docs2vecs/docs/readme/sample-config-file-3.yml at 2e56a46c73225039c7739c2af2738479df20194c · dpomian/docs2vecs · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
definitions:
  - skill: &ScrollHTMLExporter
      type: exporter
      name: scrollhtml-exporter
      params:
        api_url: https://scroll-html.de.exporter.k15t.app/api/public/1/exports
        auth_token: env.SCROLL_HTML_EXPORTER_TOKEN
        poll_interval: 2
        export_folder: ~/Downloads/html_export
        scope: current
        confluence_prefix: https://amadeus.atlassian.net/wiki
        page_ids:
          - id: 1436680207

  - skill: &HtmlToMarkdown
      type: transformer
      name: confluence-html-to-markdown
      params:
        input_dir: ~/Downloads/html_export/1436680207
        output_dir: ~/Downloads/html_export/1436680207/markdown

  - skill: &FileScanner
      type: file-scanner
      name: multi-file-scanner
      params:
        path: ~/Downloads/html_export/1436680207/markdown
        filter: ["*.md"]
        recursive: false

  - skill: &FileReader
      type: file-reader
      name: multi-file-reader

  - skill: &TextSplitter
      type: splitter
      name: recursive-character-splitter
      params:
        chunk_size: 1200
        overlap: 200

  - skill: &FastEmbed
      type: embedding
      name: llama-fastembed

  - skill: &ChromaDbVectorStore
      type: vector-store
      name: chromadb
      params:
        db_path: ~/Downloads/html_export/chroma_db
        collection_name: confluence-html-export

  - skillset: &Pipeline
      - *ScrollHTMLExporter
      - *HtmlToMarkdown
      - *FileScanner
      - *FileReader
      - *TextSplitter
      - *FastEmbed
      - *ChromaDbVectorStore

indexer:
  id: confluence-html-to-vectorstore
  skillset: *Pipeline