of ${batch.length}`, processedFiles, totalFiles);
|
|
764
775
|
const vectors = await embedDocuments(batch.map((chunk) => buildChunkEmbeddingText(chunk)), signal);
|
|
765
776
|
if (signal?.aborted)
|
|
@@ -774,7 +785,7 @@ export class KnowledgeEngine {
|
|
|
774
785
|
};
|
|
775
786
|
const addChunks = async (chunks, processedFiles, totalFiles) => {
|
|
776
787
|
pendingChunks.push(...chunks);
|
|
777
|
-
while (pendingChunks.length >=
|
|
788
|
+
while (pendingChunks.length >= embeddingBatchSize) {
|
|
778
789
|
await flushPending(processedFiles, totalFiles);
|
|
779
790
|
}
|
|
780
791
|
};
|
|
@@ -927,6 +938,7 @@ export class KnowledgeEngine {
|
|
|
927
938
|
startIndexingJob(this.db, kb.id, "update", `Starting update for "${kb.name}"`);
|
|
928
939
|
const scanOptions = toScanOptions(parseAddOptions(kb.source_options));
|
|
929
940
|
const embeddingConfig = resolveEmbeddingConfig();
|
|
941
|
+
const embeddingBatchSize = resolveIndexEmbedBatchSize();
|
|
930
942
|
const embeddingModel = embeddingConfigLabel(embeddingConfig);
|
|
931
943
|
const currentSignature = kb.embedding_dimension === null ? undefined : embeddingSignature(embeddingConfig, kb.embedding_dimension);
|
|
932
944
|
let canReuseExistingVectors = kb.embedding_signature !== null && kb.embedding_dimension !== null && kb.embedding_signature === currentSignature;
|
|
@@ -991,7 +1003,7 @@ export class KnowledgeEngine {
|
|
|
991
1003
|
return;
|
|
992
1004
|
if (signal?.aborted)
|
|
993
1005
|
throw new Error("Cancelled");
|
|
994
|
-
const batch = pendingChunks.splice(0,
|
|
1006
|
+
const batch = pendingChunks.splice(0, embeddingBatchSize);
|
|
995
1007
|
const elapsed = Date.now() - startedAt;
|
|
996
1008
|
const message = `Embedding update batch: ${addedCount} new chunks stored, ${scannedFiles} files scanned, elapsed ${formatDuration(elapsed)}`;
|
|
997
1009
|
updateIndexingJob(this.db, kb.id, {
|
|
@@ -1045,7 +1057,7 @@ export class KnowledgeEngine {
|
|
|
1045
1057
|
continue;
|
|
1046
1058
|
}
|
|
1047
1059
|
pendingChunks.push(chunk);
|
|
1048
|
-
if (pendingChunks.length >=
|
|
1060
|
+
if (pendingChunks.length >= embeddingBatchSize)
|
|
1049
1061
|
await flushPending();
|
|
1050
1062
|
}
|
|
1051
1063
|
};
|
|
@@ -1359,8 +1371,9 @@ export class KnowledgeEngine {
|
|
|
1359
1371
|
vectorsByChunkId.set(chunkId, vector);
|
|
1360
1372
|
}
|
|
1361
1373
|
else {
|
|
1374
|
+
const semanticHybrid = retrievalMode === "semantic_hybrid";
|
|
1362
1375
|
const bm25Results = searchBM25(db, normalizedQuery || query, candidateLimit, kb.id);
|
|
1363
|
-
if (bm25Results.length === 0)
|
|
1376
|
+
if (bm25Results.length === 0 && !semanticHybrid)
|
|
1364
1377
|
continue;
|
|
1365
1378
|
let vecResults = [];
|
|
1366
1379
|
const { vector: queryVec, config: queryEmbeddingConfig } = await embedQueryWithConfig(query, signal);
|
|
@@ -1410,6 +1423,8 @@ export class KnowledgeEngine {
|
|
|
1410
1423
|
const chunk = getChunkById(db, result.chunkId);
|
|
1411
1424
|
if (!chunk)
|
|
1412
1425
|
return false;
|
|
1426
|
+
if (retrievalMode === "semantic_hybrid")
|
|
1427
|
+
return result.score >= tuning.minHybridScore;
|
|
1413
1428
|
return result.score >= tuning.minHybridScore && hasEnoughLexicalEvidence(chunk, queryTokens);
|
|
1414
1429
|
});
|
|
1415
1430
|
}
|
|
@@ -1566,7 +1581,7 @@ export class KnowledgeEngine {
|
|
|
1566
1581
|
tuning: tuningSummary,
|
|
1567
1582
|
suggestions: results.length === 0
|
|
1568
1583
|
? [
|
|
1569
|
-
"Try mode 'fast' for exact symbols
|
|
1584
|
+
"Try mode 'fast' for exact symbols, mode 'semantic' for pure vector search, or mode 'semantic_hybrid' when weak lexical overlap should not block fused vector results.",
|
|
1570
1585
|
"Run knowledge_status if the KB should contain this answer.",
|
|
1571
1586
|
]
|
|
1572
1587
|
: undefined,
|
|
@@ -1789,6 +1804,7 @@ export class KnowledgeEngine {
|
|
|
1789
1804
|
const { createWriteStream } = await import("node:fs");
|
|
1790
1805
|
const tempOutputPath = tempVectorPath(outputPath);
|
|
1791
1806
|
const stream = createWriteStream(tempOutputPath, { encoding: "utf-8" });
|
|
1807
|
+
const progressBatchSize = resolveIndexEmbedBatchSize();
|
|
1792
1808
|
let count = 0;
|
|
1793
1809
|
const header = JSON.stringify({
|
|
1794
1810
|
name: kb.name,
|
|
@@ -1809,7 +1825,7 @@ export class KnowledgeEngine {
|
|
|
1809
1825
|
metadata_json: chunk.metadata_json,
|
|
1810
1826
|
}));
|
|
1811
1827
|
count++;
|
|
1812
|
-
if (count %
|
|
1828
|
+
if (count % progressBatchSize === 0)
|
|
1813
1829
|
onProgress?.(`Exported ${count}/${kb.chunk_count} chunks...`);
|
|
1814
1830
|
}
|
|
1815
1831
|
await finishWriteStream(stream);
|
|
@@ -1838,6 +1854,7 @@ export class KnowledgeEngine {
|
|
|
1838
1854
|
const stream = createReadStream(inputPath, { encoding: "utf-8" });
|
|
1839
1855
|
const lines = createInterface({ input: stream, crlfDelay: Infinity });
|
|
1840
1856
|
const embeddingConfig = resolveEmbeddingConfig();
|
|
1857
|
+
const embeddingBatchSize = resolveIndexEmbedBatchSize();
|
|
1841
1858
|
let header;
|
|
1842
1859
|
let kb;
|
|
1843
1860
|
let vectorWriter;
|
|
@@ -1850,7 +1867,7 @@ export class KnowledgeEngine {
|
|
|
1850
1867
|
if (!this.db || !kb || !vectorWriter || pendingChunks.length === 0)
|
|
1851
1868
|
return;
|
|
1852
1869
|
throwIfAborted(signal);
|
|
1853
|
-
const batch = pendingChunks.splice(0,
|
|
1870
|
+
const batch = pendingChunks.splice(0, embeddingBatchSize);
|
|
1854
1871
|
const symbols = pendingSymbols.splice(0);
|
|
1855
1872
|
const total = header?.chunk_count;
|
|
1856
1873
|
const message = `Embedding import batch: ${inserted}/${total ?? "unknown"} chunks stored`;
|
|
@@ -1919,7 +1936,7 @@ export class KnowledgeEngine {
|
|
|
1919
1936
|
chunk.content_tokenized = preTokenizeForFTS(buildChunkEmbeddingText(chunk));
|
|
1920
1937
|
pendingChunks.push(chunk);
|
|
1921
1938
|
pendingSymbols.push(...extractSymbols(imported.content, imported.file_path, imported.file_type));
|
|
1922
|
-
if (pendingChunks.length >=
|
|
1939
|
+
if (pendingChunks.length >= embeddingBatchSize)
|
|
1923
1940
|
await flushPending();
|
|
1924
1941
|
}
|
|
1925
1942
|
if (!header)
|
|
@@ -2,7 +2,7 @@ import type { HfRerankerConfig } from "./search/reranker-config.ts";
|
|
|
2
2
|
export declare function validateModelWorkerNodePath(nodePath: string): string;
|
|
3
3
|
export declare function resolveModelWorkerNodePath(): string;
|
|
4
4
|
export declare function configureModelWorkerNodePath(nodePath?: string): string;
|
|
5
|
-
export declare function embedInModelWorker(texts: string[], prefix: "query" | "passage", signal?: AbortSignal): Promise<Float32Array[]>;
|
|
5
|
+
export declare function embedInModelWorker(texts: string[], prefix: "query" | "passage", prefixesOrSignal?: "on" | "off" | AbortSignal, signal?: AbortSignal): Promise<Float32Array[]>;
|
|
6
6
|
export interface RerankWorkerCandidate {
|
|
7
7
|
chunkId: string;
|
|
8
8
|
content: string;
|
|
@@ -385,8 +385,10 @@ function getWorker() {
|
|
|
385
385
|
IpcModelWorkerTransport.create(workerPath, nodeExecPath) ?? new StdioModelWorkerTransport(workerPath, nodeExecPath);
|
|
386
386
|
return worker;
|
|
387
387
|
}
|
|
388
|
-
export async function embedInModelWorker(texts, prefix, signal) {
|
|
389
|
-
const
|
|
388
|
+
export async function embedInModelWorker(texts, prefix, prefixesOrSignal, signal) {
|
|
389
|
+
const prefixes = prefixesOrSignal === "off" ? "off" : "on";
|
|
390
|
+
const requestSignal = typeof prefixesOrSignal === "object" ? prefixesOrSignal : signal;
|
|
391
|
+
const result = await getWorker().request({ type: "embed", texts, prefix, prefixes }, requestSignal);
|
|
390
392
|
if (!Array.isArray(result))
|
|
391
393
|
throw new Error("Invalid embedding worker response");
|
|
392
394
|
return result.map((vector) => {
|
package/dist/src/model-worker.js
CHANGED
|
@@ -66,11 +66,17 @@ async function loadRerankerPipeline(config) {
|
|
|
66
66
|
rerankerPipeline = { key, pipe: loaded };
|
|
67
67
|
return loaded;
|
|
68
68
|
}
|
|
69
|
+
function applyEmbeddingPrefix(text, prefix, prefixes) {
|
|
70
|
+
return prefixes === "on" ? `${prefix}: ${text}` : text;
|
|
71
|
+
}
|
|
69
72
|
async function handleEmbed(request) {
|
|
70
73
|
const pipe = await loadEmbeddingPipeline();
|
|
71
74
|
const vectors = [];
|
|
72
75
|
for (const text of request.texts) {
|
|
73
|
-
const output = await pipe(
|
|
76
|
+
const output = await pipe(applyEmbeddingPrefix(text, request.prefix, request.prefixes), {
|
|
77
|
+
pooling: "mean",
|
|
78
|
+
normalize: true,
|
|
79
|
+
});
|
|
74
80
|
vectors.push(Array.from(output.data));
|
|
75
81
|
}
|
|
76
82
|
return vectors;
|
|
@@ -110,7 +116,11 @@ function parseWorkerRequest(message) {
|
|
|
110
116
|
if (!("prefix" in message) || (message.prefix !== "query" && message.prefix !== "passage")) {
|
|
111
117
|
throw new Error("Invalid embed prefix");
|
|
112
118
|
}
|
|
113
|
-
|
|
119
|
+
const prefixes = "prefixes" in message && (message.prefixes === "on" || message.prefixes === "off") ? message.prefixes : "on";
|
|
120
|
+
if ("prefixes" in message && message.prefixes !== "on" && message.prefixes !== "off") {
|
|
121
|
+
throw new Error("Invalid embed prefix strategy");
|
|
122
|
+
}
|
|
123
|
+
return { id: message.id, type: "embed", texts: message.texts, prefix: message.prefix, prefixes };
|
|
114
124
|
}
|
|
115
125
|
if (message.type === "rerank") {
|
|
116
126
|
if (!("query" in message) || typeof message.query !== "string")
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
export type SearchProfile = "auto" | "balanced" | "low_token" | "precision" | "recall" | "long_context" | "code" | "docs";
|
|
2
2
|
export type RuntimeProfile = Exclude<SearchProfile, "auto">;
|
|
3
|
-
type SearchModeForTuning = "auto" | "fast" | "semantic" | "hybrid" | "deep" | "adaptive" | "code" | "config" | "docs" | "errors" | "decision";
|
|
3
|
+
type SearchModeForTuning = "auto" | "fast" | "semantic" | "hybrid" | "semantic_hybrid" | "deep" | "adaptive" | "code" | "config" | "docs" | "errors" | "decision";
|
|
4
4
|
export interface SearchTuning {
|
|
5
5
|
requestedProfile: SearchProfile;
|
|
6
6
|
selectedProfile: RuntimeProfile;
|
|
@@ -143,7 +143,7 @@ function chooseRuntimeProfile(input) {
|
|
|
143
143
|
}
|
|
144
144
|
if (input.mode === "docs" || input.mode === "decision" || input.mode === "adaptive")
|
|
145
145
|
return "long_context";
|
|
146
|
-
if (input.mode === "semantic")
|
|
146
|
+
if (input.mode === "semantic" || input.mode === "semantic_hybrid")
|
|
147
147
|
return "recall";
|
|
148
148
|
if (looksErrorQuery(input.query) || looksExactOrCodeQuery(input.query))
|
|
149
149
|
return "precision";
|
package/docs/configuration.md
CHANGED
|
@@ -21,16 +21,19 @@ Default data storage is `~/.pi/knowledge` under Pi and `~/.omp/knowledge` under
|
|
|
21
21
|
| Variable | Default | Purpose |
|
|
22
22
|
|----------|---------|---------|
|
|
23
23
|
| `PI_KNOWLEDGE_EMBEDDING` | `local:multilingual-e5-small` | Select the embedding provider and model. Supported values are local embeddings and `openai:<model>`. |
|
|
24
|
-
| `
|
|
24
|
+
| `PI_KNOWLEDGE_EMBEDDING_API_KEY` | unset | API key for OpenAI-compatible embedding APIs. Takes precedence over `OPENAI_API_KEY`; omit for trusted local endpoints that do not require auth. |
|
|
25
|
+
| `OPENAI_API_KEY` | unset | Fallback API key used when `PI_KNOWLEDGE_EMBEDDING=openai:<model>`. Required by OpenAI's hosted API; many local OpenAI-compatible servers do not need it. |
|
|
25
26
|
| `PI_KNOWLEDGE_EMBEDDING_BASE_URL` | unset | OpenAI-compatible embedding API root, such as `http://127.0.0.1:8080/v1`. Takes precedence over `OPENAI_BASE_URL`. |
|
|
26
27
|
| `OPENAI_BASE_URL` | `https://api.openai.com/v1` | Common OpenAI-compatible API root fallback. |
|
|
28
|
+
| `PI_KNOWLEDGE_EMBEDDING_PREFIXES` | `on` | Controls whether `query: ` and `passage: ` prefixes are prepended before embedding. Values: `on`, `off`. Keep `on` for the default E5 local model; use `off` only for models or self-hosted APIs that are evaluated without E5-style prefixes. |
|
|
27
29
|
| `PI_KNOWLEDGE_EMBEDDING_MAX_CHARS` | `20000` | Final per-input API embedding safety cap for OpenAI-compatible servers with smaller context windows. This does not replace chunker bounds. |
|
|
30
|
+
| `PI_KNOWLEDGE_EMBEDDING_BATCH_SIZE` | `64` | Maximum number of document chunks sent in one embedding request during add, update, and import. Lower this for self-hosted embedding servers with smaller request batch limits. |
|
|
28
31
|
| `PI_KNOWLEDGE_EMBEDDING_API_FALLBACK` | unset | Set to `local` to explicitly fall back to local embeddings for query embeddings after API failures. Indexing/import/update document batches do not fall back because mixed-provider vector files are unsafe. |
|
|
29
32
|
| `PI_KNOWLEDGE_ENABLE_NATIVE_IDLE_DISPOSE` | unset | Enables idle timers for embedding/reranker run coordination. It does not guarantee immediate worker memory release; model-worker shutdown remains tied to engine/session shutdown. Disabled by default for stable shutdown. |
|
|
30
33
|
| `PI_KNOWLEDGE_EMBEDDING_IDLE_MS` | `30000` | Idle timer used only when native idle disposal coordination is enabled. Mainly for lifecycle stress tests. |
|
|
31
34
|
| `PI_KNOWLEDGE_OFFLINE` | unset | Use with a pre-populated model cache for offline local model operation. See `docs/offline-mode.md`. |
|
|
32
35
|
|
|
33
|
-
Each KB stores the embedding model label, vector dimension, and a non-secret embedding signature that includes provider/model semantics, query/document prefixes, pooling, normalization, API input cap, and a hash of the API base URL when applicable. `knowledge_search` skips vector retrieval for KBs whose stored signature or dimension is missing or incompatible with the current query embedding and uses BM25-only fallback for hybrid searches. Run `knowledge_update` to rebuild vectors after changing embedding provider/model/max-character settings or after upgrading older KBs with no signature metadata.
|
|
36
|
+
Each KB stores the embedding model label, vector dimension, and a non-secret embedding signature that includes provider/model semantics, query/document prefixes, non-default prefix strategy, pooling, normalization, API input cap, and a hash of the API base URL when applicable. `knowledge_search` skips vector retrieval for KBs whose stored signature or dimension is missing or incompatible with the current query embedding and uses BM25-only fallback for hybrid searches. Run `knowledge_update` to rebuild vectors after changing embedding provider/model/max-character/prefix settings or after upgrading older KBs with no signature metadata.
|
|
34
37
|
|
|
35
38
|
## Reranker
|
|
36
39
|
|
|
@@ -59,7 +62,7 @@ For Hugging Face Text Embeddings Inference rerankers, set `PI_KNOWLEDGE_RERANKER
|
|
|
59
62
|
|
|
60
63
|
Local embeddings require a real Node 22+ executable for the isolated model worker. `pi-knowledge` first tries Node IPC and automatically falls back to a stdin/stdout JSONL worker transport when the host runtime does not expose `child_process.fork().send()`, which can happen in Windows OMP compatibility layers. On Windows it searches `PI_KNOWLEDGE_NODE_PATH`, persisted `knowledge_configure` settings, common Node, Volta, NVM, Codex `cua_node`, and `PATH` locations before failing. If worker startup still fails, call `knowledge_configure` with the full `node.exe` path such as `C:\Program Files\nodejs\node.exe`; accidental surrounding quotes are ignored. OpenAI-compatible embeddings avoid the local worker entirely.
|
|
61
64
|
|
|
62
|
-
API embedding failures intentionally surface by default. Silent fallback can hide bad API keys, wrong base URLs, unsupported model names,
|
|
65
|
+
API embedding failures intentionally surface by default. Silent fallback can hide bad API keys, wrong base URLs, unsupported model names, context-window errors, or server batch limits and can produce a KB with a different embedding model than intended. Query-time fallback is opt-in; indexing fallback is disabled to prevent mixed vector spaces in one KB. OpenAI-compatible embedding requests send `Authorization: Bearer <key>` only when `PI_KNOWLEDGE_EMBEDDING_API_KEY` or `OPENAI_API_KEY` is configured.
|
|
63
66
|
|
|
64
67
|
## Runtime Features and Diagnostics
|
|
65
68
|
|
|
@@ -82,7 +85,7 @@ API embedding failures intentionally surface by default. Silent fallback can hid
|
|
|
82
85
|
|
|
83
86
|
Search diagnostics include result provenance and applied search tuning in both text output and structured `details`: selected profile, effective limit, snippet length, hybrid threshold, candidate pool size, chunk id, chunk hash, match reason, indexed timestamp, stale flag, and source mtime when the original source file is available. This provenance is stored in SQLite and derived from indexed source metadata; it does not create or modify files in the indexed project.
|
|
84
87
|
|
|
85
|
-
`knowledge_search` supports `file_type`, `path_pattern`, `profile`, and explicit `limit` filters. Search profiles tune result count, snippets, hybrid strictness, candidate breadth, adaptive context, and deep rerank breadth at runtime. `auto` chooses from query shape, mode, and KB source type; explicit tool parameters win over env overrides, env overrides win over profile defaults, and profile defaults win over built-in compatibility values. `hybrid` mode remains lexical-anchored to prevent low-evidence semantic false positives; use `semantic`
|
|
88
|
+
`knowledge_search` supports `file_type`, `path_pattern`, `profile`, and explicit `limit` filters. Search profiles tune result count, snippets, hybrid strictness, candidate breadth, adaptive context, and deep rerank breadth at runtime. `auto` chooses from query shape, mode, and KB source type; explicit tool parameters win over env overrides, env overrides win over profile defaults, and profile defaults win over built-in compatibility values. `hybrid` mode remains lexical-anchored to prevent low-evidence semantic false positives; use `semantic` for pure vector search, or `semantic_hybrid` when weak lexical overlap should not block vector-backed weighted fusion. `adaptive` uses bounded same-file context expansion; when AST metadata is present it can prefer same-parent/sibling chunks, but it remains metadata-driven context expansion rather than caller/callee analysis.
|
|
86
89
|
|
|
87
90
|
`knowledge_doctor` emits both human-readable issues and machine-readable actions in structured `details`. Action codes include `run_update`, `rebuild_kb`, `wait_for_indexing`, `review_skipped_scope`, `rebuild_vectors`, `check_source`, and `none`. Agents should prefer these action codes over parsing the English action text.
|
|
88
91
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "pi-knowledge",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.11.0",
|
|
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",
|