doc2vec 1.1.1 → 1.2.0
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/README.md +64 -11
- package/dist/content-processor.js +725 -0
- package/dist/database.js +507 -0
- package/dist/doc2vec.js +48 -1012
- package/dist/types.js +2 -0
- package/dist/utils.js +118 -0
- package/package.json +8 -2
- package/Dockerfile +0 -29
- package/config.yaml +0 -167
- package/doc2vec.ts +0 -1734
- package/logger.ts +0 -287
- package/mcp/Dockerfile +0 -14
- package/mcp/README.md +0 -166
- package/mcp/package-lock.json +0 -1754
- package/mcp/package.json +0 -41
- package/mcp/src/index.ts +0 -214
- package/mcp/tsconfig.json +0 -16
- package/tsconfig.json +0 -18
package/dist/types.js
ADDED
package/dist/utils.js
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
1
|
+
"use strict";
|
|
2
|
+
var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
|
|
3
|
+
if (k2 === undefined) k2 = k;
|
|
4
|
+
var desc = Object.getOwnPropertyDescriptor(m, k);
|
|
5
|
+
if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
|
|
6
|
+
desc = { enumerable: true, get: function() { return m[k]; } };
|
|
7
|
+
}
|
|
8
|
+
Object.defineProperty(o, k2, desc);
|
|
9
|
+
}) : (function(o, m, k, k2) {
|
|
10
|
+
if (k2 === undefined) k2 = k;
|
|
11
|
+
o[k2] = m[k];
|
|
12
|
+
}));
|
|
13
|
+
var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
|
|
14
|
+
Object.defineProperty(o, "default", { enumerable: true, value: v });
|
|
15
|
+
}) : function(o, v) {
|
|
16
|
+
o["default"] = v;
|
|
17
|
+
});
|
|
18
|
+
var __importStar = (this && this.__importStar) || (function () {
|
|
19
|
+
var ownKeys = function(o) {
|
|
20
|
+
ownKeys = Object.getOwnPropertyNames || function (o) {
|
|
21
|
+
var ar = [];
|
|
22
|
+
for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
|
|
23
|
+
return ar;
|
|
24
|
+
};
|
|
25
|
+
return ownKeys(o);
|
|
26
|
+
};
|
|
27
|
+
return function (mod) {
|
|
28
|
+
if (mod && mod.__esModule) return mod;
|
|
29
|
+
var result = {};
|
|
30
|
+
if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
|
|
31
|
+
__setModuleDefault(result, mod);
|
|
32
|
+
return result;
|
|
33
|
+
};
|
|
34
|
+
})();
|
|
35
|
+
var __importDefault = (this && this.__importDefault) || function (mod) {
|
|
36
|
+
return (mod && mod.__esModule) ? mod : { "default": mod };
|
|
37
|
+
};
|
|
38
|
+
Object.defineProperty(exports, "__esModule", { value: true });
|
|
39
|
+
exports.Utils = void 0;
|
|
40
|
+
const crypto_1 = __importDefault(require("crypto"));
|
|
41
|
+
const path = __importStar(require("path"));
|
|
42
|
+
class Utils {
|
|
43
|
+
static generateHash(content) {
|
|
44
|
+
return crypto_1.default.createHash("sha256").update(content).digest("hex");
|
|
45
|
+
}
|
|
46
|
+
static generateMetadataUUID(repo) {
|
|
47
|
+
// Simple deterministic approach - hash the repo name and convert to UUID format
|
|
48
|
+
const hash = crypto_1.default.createHash('md5').update(`metadata_${repo}`).digest('hex');
|
|
49
|
+
// Format as UUID with version bits set correctly (version 4)
|
|
50
|
+
return `${hash.substr(0, 8)}-${hash.substr(8, 4)}-4${hash.substr(13, 3)}-${hash.substr(16, 4)}-${hash.substr(20, 12)}`;
|
|
51
|
+
}
|
|
52
|
+
static getUrlPrefix(url) {
|
|
53
|
+
try {
|
|
54
|
+
const parsedUrl = new URL(url);
|
|
55
|
+
return parsedUrl.origin + parsedUrl.pathname;
|
|
56
|
+
}
|
|
57
|
+
catch (error) {
|
|
58
|
+
return url;
|
|
59
|
+
}
|
|
60
|
+
}
|
|
61
|
+
static normalizeUrl(url) {
|
|
62
|
+
try {
|
|
63
|
+
const urlObj = new URL(url);
|
|
64
|
+
urlObj.hash = '';
|
|
65
|
+
urlObj.search = '';
|
|
66
|
+
return urlObj.toString();
|
|
67
|
+
}
|
|
68
|
+
catch (error) {
|
|
69
|
+
return url;
|
|
70
|
+
}
|
|
71
|
+
}
|
|
72
|
+
static buildUrl(href, currentUrl) {
|
|
73
|
+
try {
|
|
74
|
+
return new URL(href, currentUrl).toString();
|
|
75
|
+
}
|
|
76
|
+
catch (error) {
|
|
77
|
+
console.warn(`Invalid URL found: ${href}`);
|
|
78
|
+
return '';
|
|
79
|
+
}
|
|
80
|
+
}
|
|
81
|
+
static shouldProcessUrl(url) {
|
|
82
|
+
const parsedUrl = new URL(url);
|
|
83
|
+
const pathname = parsedUrl.pathname;
|
|
84
|
+
const ext = path.extname(pathname);
|
|
85
|
+
if (!ext)
|
|
86
|
+
return true;
|
|
87
|
+
return ['.html', '.htm', '.pdf'].includes(ext.toLowerCase());
|
|
88
|
+
}
|
|
89
|
+
static isPdfUrl(url) {
|
|
90
|
+
try {
|
|
91
|
+
const parsedUrl = new URL(url);
|
|
92
|
+
const pathname = parsedUrl.pathname;
|
|
93
|
+
const ext = path.extname(pathname);
|
|
94
|
+
return ext.toLowerCase() === '.pdf';
|
|
95
|
+
}
|
|
96
|
+
catch (error) {
|
|
97
|
+
return false;
|
|
98
|
+
}
|
|
99
|
+
}
|
|
100
|
+
static isValidUuid(str) {
|
|
101
|
+
const uuidRegex = /^[0-9a-f]{8}-[0-9a-f]{4}-[1-5][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}$/i;
|
|
102
|
+
return uuidRegex.test(str);
|
|
103
|
+
}
|
|
104
|
+
static hashToUuid(hash) {
|
|
105
|
+
const truncatedHash = hash.substring(0, 32);
|
|
106
|
+
return [
|
|
107
|
+
truncatedHash.substring(0, 8),
|
|
108
|
+
truncatedHash.substring(8, 12),
|
|
109
|
+
'5' + truncatedHash.substring(13, 16),
|
|
110
|
+
'8' + truncatedHash.substring(17, 20),
|
|
111
|
+
truncatedHash.substring(20, 32)
|
|
112
|
+
].join('-');
|
|
113
|
+
}
|
|
114
|
+
static tokenize(text) {
|
|
115
|
+
return text.split(/(\s+)/).filter(token => token.length > 0);
|
|
116
|
+
}
|
|
117
|
+
}
|
|
118
|
+
exports.Utils = Utils;
|
package/package.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "doc2vec",
|
|
3
|
-
"version": "1.
|
|
3
|
+
"version": "1.2.0",
|
|
4
4
|
"type": "commonjs",
|
|
5
5
|
"description": "",
|
|
6
|
-
"main": "doc2vec.
|
|
6
|
+
"main": "dist/doc2vec.js",
|
|
7
7
|
"private": false,
|
|
8
8
|
"publishConfig": {
|
|
9
9
|
"access": "public"
|
|
@@ -11,6 +11,11 @@
|
|
|
11
11
|
"bin": {
|
|
12
12
|
"doc2vec": "dist/doc2vec.js"
|
|
13
13
|
},
|
|
14
|
+
"files": [
|
|
15
|
+
"dist/",
|
|
16
|
+
"README.md",
|
|
17
|
+
"LICENSE"
|
|
18
|
+
],
|
|
14
19
|
"scripts": {
|
|
15
20
|
"build": "tsc && chmod 755 dist/doc2vec.js",
|
|
16
21
|
"start": "node dist/doc2vec.js",
|
|
@@ -32,6 +37,7 @@
|
|
|
32
37
|
"js-yaml": "^4.1.0",
|
|
33
38
|
"jsdom": "^26.0.0",
|
|
34
39
|
"openai": "^4.20.1",
|
|
40
|
+
"pdfjs-dist": "^5.3.31",
|
|
35
41
|
"puppeteer": "^24.1.1",
|
|
36
42
|
"sanitize-html": "^2.11.0",
|
|
37
43
|
"sqlite-vec": "0.1.7-alpha.2",
|
package/Dockerfile
DELETED
|
@@ -1,29 +0,0 @@
|
|
|
1
|
-
FROM node:20-slim
|
|
2
|
-
|
|
3
|
-
WORKDIR /app
|
|
4
|
-
|
|
5
|
-
RUN apt-get update && apt-get install -y \
|
|
6
|
-
git \
|
|
7
|
-
python3 \
|
|
8
|
-
make \
|
|
9
|
-
g++ \
|
|
10
|
-
sqlite3 \
|
|
11
|
-
libsqlite3-dev \
|
|
12
|
-
curl \
|
|
13
|
-
ca-certificates \
|
|
14
|
-
chromium \
|
|
15
|
-
fonts-freefont-ttf \
|
|
16
|
-
fonts-ipafont-gothic \
|
|
17
|
-
fonts-kacst \
|
|
18
|
-
fonts-liberation \
|
|
19
|
-
fonts-noto-color-emoji \
|
|
20
|
-
fonts-thai-tlwg \
|
|
21
|
-
libx11-xcb1 \
|
|
22
|
-
libxcb-dri3-0 \
|
|
23
|
-
libxcomposite1 \
|
|
24
|
-
libxdamage1 \
|
|
25
|
-
libxi6 \
|
|
26
|
-
libxrandr2 \
|
|
27
|
-
libxshmfence1 \
|
|
28
|
-
libxtst6 \
|
|
29
|
-
&& apt-get clean
|
package/config.yaml
DELETED
|
@@ -1,167 +0,0 @@
|
|
|
1
|
-
# Doc2Vec Configuration
|
|
2
|
-
sources:
|
|
3
|
-
# GitHub Sources
|
|
4
|
-
- type: github
|
|
5
|
-
product_name: 'istio'
|
|
6
|
-
version: 'latest'
|
|
7
|
-
repo: 'istio/istio'
|
|
8
|
-
start_date: '2025-01-01'
|
|
9
|
-
max_size: 1048576
|
|
10
|
-
database_config:
|
|
11
|
-
type: 'sqlite'
|
|
12
|
-
params:
|
|
13
|
-
db_path: './istio-issues.db'
|
|
14
|
-
|
|
15
|
-
# Website Sources
|
|
16
|
-
- type: website
|
|
17
|
-
product_name: 'ambient'
|
|
18
|
-
version: 'latest'
|
|
19
|
-
url: 'https://ambientmesh.io/docs/'
|
|
20
|
-
max_size: 1048576
|
|
21
|
-
database_config:
|
|
22
|
-
type: 'sqlite'
|
|
23
|
-
params:
|
|
24
|
-
db_path: './ambient.db'
|
|
25
|
-
|
|
26
|
-
- type: website
|
|
27
|
-
product_name: 'argo'
|
|
28
|
-
version: 'latest'
|
|
29
|
-
url: 'https://argo-cd.readthedocs.io/en/stable/'
|
|
30
|
-
max_size: 1048576
|
|
31
|
-
database_config:
|
|
32
|
-
type: 'sqlite'
|
|
33
|
-
params:
|
|
34
|
-
db_path: './argo.db'
|
|
35
|
-
|
|
36
|
-
- type: website
|
|
37
|
-
product_name: 'argo-rollouts'
|
|
38
|
-
version: 'latest'
|
|
39
|
-
url: 'https://argoproj.github.io/argo-rollouts/installation/'
|
|
40
|
-
max_size: 1048576
|
|
41
|
-
database_config:
|
|
42
|
-
type: 'sqlite'
|
|
43
|
-
params:
|
|
44
|
-
db_path: './argo-rollouts.db'
|
|
45
|
-
|
|
46
|
-
- type: website
|
|
47
|
-
product_name: 'argo-rollouts'
|
|
48
|
-
version: 'latest'
|
|
49
|
-
url: 'https://rollouts-plugin-trafficrouter-gatewayapi.readthedocs.io/en/latest/'
|
|
50
|
-
max_size: 1048576
|
|
51
|
-
database_config:
|
|
52
|
-
type: 'sqlite'
|
|
53
|
-
params:
|
|
54
|
-
db_path: './argo-rollouts.db'
|
|
55
|
-
|
|
56
|
-
- type: website
|
|
57
|
-
product_name: 'cilium'
|
|
58
|
-
version: 'latest'
|
|
59
|
-
url: 'https://docs.cilium.io/en/stable/'
|
|
60
|
-
max_size: 1048576
|
|
61
|
-
database_config:
|
|
62
|
-
type: 'sqlite'
|
|
63
|
-
params:
|
|
64
|
-
db_path: './cilium.db'
|
|
65
|
-
|
|
66
|
-
- type: website
|
|
67
|
-
product_name: 'gateway-api'
|
|
68
|
-
version: 'latest'
|
|
69
|
-
url: 'https://gateway-api.sigs.k8s.io/'
|
|
70
|
-
max_size: 1048576
|
|
71
|
-
database_config:
|
|
72
|
-
type: 'sqlite'
|
|
73
|
-
params:
|
|
74
|
-
db_path: './gateway-api.db'
|
|
75
|
-
|
|
76
|
-
- type: website
|
|
77
|
-
product_name: 'gloo-mesh-core'
|
|
78
|
-
version: 'latest'
|
|
79
|
-
url: 'https://docs.solo.io/gloo-mesh/latest/'
|
|
80
|
-
sitemap_url: 'https://docs.solo.io/gloo-mesh/sitemap.xml'
|
|
81
|
-
max_size: 1048576
|
|
82
|
-
database_config:
|
|
83
|
-
type: 'sqlite'
|
|
84
|
-
params:
|
|
85
|
-
db_path: './gloo-mesh-core.db'
|
|
86
|
-
|
|
87
|
-
- type: website
|
|
88
|
-
product_name: 'gloo-mesh-enterprise'
|
|
89
|
-
version: 'latest'
|
|
90
|
-
url: 'https://docs.solo.io/gloo-mesh-enterprise/latest/'
|
|
91
|
-
sitemap_url: 'https://docs.solo.io/gloo-mesh-enterprise/sitemap.xml'
|
|
92
|
-
max_size: 1048576
|
|
93
|
-
database_config:
|
|
94
|
-
type: 'sqlite'
|
|
95
|
-
params:
|
|
96
|
-
db_path: './gloo-mesh-enterprise.db'
|
|
97
|
-
|
|
98
|
-
- type: website
|
|
99
|
-
product_name: 'gloo-edge'
|
|
100
|
-
version: 'latest'
|
|
101
|
-
url: 'https://docs.solo.io/gloo-edge/latest/'
|
|
102
|
-
max_size: 1048576
|
|
103
|
-
database_config:
|
|
104
|
-
type: 'sqlite'
|
|
105
|
-
params:
|
|
106
|
-
db_path: './gloo-edge.db'
|
|
107
|
-
|
|
108
|
-
- type: website
|
|
109
|
-
product_name: 'gloo-gateway'
|
|
110
|
-
version: 'latest'
|
|
111
|
-
url: 'https://docs.solo.io/gateway/latest/'
|
|
112
|
-
sitemap_url: 'https://docs.solo.io/gateway/sitemap.xml'
|
|
113
|
-
max_size: 1048576
|
|
114
|
-
database_config:
|
|
115
|
-
type: 'sqlite'
|
|
116
|
-
params:
|
|
117
|
-
db_path: './gloo-gateway.db'
|
|
118
|
-
|
|
119
|
-
- type: website
|
|
120
|
-
product_name: 'helm'
|
|
121
|
-
version: 'latest'
|
|
122
|
-
url: 'https://helm.sh/docs/'
|
|
123
|
-
max_size: 1048576
|
|
124
|
-
database_config:
|
|
125
|
-
type: 'sqlite'
|
|
126
|
-
params:
|
|
127
|
-
db_path: './helm.db'
|
|
128
|
-
|
|
129
|
-
- type: website
|
|
130
|
-
product_name: 'istio'
|
|
131
|
-
version: 'latest'
|
|
132
|
-
url: 'https://istio.io/latest/docs/'
|
|
133
|
-
max_size: 1048576
|
|
134
|
-
database_config:
|
|
135
|
-
type: 'sqlite'
|
|
136
|
-
params:
|
|
137
|
-
db_path: './istio.db'
|
|
138
|
-
|
|
139
|
-
- type: website
|
|
140
|
-
product_name: 'kubernetes'
|
|
141
|
-
version: 'latest'
|
|
142
|
-
url: 'https://kubernetes.io/docs/'
|
|
143
|
-
max_size: 1048576
|
|
144
|
-
database_config:
|
|
145
|
-
type: 'sqlite'
|
|
146
|
-
params:
|
|
147
|
-
db_path: './kubernetes.db'
|
|
148
|
-
|
|
149
|
-
- type: website
|
|
150
|
-
product_name: 'otel'
|
|
151
|
-
version: 'latest'
|
|
152
|
-
url: 'https://opentelemetry.io/docs/'
|
|
153
|
-
max_size: 1048576
|
|
154
|
-
database_config:
|
|
155
|
-
type: 'sqlite'
|
|
156
|
-
params:
|
|
157
|
-
db_path: './otel.db'
|
|
158
|
-
|
|
159
|
-
- type: website
|
|
160
|
-
product_name: 'prometheus'
|
|
161
|
-
version: 'latest'
|
|
162
|
-
url: 'https://prometheus.io/docs/'
|
|
163
|
-
max_size: 1048576
|
|
164
|
-
database_config:
|
|
165
|
-
type: 'sqlite'
|
|
166
|
-
params:
|
|
167
|
-
db_path: './prometheus.db'
|