datasinking 0.2.8__tar.gz → 0.2.9__tar.gz

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.
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: datasinking
3
- Version: 0.2.8
3
+ Version: 0.2.9
4
4
  Summary: Python client for DataSinking — full-text Asian financial reports (China, Korea, Japan, Taiwan) as Markdown.
5
5
  Author: DataSinking
6
6
  License: MIT
@@ -31,27 +31,58 @@ Dynamic: license-file
31
31
  **Full-text financial reports across Asia, as clean Markdown.**
32
32
 
33
33
  [DataSinking](https://datasink.ing) serves **full-text financial reports** — annual, semi-annual
34
- and quarterly — from **China, Korea and Japan** as clean **Markdown**, ready for LLM reading
35
- and RAG. Query by FMP-style symbol (`600519.SS`, `005930.KS`, `7203.T`) or filter by exchange,
36
- report period, or **section** — pull just the MD&A / risk section instead of the whole report.
37
- Reports are sourced from official disclosure platforms and parsed into structured Markdown with
38
- YAML frontmatter, preserved headings, paragraphs and tables.
34
+ and quarterly — from **China, Korea, Japan and Taiwan** as clean **Markdown**, ready for LLM reading
35
+ and RAG. Query by FMP-style symbol (`600519.SS`, `005930.KS`, `7203.T`, `2330.TW`) or filter by
36
+ exchange, report period, or **section** — pull just the MD&A / risk section instead of the whole
37
+ report. Reports are sourced from official disclosure platforms and parsed into structured Markdown
38
+ with YAML frontmatter, preserved headings, paragraphs and tables.
39
39
 
40
40
  ---
41
41
 
42
42
  ## MCP server
43
43
 
44
- Ship DataSinking to any AI agent (Claude Desktop / Cursor / Codex / Windsurf) as an
44
+ Ship DataSinking to any AI agent (Claude / Cursor / Codex / Windsurf) as an
45
45
  [MCP](https://modelcontextprotocol.io) server — 6 tools: list exchanges, list stocks,
46
46
  list reports, fetch a report, list sections, fetch one section (token-friendly for RAG).
47
47
 
48
+ ### Hosted — nothing to install
49
+
50
+ Point any MCP client at our endpoint and you're done. No package, no Python, no local server:
51
+
52
+ ```json
53
+ {
54
+ "mcpServers": {
55
+ "datasinking": {
56
+ "type": "http",
57
+ "url": "https://api.datasink.ing/mcp?apikey=YOUR_KEY"
58
+ }
59
+ }
60
+ }
61
+ ```
62
+
63
+ Claude Code, in one line:
64
+
65
+ ```bash
66
+ claude mcp add --transport http datasinking https://api.datasink.ing/mcp \
67
+ --header "Authorization: Bearer YOUR_KEY"
68
+ ```
69
+
70
+ Your key rides inside the URL, so treat that config as a secret. Clients that support custom
71
+ headers can send `Authorization: Bearer YOUR_KEY` instead — Claude Code redacts headers in its
72
+ output but can't redact a URL.
73
+
74
+ ### Local — run it yourself
75
+
76
+ If you'd rather keep everything on your own machine:
77
+
48
78
  ```bash
49
79
  pip install "datasinking[mcp]"
50
80
  datasinking-mcp # requires DATASINK_API_KEY (free at https://datasink.ing)
51
81
  ```
52
82
 
53
- Or add to your client with `command: datasinking-mcp`. A remote streamable-HTTP endpoint
54
- is also live at `https://api.datasink.ing/mcp`. See [`mcp-server.md`](mcp-server.md).
83
+ Then use `command: datasinking-mcp` in your client.
84
+
85
+ Full per-client setup: [`mcp-server.md`](mcp-server.md).
55
86
 
56
87
  ![DataSinking MCP in Claude](docs/images/mcp-demo.png)
57
88
 
@@ -8,27 +8,58 @@
8
8
  **Full-text financial reports across Asia, as clean Markdown.**
9
9
 
10
10
  [DataSinking](https://datasink.ing) serves **full-text financial reports** — annual, semi-annual
11
- and quarterly — from **China, Korea and Japan** as clean **Markdown**, ready for LLM reading
12
- and RAG. Query by FMP-style symbol (`600519.SS`, `005930.KS`, `7203.T`) or filter by exchange,
13
- report period, or **section** — pull just the MD&A / risk section instead of the whole report.
14
- Reports are sourced from official disclosure platforms and parsed into structured Markdown with
15
- YAML frontmatter, preserved headings, paragraphs and tables.
11
+ and quarterly — from **China, Korea, Japan and Taiwan** as clean **Markdown**, ready for LLM reading
12
+ and RAG. Query by FMP-style symbol (`600519.SS`, `005930.KS`, `7203.T`, `2330.TW`) or filter by
13
+ exchange, report period, or **section** — pull just the MD&A / risk section instead of the whole
14
+ report. Reports are sourced from official disclosure platforms and parsed into structured Markdown
15
+ with YAML frontmatter, preserved headings, paragraphs and tables.
16
16
 
17
17
  ---
18
18
 
19
19
  ## MCP server
20
20
 
21
- Ship DataSinking to any AI agent (Claude Desktop / Cursor / Codex / Windsurf) as an
21
+ Ship DataSinking to any AI agent (Claude / Cursor / Codex / Windsurf) as an
22
22
  [MCP](https://modelcontextprotocol.io) server — 6 tools: list exchanges, list stocks,
23
23
  list reports, fetch a report, list sections, fetch one section (token-friendly for RAG).
24
24
 
25
+ ### Hosted — nothing to install
26
+
27
+ Point any MCP client at our endpoint and you're done. No package, no Python, no local server:
28
+
29
+ ```json
30
+ {
31
+ "mcpServers": {
32
+ "datasinking": {
33
+ "type": "http",
34
+ "url": "https://api.datasink.ing/mcp?apikey=YOUR_KEY"
35
+ }
36
+ }
37
+ }
38
+ ```
39
+
40
+ Claude Code, in one line:
41
+
42
+ ```bash
43
+ claude mcp add --transport http datasinking https://api.datasink.ing/mcp \
44
+ --header "Authorization: Bearer YOUR_KEY"
45
+ ```
46
+
47
+ Your key rides inside the URL, so treat that config as a secret. Clients that support custom
48
+ headers can send `Authorization: Bearer YOUR_KEY` instead — Claude Code redacts headers in its
49
+ output but can't redact a URL.
50
+
51
+ ### Local — run it yourself
52
+
53
+ If you'd rather keep everything on your own machine:
54
+
25
55
  ```bash
26
56
  pip install "datasinking[mcp]"
27
57
  datasinking-mcp # requires DATASINK_API_KEY (free at https://datasink.ing)
28
58
  ```
29
59
 
30
- Or add to your client with `command: datasinking-mcp`. A remote streamable-HTTP endpoint
31
- is also live at `https://api.datasink.ing/mcp`. See [`mcp-server.md`](mcp-server.md).
60
+ Then use `command: datasinking-mcp` in your client.
61
+
62
+ Full per-client setup: [`mcp-server.md`](mcp-server.md).
32
63
 
33
64
  ![DataSinking MCP in Claude](docs/images/mcp-demo.png)
34
65
 
@@ -8,4 +8,4 @@ pyproject.toml 用 `dynamic = ["version"]` 从这里读,`client.py` 的 User-A
8
8
  写着旧版本)。现在只有这一处需要改。
9
9
  """
10
10
 
11
- __version__ = "0.2.8"
11
+ __version__ = "0.2.9"
@@ -2,7 +2,7 @@
2
2
  """DataSinking MCP server (Model Context Protocol).
3
3
 
4
4
  Expose the DataSinking API — full-text financial reports across Asia
5
- (China, Korea, Japan) as clean Markdown — to AI agents (Claude, Cursor,
5
+ (China, Korea, Japan, Taiwan) as clean Markdown — to AI agents (Claude, Cursor,
6
6
  Codex, DeepSeek, Windsurf, …).
7
7
 
8
8
  Install the MCP extra::
@@ -127,10 +127,15 @@ def get_report(
127
127
  def list_sections(
128
128
  document_id: Annotated[int, Field(description="Report id, from list_reports items[].id")],
129
129
  ) -> dict:
130
- """List every section heading in a report (feed the headings to get_section).
130
+ """List every section of a report with its size call this before pulling anything.
131
131
 
132
- Call this before get_section to see the exact headings — the headings are in the
133
- report's own language.
132
+ Returns ``sections`` (titles, in order) plus ``section_details``: the same list as
133
+ objects with ``title``, ``has_tables``, ``chars`` and ``estimated_tokens``.
134
+
135
+ Use ``estimated_tokens`` to avoid pulling a chapter that would blow your context,
136
+ and ``has_tables`` to know whether a chapter needs special handling (tables are the
137
+ part RAG pipelines usually get wrong). Then call get_section with a heading keyword —
138
+ the headings are in the report's own language.
134
139
  """
135
140
  return _get(f"/documents/{document_id}/sections")
136
141
 
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: datasinking
3
- Version: 0.2.8
3
+ Version: 0.2.9
4
4
  Summary: Python client for DataSinking — full-text Asian financial reports (China, Korea, Japan, Taiwan) as Markdown.
5
5
  Author: DataSinking
6
6
  License: MIT
@@ -31,27 +31,58 @@ Dynamic: license-file
31
31
  **Full-text financial reports across Asia, as clean Markdown.**
32
32
 
33
33
  [DataSinking](https://datasink.ing) serves **full-text financial reports** — annual, semi-annual
34
- and quarterly — from **China, Korea and Japan** as clean **Markdown**, ready for LLM reading
35
- and RAG. Query by FMP-style symbol (`600519.SS`, `005930.KS`, `7203.T`) or filter by exchange,
36
- report period, or **section** — pull just the MD&A / risk section instead of the whole report.
37
- Reports are sourced from official disclosure platforms and parsed into structured Markdown with
38
- YAML frontmatter, preserved headings, paragraphs and tables.
34
+ and quarterly — from **China, Korea, Japan and Taiwan** as clean **Markdown**, ready for LLM reading
35
+ and RAG. Query by FMP-style symbol (`600519.SS`, `005930.KS`, `7203.T`, `2330.TW`) or filter by
36
+ exchange, report period, or **section** — pull just the MD&A / risk section instead of the whole
37
+ report. Reports are sourced from official disclosure platforms and parsed into structured Markdown
38
+ with YAML frontmatter, preserved headings, paragraphs and tables.
39
39
 
40
40
  ---
41
41
 
42
42
  ## MCP server
43
43
 
44
- Ship DataSinking to any AI agent (Claude Desktop / Cursor / Codex / Windsurf) as an
44
+ Ship DataSinking to any AI agent (Claude / Cursor / Codex / Windsurf) as an
45
45
  [MCP](https://modelcontextprotocol.io) server — 6 tools: list exchanges, list stocks,
46
46
  list reports, fetch a report, list sections, fetch one section (token-friendly for RAG).
47
47
 
48
+ ### Hosted — nothing to install
49
+
50
+ Point any MCP client at our endpoint and you're done. No package, no Python, no local server:
51
+
52
+ ```json
53
+ {
54
+ "mcpServers": {
55
+ "datasinking": {
56
+ "type": "http",
57
+ "url": "https://api.datasink.ing/mcp?apikey=YOUR_KEY"
58
+ }
59
+ }
60
+ }
61
+ ```
62
+
63
+ Claude Code, in one line:
64
+
65
+ ```bash
66
+ claude mcp add --transport http datasinking https://api.datasink.ing/mcp \
67
+ --header "Authorization: Bearer YOUR_KEY"
68
+ ```
69
+
70
+ Your key rides inside the URL, so treat that config as a secret. Clients that support custom
71
+ headers can send `Authorization: Bearer YOUR_KEY` instead — Claude Code redacts headers in its
72
+ output but can't redact a URL.
73
+
74
+ ### Local — run it yourself
75
+
76
+ If you'd rather keep everything on your own machine:
77
+
48
78
  ```bash
49
79
  pip install "datasinking[mcp]"
50
80
  datasinking-mcp # requires DATASINK_API_KEY (free at https://datasink.ing)
51
81
  ```
52
82
 
53
- Or add to your client with `command: datasinking-mcp`. A remote streamable-HTTP endpoint
54
- is also live at `https://api.datasink.ing/mcp`. See [`mcp-server.md`](mcp-server.md).
83
+ Then use `command: datasinking-mcp` in your client.
84
+
85
+ Full per-client setup: [`mcp-server.md`](mcp-server.md).
55
86
 
56
87
  ![DataSinking MCP in Claude](docs/images/mcp-demo.png)
57
88
 
File without changes
File without changes
File without changes