structx 0.4.10__tar.gz → 0.4.11__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.
- {structx-0.4.10/structx.egg-info → structx-0.4.11}/PKG-INFO +15 -15
- {structx-0.4.10 → structx-0.4.11}/README.md +13 -13
- {structx-0.4.10 → structx-0.4.11}/pyproject.toml +3 -3
- {structx-0.4.10 → structx-0.4.11}/structx/__init__.py +1 -1
- {structx-0.4.10 → structx-0.4.11}/structx/extraction/processors/data_content.py +3 -3
- {structx-0.4.10 → structx-0.4.11/structx.egg-info}/PKG-INFO +15 -15
- {structx-0.4.10 → structx-0.4.11}/LICENSE +0 -0
- {structx-0.4.10 → structx-0.4.11}/setup.cfg +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/core/__init__.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/core/config.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/core/exceptions.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/core/models.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/extraction/__init__.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/extraction/core/__init__.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/extraction/core/llm_core.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/extraction/core/model_utils.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/extraction/engines/__init__.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/extraction/engines/extraction_engine.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/extraction/extractor.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/extraction/generator.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/extraction/processors/__init__.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/extraction/processors/model_operations.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/extraction/result_manager.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/utils/__init__.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/utils/constants.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/utils/file_reader.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/utils/helpers.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/utils/prompts.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/utils/types.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx/utils/usage.py +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx.egg-info/SOURCES.txt +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx.egg-info/dependency_links.txt +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx.egg-info/requires.txt +0 -0
- {structx-0.4.10 → structx-0.4.11}/structx.egg-info/top_level.txt +0 -0
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: structx
|
|
3
|
-
Version: 0.4.
|
|
3
|
+
Version: 0.4.11
|
|
4
4
|
Summary: Structured data extraction from text using LLMs and dynamic model generation
|
|
5
|
-
Author-email: blacksuan19 <py@
|
|
5
|
+
Author-email: blacksuan19 <py@aolabs.dev>
|
|
6
6
|
Classifier: Development Status :: 5 - Production/Stable
|
|
7
7
|
Classifier: Framework :: AsyncIO
|
|
8
8
|
Classifier: Framework :: Pydantic
|
|
@@ -90,8 +90,8 @@ Dynamic: license-file
|
|
|
90
90
|
Advanced structured data extraction from any document using LLMs with multimodal
|
|
91
91
|
support.
|
|
92
92
|
|
|
93
|
-
[](https://structx.
|
|
94
|
-
[](https://structx.aolabs.dev "Documentation")
|
|
94
|
+
[](https://pypi.org/project/structx "Package")
|
|
95
95
|
[](# "Build with GitHub Actions")
|
|
96
96
|
|
|
97
97
|
`structx` is a powerful Python library for extracting structured data from any
|
|
@@ -260,20 +260,20 @@ traditional text-based extraction:
|
|
|
260
260
|
## 📚 Documentation
|
|
261
261
|
|
|
262
262
|
For comprehensive documentation, examples, and guides, visit our
|
|
263
|
-
[documentation site](https://structx.
|
|
263
|
+
[documentation site](https://structx.aolabs.dev).
|
|
264
264
|
|
|
265
|
-
- [Getting Started](https://structx.
|
|
266
|
-
- [Basic Extraction](https://structx.
|
|
267
|
-
- [Unstructured Text Processing](https://structx.
|
|
268
|
-
- [Async Operations](https://structx.
|
|
269
|
-
- [Multiple Queries](https://structx.
|
|
270
|
-
- [Custom Models](https://structx.
|
|
271
|
-
- [Token Usage Tracking](https://structx.
|
|
272
|
-
- [API Reference](https://structx.
|
|
265
|
+
- [Getting Started](https://structx.aolabs.dev/getting-started)
|
|
266
|
+
- [Basic Extraction](https://structx.aolabs.dev/guides/basic-extraction)
|
|
267
|
+
- [Unstructured Text Processing](https://structx.aolabs.dev/guides/unstructured-text)
|
|
268
|
+
- [Async Operations](https://structx.aolabs.dev/guides/async-operations)
|
|
269
|
+
- [Multiple Queries](https://structx.aolabs.dev/guides/multiple-queries)
|
|
270
|
+
- [Custom Models](https://structx.aolabs.dev/guides/custom-models)
|
|
271
|
+
- [Token Usage Tracking](https://structx.aolabs.dev/guides/token-tracking)
|
|
272
|
+
- [API Reference](https://structx.aolabs.dev/api/extractor)
|
|
273
273
|
|
|
274
274
|
## Examples
|
|
275
275
|
|
|
276
|
-
Check out our [example gallery](https://structx.
|
|
276
|
+
Check out our [example gallery](https://structx.aolabs.dev/examples) for
|
|
277
277
|
real-world use cases,
|
|
278
278
|
|
|
279
279
|
## 📁 Supported File Formats
|
|
@@ -304,7 +304,7 @@ real-world use cases,
|
|
|
304
304
|
## Contributing
|
|
305
305
|
|
|
306
306
|
Contributions are welcome! Please read our
|
|
307
|
-
[Contributing Guidelines](https://structx.
|
|
307
|
+
[Contributing Guidelines](https://structx.aolabs.dev/contributing) for
|
|
308
308
|
details.
|
|
309
309
|
|
|
310
310
|
## License
|
|
@@ -3,8 +3,8 @@
|
|
|
3
3
|
Advanced structured data extraction from any document using LLMs with multimodal
|
|
4
4
|
support.
|
|
5
5
|
|
|
6
|
-
[](https://structx.
|
|
7
|
-
[](https://structx.aolabs.dev "Documentation")
|
|
7
|
+
[](https://pypi.org/project/structx "Package")
|
|
8
8
|
[](# "Build with GitHub Actions")
|
|
9
9
|
|
|
10
10
|
`structx` is a powerful Python library for extracting structured data from any
|
|
@@ -173,20 +173,20 @@ traditional text-based extraction:
|
|
|
173
173
|
## 📚 Documentation
|
|
174
174
|
|
|
175
175
|
For comprehensive documentation, examples, and guides, visit our
|
|
176
|
-
[documentation site](https://structx.
|
|
176
|
+
[documentation site](https://structx.aolabs.dev).
|
|
177
177
|
|
|
178
|
-
- [Getting Started](https://structx.
|
|
179
|
-
- [Basic Extraction](https://structx.
|
|
180
|
-
- [Unstructured Text Processing](https://structx.
|
|
181
|
-
- [Async Operations](https://structx.
|
|
182
|
-
- [Multiple Queries](https://structx.
|
|
183
|
-
- [Custom Models](https://structx.
|
|
184
|
-
- [Token Usage Tracking](https://structx.
|
|
185
|
-
- [API Reference](https://structx.
|
|
178
|
+
- [Getting Started](https://structx.aolabs.dev/getting-started)
|
|
179
|
+
- [Basic Extraction](https://structx.aolabs.dev/guides/basic-extraction)
|
|
180
|
+
- [Unstructured Text Processing](https://structx.aolabs.dev/guides/unstructured-text)
|
|
181
|
+
- [Async Operations](https://structx.aolabs.dev/guides/async-operations)
|
|
182
|
+
- [Multiple Queries](https://structx.aolabs.dev/guides/multiple-queries)
|
|
183
|
+
- [Custom Models](https://structx.aolabs.dev/guides/custom-models)
|
|
184
|
+
- [Token Usage Tracking](https://structx.aolabs.dev/guides/token-tracking)
|
|
185
|
+
- [API Reference](https://structx.aolabs.dev/api/extractor)
|
|
186
186
|
|
|
187
187
|
## Examples
|
|
188
188
|
|
|
189
|
-
Check out our [example gallery](https://structx.
|
|
189
|
+
Check out our [example gallery](https://structx.aolabs.dev/examples) for
|
|
190
190
|
real-world use cases,
|
|
191
191
|
|
|
192
192
|
## 📁 Supported File Formats
|
|
@@ -217,7 +217,7 @@ real-world use cases,
|
|
|
217
217
|
## Contributing
|
|
218
218
|
|
|
219
219
|
Contributions are welcome! Please read our
|
|
220
|
-
[Contributing Guidelines](https://structx.
|
|
220
|
+
[Contributing Guidelines](https://structx.aolabs.dev/contributing) for
|
|
221
221
|
details.
|
|
222
222
|
|
|
223
223
|
## License
|
|
@@ -4,9 +4,9 @@ build-backend = "setuptools.build_meta"
|
|
|
4
4
|
|
|
5
5
|
[project]
|
|
6
6
|
name = "structx"
|
|
7
|
-
version = "0.4.
|
|
7
|
+
version = "0.4.11"
|
|
8
8
|
description = "Structured data extraction from text using LLMs and dynamic model generation"
|
|
9
|
-
authors = [{ name = "blacksuan19", email = "py@
|
|
9
|
+
authors = [{ name = "blacksuan19", email = "py@aolabs.dev" }]
|
|
10
10
|
license-files = ["LICENSE"]
|
|
11
11
|
readme = "README.md"
|
|
12
12
|
requires-python = ">=3.10"
|
|
@@ -94,7 +94,7 @@ mkdocs = [
|
|
|
94
94
|
]
|
|
95
95
|
|
|
96
96
|
[tool.bumpver]
|
|
97
|
-
current_version = "0.4.
|
|
97
|
+
current_version = "0.4.11"
|
|
98
98
|
version_pattern = "MAJOR.MINOR.PATCH"
|
|
99
99
|
commit_message = "Bump version {old_version} -> {new_version}"
|
|
100
100
|
commit = true
|
|
@@ -94,12 +94,12 @@ class ContentAnalyzer:
|
|
|
94
94
|
try:
|
|
95
95
|
# Check if this is a file-based row
|
|
96
96
|
if "pdf_path" in row and pd.notna(row["pdf_path"]):
|
|
97
|
-
# For PDF files, extract text sample using
|
|
97
|
+
# For PDF files, extract text sample using PyPDF2
|
|
98
98
|
try:
|
|
99
|
-
import
|
|
99
|
+
import PyPDF2
|
|
100
100
|
|
|
101
101
|
with open(row["pdf_path"], "rb") as file:
|
|
102
|
-
reader =
|
|
102
|
+
reader = PyPDF2.PdfReader(file)
|
|
103
103
|
text = ""
|
|
104
104
|
# Extract from first few pages
|
|
105
105
|
for page_num in range(min(3, len(reader.pages))):
|
|
@@ -1,8 +1,8 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: structx
|
|
3
|
-
Version: 0.4.
|
|
3
|
+
Version: 0.4.11
|
|
4
4
|
Summary: Structured data extraction from text using LLMs and dynamic model generation
|
|
5
|
-
Author-email: blacksuan19 <py@
|
|
5
|
+
Author-email: blacksuan19 <py@aolabs.dev>
|
|
6
6
|
Classifier: Development Status :: 5 - Production/Stable
|
|
7
7
|
Classifier: Framework :: AsyncIO
|
|
8
8
|
Classifier: Framework :: Pydantic
|
|
@@ -90,8 +90,8 @@ Dynamic: license-file
|
|
|
90
90
|
Advanced structured data extraction from any document using LLMs with multimodal
|
|
91
91
|
support.
|
|
92
92
|
|
|
93
|
-
[](https://structx.
|
|
94
|
-
[](https://structx.aolabs.dev "Documentation")
|
|
94
|
+
[](https://pypi.org/project/structx "Package")
|
|
95
95
|
[](# "Build with GitHub Actions")
|
|
96
96
|
|
|
97
97
|
`structx` is a powerful Python library for extracting structured data from any
|
|
@@ -260,20 +260,20 @@ traditional text-based extraction:
|
|
|
260
260
|
## 📚 Documentation
|
|
261
261
|
|
|
262
262
|
For comprehensive documentation, examples, and guides, visit our
|
|
263
|
-
[documentation site](https://structx.
|
|
263
|
+
[documentation site](https://structx.aolabs.dev).
|
|
264
264
|
|
|
265
|
-
- [Getting Started](https://structx.
|
|
266
|
-
- [Basic Extraction](https://structx.
|
|
267
|
-
- [Unstructured Text Processing](https://structx.
|
|
268
|
-
- [Async Operations](https://structx.
|
|
269
|
-
- [Multiple Queries](https://structx.
|
|
270
|
-
- [Custom Models](https://structx.
|
|
271
|
-
- [Token Usage Tracking](https://structx.
|
|
272
|
-
- [API Reference](https://structx.
|
|
265
|
+
- [Getting Started](https://structx.aolabs.dev/getting-started)
|
|
266
|
+
- [Basic Extraction](https://structx.aolabs.dev/guides/basic-extraction)
|
|
267
|
+
- [Unstructured Text Processing](https://structx.aolabs.dev/guides/unstructured-text)
|
|
268
|
+
- [Async Operations](https://structx.aolabs.dev/guides/async-operations)
|
|
269
|
+
- [Multiple Queries](https://structx.aolabs.dev/guides/multiple-queries)
|
|
270
|
+
- [Custom Models](https://structx.aolabs.dev/guides/custom-models)
|
|
271
|
+
- [Token Usage Tracking](https://structx.aolabs.dev/guides/token-tracking)
|
|
272
|
+
- [API Reference](https://structx.aolabs.dev/api/extractor)
|
|
273
273
|
|
|
274
274
|
## Examples
|
|
275
275
|
|
|
276
|
-
Check out our [example gallery](https://structx.
|
|
276
|
+
Check out our [example gallery](https://structx.aolabs.dev/examples) for
|
|
277
277
|
real-world use cases,
|
|
278
278
|
|
|
279
279
|
## 📁 Supported File Formats
|
|
@@ -304,7 +304,7 @@ real-world use cases,
|
|
|
304
304
|
## Contributing
|
|
305
305
|
|
|
306
306
|
Contributions are welcome! Please read our
|
|
307
|
-
[Contributing Guidelines](https://structx.
|
|
307
|
+
[Contributing Guidelines](https://structx.aolabs.dev/contributing) for
|
|
308
308
|
details.
|
|
309
309
|
|
|
310
310
|
## License
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|