pageindex 0.2.10.dev4__tar.gz → 0.2.10.dev6__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.
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/PKG-INFO +3 -3
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/README.md +1 -1
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/__init__.py +3 -17
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/agent_tools.py +218 -162
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/client.py +194 -70
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/cloud_api.py +6 -4
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/config.yaml +2 -2
- pageindex-0.2.10.dev6/pageindex/errors.py +7 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/api.py +20 -6
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/embedded_toc.py +9 -3
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/char_extract.py +11 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/geometry.py +3 -1
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/pipeline.py +1 -1
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/unicode_apply.py +6 -10
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_parallel.py +31 -1
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/integrations/claude_agent_sdk.py +7 -9
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/integrations/openai_agents.py +2 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/local_api.py +45 -37
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/local_chat.py +263 -122
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/local_store.py +19 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/mcp_bridge.py +25 -8
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/page_index_classic.py +0 -1
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/tree_optimize.py +6 -4
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/utils.py +120 -63
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pyproject.toml +2 -2
- pageindex-0.2.10.dev4/pageindex/errors.py +0 -2
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/LICENSE +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/_version.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/README.md +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/blocks/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/blocks/build.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/blocks/join_rules.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/classification/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/classification/body_text.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/classification/header_footer.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/classification/keyword_tables.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/classification/toc_boilerplate.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/clustering/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/clustering/build.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/clustering/merge_rules.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/columns/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/columns/gutters.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/columns/splitting.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/data/boilerplate_phrases.json +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/data/dictionaries.json +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/data/glyph_name_table.json +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/data/normalized_unicodes.json +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/data/script_bucket_table.json +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/heading_detection/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/heading_detection/candidates.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/heading_detection/detectors.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/heading_detection/keyword_tables.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/heading_detection/neighbors.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/heading_detection/page_scan.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/heading_detection/style_detectors.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/heading_detection/text_checks.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/labels/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/labels/caption_regions.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/labels/caption_text.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/main.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/model/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/model/block.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/model/char_stats.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/model/numbering.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/model/rects.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/model/span_line.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/outline/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/outline/filtering.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/outline/tree.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/outline_assembly/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/outline_assembly/assembly.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/outline_assembly/candidates.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/outline_assembly/cliques.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/outline_assembly/selection.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/outline_assembly/style_context.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/cmap_parse.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/code_walk.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/content_stream.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/font_unicode.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/glyph_tables.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/merge.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/pdf_objects.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/remerge.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/parser_pdfium_charlevel/text_normalize.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/phases/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/phases/line_numbers.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/phases/page_view.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/stats/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/stats/aggregates.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/stats/scripts.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/title/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/title/detect.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/title/dicts.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/title/scoring.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/tokens/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/tokens/hashing.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/tokens/token_types.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/tokens/tokenizer.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/flash/tokens/tries.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/integrations/__init__.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/integrations/anthropic_sdk.py +0 -0
- {pageindex-0.2.10.dev4 → pageindex-0.2.10.dev6}/pageindex/page_index_md.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: pageindex
|
|
3
|
-
Version: 0.2.10.
|
|
3
|
+
Version: 0.2.10.dev6
|
|
4
4
|
Summary: Python SDK for PageIndex — reasoning-based, vectorless document retrieval, cloud and local
|
|
5
5
|
License: MIT
|
|
6
6
|
License-File: LICENSE
|
|
@@ -27,7 +27,7 @@ Requires-Dist: claude-agent-sdk (>=0.1.53) ; extra == "claude"
|
|
|
27
27
|
Requires-Dist: litellm (>=1.97.0)
|
|
28
28
|
Requires-Dist: openai (>=1.70.0)
|
|
29
29
|
Requires-Dist: openai-agents (>=0.18.1)
|
|
30
|
-
Requires-Dist: pypdfium2 (>=
|
|
30
|
+
Requires-Dist: pypdfium2 (>=5)
|
|
31
31
|
Requires-Dist: python-dotenv (>=1.0.0)
|
|
32
32
|
Requires-Dist: pyyaml (>=6.0)
|
|
33
33
|
Requires-Dist: regex (>=2024.0.0)
|
|
@@ -214,7 +214,7 @@ python3 run_pageindex.py --pdf_path /path/to/your/document.pdf
|
|
|
214
214
|
<details>
|
|
215
215
|
<summary>Optional parameters</summary>
|
|
216
216
|
<br>
|
|
217
|
-
You can customize the processing with additional optional arguments (the structure-tuning flags
|
|
217
|
+
You can customize the processing with additional optional arguments (the structure-tuning flags from <code>--toc-check-pages</code> down require <code>--mode standard</code>):
|
|
218
218
|
|
|
219
219
|
```
|
|
220
220
|
--mode Processing mode: flash (default) or standard
|
|
@@ -173,7 +173,7 @@ python3 run_pageindex.py --pdf_path /path/to/your/document.pdf
|
|
|
173
173
|
<details>
|
|
174
174
|
<summary>Optional parameters</summary>
|
|
175
175
|
<br>
|
|
176
|
-
You can customize the processing with additional optional arguments (the structure-tuning flags
|
|
176
|
+
You can customize the processing with additional optional arguments (the structure-tuning flags from <code>--toc-check-pages</code> down require <code>--mode standard</code>):
|
|
177
177
|
|
|
178
178
|
```
|
|
179
179
|
--mode Processing mode: flash (default) or standard
|
|
@@ -1,11 +1,6 @@
|
|
|
1
1
|
"""PageIndex SDK."""
|
|
2
|
-
import os as _os
|
|
3
2
|
from typing import TYPE_CHECKING as _TYPE_CHECKING
|
|
4
3
|
|
|
5
|
-
# LiteLLM's import otherwise fetches its model map over the network — seconds
|
|
6
|
-
# of blocking (or a hang offline). setdefault, so an explicit user choice wins.
|
|
7
|
-
_os.environ.setdefault("LITELLM_LOCAL_MODEL_COST_MAP", "True")
|
|
8
|
-
|
|
9
4
|
from .client import PageIndexClient, PageIndexCloudClient, PageIndexLocalClient
|
|
10
5
|
from .errors import PageIndexAPIError
|
|
11
6
|
|
|
@@ -23,8 +18,6 @@ __all__ = [
|
|
|
23
18
|
]
|
|
24
19
|
|
|
25
20
|
_LAZY = {
|
|
26
|
-
"page_index": ".page_index_classic",
|
|
27
|
-
"page_index_main": ".page_index_classic",
|
|
28
21
|
"page_index_flash": ".flash",
|
|
29
22
|
"optimize_tree": ".tree_optimize",
|
|
30
23
|
"md_to_tree": ".page_index_md",
|
|
@@ -34,25 +27,18 @@ _SUBMODULES = {"agent_tools", "client", "cloud_api", "errors", "flash",
|
|
|
34
27
|
"mcp_bridge", "page_index_classic", "page_index_md",
|
|
35
28
|
"tree_optimize", "utils"}
|
|
36
29
|
|
|
30
|
+
|
|
37
31
|
def __getattr__(name):
|
|
38
32
|
if name.startswith("_"):
|
|
39
|
-
# Dunder probes (copy, pickle, inspect) are the frequent unknown
|
|
40
|
-
# names — they must not trigger the classic import below.
|
|
41
33
|
raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
|
|
42
34
|
import importlib
|
|
43
35
|
if name in _SUBMODULES:
|
|
44
36
|
return importlib.import_module(f".{name}", __name__)
|
|
45
|
-
|
|
46
|
-
# whose public surface (ConfigLoader, count_tokens, ...) resolved as
|
|
47
|
-
# package attributes. A non-underscore typo pays one classic import
|
|
48
|
-
# before its AttributeError — not worth an allowlist.
|
|
49
|
-
module = importlib.import_module(_LAZY.get(name, ".page_index_classic"),
|
|
50
|
-
__name__)
|
|
37
|
+
module = importlib.import_module(_LAZY.get(name, ".page_index_classic"), __name__)
|
|
51
38
|
try:
|
|
52
39
|
value = getattr(module, name)
|
|
53
40
|
except AttributeError:
|
|
54
|
-
raise AttributeError(
|
|
55
|
-
f"module {__name__!r} has no attribute {name!r}") from None
|
|
41
|
+
raise AttributeError(f"module {__name__!r} has no attribute {name!r}") from None
|
|
56
42
|
globals()[name] = value
|
|
57
43
|
return value
|
|
58
44
|
|