qwksearch-api-client 0.0.11 → 0.0.13
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 +35 -39
- package/dist/api-client.js +1 -819
- package/dist/api-client.umd.cjs +1 -1
- package/package.json +12 -5
- package/dist/index.d.ts +0 -763
package/README.md
CHANGED
|
@@ -22,44 +22,6 @@ QwkSearch API provides three core services for AI-powered research and content a
|
|
|
22
22
|
2. **Language Generation** - Generate AI responses using multiple language model providers
|
|
23
23
|
3. **Web Search** - Search the web using metasearch engine across 100+ sources
|
|
24
24
|
|
|
25
|
-
## Base URL
|
|
26
|
-
|
|
27
|
-
```
|
|
28
|
-
https://qwksearch.com/api
|
|
29
|
-
```
|
|
30
|
-
|
|
31
|
-
## API Endpoints
|
|
32
|
-
|
|
33
|
-
### 1. Extract Content (`/extract`)
|
|
34
|
-
|
|
35
|
-
Extract structured content, citations, and metadata from any URL including articles, PDFs, and YouTube videos.
|
|
36
|
-
|
|
37
|
-
#### Features
|
|
38
|
-
|
|
39
|
-
- **Main Content Detection**: Combines Mozilla Readability and Postlight Mercury algorithms with 100+ custom adapters
|
|
40
|
-
- **HTML Standardization**: Transforms complex HTML into simplified reading-mode format
|
|
41
|
-
- **YouTube Transcripts**: Retrieves complete video transcripts with timestamps
|
|
42
|
-
- **PDF Processing**: Extracts formatted text and infers heading hierarchy
|
|
43
|
-
- **Citation Extraction**: Identifies author names, publication dates, sources, and titles
|
|
44
|
-
- **Author Formatting**: Validates against 90,000+ name database for proper citation formatting
|
|
45
|
-
|
|
46
|
-
#### Request
|
|
47
|
-
|
|
48
|
-
```http
|
|
49
|
-
GET /extract?url={url}&images={boolean}&links={boolean}
|
|
50
|
-
```
|
|
51
|
-
|
|
52
|
-
**Parameters:**
|
|
53
|
-
|
|
54
|
-
| Parameter | Type | Required | Default | Description |
|
|
55
|
-
|-----------|------|----------|---------|-------------|
|
|
56
|
-
| `url` | string (uri) | Yes | - | URL to extract content from |
|
|
57
|
-
| `images` | boolean | No | true | Include images in output |
|
|
58
|
-
| `links` | boolean | No | true | Include hyperlinks in output |
|
|
59
|
-
| `formatting` | boolean | No | true | Preserve text formatting |
|
|
60
|
-
| `absoluteURLs` | boolean | No | true | Convert relative URLs to absolute |
|
|
61
|
-
| `timeout` | integer | No | 5 | HTTP request timeout (1-30 seconds) |
|
|
62
|
-
|
|
63
25
|
|
|
64
26
|
|
|
65
27
|
## Complete Example: Research Pipeline
|
|
@@ -124,6 +86,40 @@ researchTopic('quantum computing applications')
|
|
|
124
86
|
|
|
125
87
|
---
|
|
126
88
|
|
|
89
|
+
|
|
90
|
+
## API Endpoints
|
|
91
|
+
|
|
92
|
+
### 1. Extract Content (`/extract`)
|
|
93
|
+
|
|
94
|
+
Extract structured content, citations, and metadata from any URL including articles, PDFs, and YouTube videos.
|
|
95
|
+
|
|
96
|
+
#### Features
|
|
97
|
+
|
|
98
|
+
- **Main Content Detection**: Combines Mozilla Readability and Postlight Mercury algorithms with 100+ custom adapters
|
|
99
|
+
- **HTML Standardization**: Transforms complex HTML into simplified reading-mode format
|
|
100
|
+
- **YouTube Transcripts**: Retrieves complete video transcripts with timestamps
|
|
101
|
+
- **PDF Processing**: Extracts formatted text and infers heading hierarchy
|
|
102
|
+
- **Citation Extraction**: Identifies author names, publication dates, sources, and titles
|
|
103
|
+
- **Author Formatting**: Validates against 90,000+ name database for proper citation formatting
|
|
104
|
+
|
|
105
|
+
#### Request
|
|
106
|
+
|
|
107
|
+
```http
|
|
108
|
+
GET /extract?url={url}&images={boolean}&links={boolean}
|
|
109
|
+
```
|
|
110
|
+
|
|
111
|
+
**Parameters:**
|
|
112
|
+
|
|
113
|
+
| Parameter | Type | Required | Default | Description |
|
|
114
|
+
|-----------|------|----------|---------|-------------|
|
|
115
|
+
| `url` | string (uri) | Yes | - | URL to extract content from |
|
|
116
|
+
| `images` | boolean | No | true | Include images in output |
|
|
117
|
+
| `links` | boolean | No | true | Include hyperlinks in output |
|
|
118
|
+
| `formatting` | boolean | No | true | Preserve text formatting |
|
|
119
|
+
| `absoluteURLs` | boolean | No | true | Convert relative URLs to absolute |
|
|
120
|
+
| `timeout` | integer | No | 5 | HTTP request timeout (1-30 seconds) |
|
|
121
|
+
|
|
122
|
+
|
|
127
123
|
### 2. Generate Language (`/agents`)
|
|
128
124
|
|
|
129
125
|
Generate AI responses using various language model providers with pre-built agent templates.
|
|
@@ -324,5 +320,5 @@ npm install qwksearch-api-client
|
|
|
324
320
|
- [Building Transformer Guide](https://www.datacamp.com/tutorial/building-a-transformer-with-py-torch)
|
|
325
321
|
- [PyTorch Overview](https://www.learnpytorch.io/pytorch_cheatsheet/)
|
|
326
322
|
- [SearXNG Overview](https://medium.com/@elmo92/search-in-peace-with--an-alternative-search-engine-that-keeps-your-searches-private-accd8cddd6fc)
|
|
327
|
-
|
|
323
|
+
- [Evaluating Large Language Models in Scientific Discovery](https://arxiv.org/pdf/2512.15567)
|
|
328
324
|
---
|