sparrow-parse 0.3.3__py3-none-any.whl → 0.3.4__py3-none-any.whl

sparrow_parse/__init__.py

@@ -1 +1 @@
-__version__ = '0.3.3'
+__version__ = '0.3.4'

{sparrow_parse-0.3.3.dist-info → sparrow_parse-0.3.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sparrow-parse
-Version: 0.3.3
+Version: 0.3.4
 Summary: Sparrow Parse is a Python package for parsing and extracting information from documents.
 Home-page: https://github.com/katanaml/sparrow/tree/main/sparrow-data/parse
 Author: Andrej Baranovskij
@@ -98,6 +98,8 @@ Example:
 
 ## Parsing and extraction
 
+### HTML extractor
+
 ```
 from sparrow_parse.extractor.html_extractor import HTMLExtractor
 
@@ -130,6 +132,36 @@ Example:
 
 *debug* - `True`
 
+### Sparrow Parse VL (vision-language) extractor
+
+```
+extractor = VLLMExtractor()
+
+# export HF_TOKEN="hf_"
+config = {
+    "method": "huggingface",  # Could be 'huggingface' or 'local_gpu'
+    "hf_space": "katanaml/sparrow-qwen2-vl-7b",
+    "hf_token": os.getenv('HF_TOKEN'),
+    # Additional fields for local GPU inference
+    # "device": "cuda", "model_path": "model.pth"
+}
+
+# Use the factory to get the correct instance
+factory = InferenceFactory(config)
+model_inference_instance = factory.get_inference_instance()
+
+input_data = [
+    {
+        "image": "/Users/andrejb/Documents/work/epik/bankstatement/bonds_table.png",
+        "text_input": "retrieve financial instruments data. return response in JSON format"
+    }
+]
+
+# Now you can run inference without knowing which implementation is used
+result = extractor.run_inference(model_inference_instance, input_data, generic_query=False, debug=True)
+print("Inference Result:", result)
+```
+
 ## PDF optimization
 
 ```

{sparrow_parse-0.3.3.dist-info → sparrow_parse-0.3.4.dist-info}/RECORD

@@ -1,4 +1,4 @@
-sparrow_parse/__init__.py,sha256=JDRpXqOC0txw4_CqkfpSl89CczeXGgyjX4XSSLChyQg,21
+sparrow_parse/__init__.py,sha256=SH0xuWVUkyLHZJwWBZ8GJoeliTeYFcqA6TWJgrkLv-U,21
 sparrow_parse/__main__.py,sha256=Xs1bpJV0n08KWOoQE34FBYn6EBXZA9HIYJKrE4ZdG78,153
 sparrow_parse/temp.py,sha256=gy4_mtNW_KfXn9br_suu6jHx7JKYLKs9pIOBynh_JWY,1134
 sparrow_parse/extractors/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -16,8 +16,8 @@ sparrow_parse/vllm/huggingface_inference.py,sha256=Q2Ju65LDzbO-8RWW7cXzrR-pbZ1zK
 sparrow_parse/vllm/inference_base.py,sha256=W0N2khehGdF1XHzZACG3I1UZaydHMk6BZgWNvaJD4Ck,197
 sparrow_parse/vllm/inference_factory.py,sha256=r04e95uPWG5l8Q23yeDqKmvFxLyF991aA2m0hfBTNn8,993
 sparrow_parse/vllm/local_gpu_inference.py,sha256=I_uWYiFAQhRrykOKbVz69NzftDxuemDKtAye4kWhtnU,617
-sparrow_parse-0.3.3.dist-info/METADATA,sha256=qFl4MsoV6lF_OqgtcfBqDRpTHX8MUJh0jeGgNr77o8w,6482
-sparrow_parse-0.3.3.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-sparrow_parse-0.3.3.dist-info/entry_points.txt,sha256=8CrvTVTTcz1YuZ8aRCYNOH15ZOAaYLlcbYX3t28HwJY,54
-sparrow_parse-0.3.3.dist-info/top_level.txt,sha256=n6b-WtT91zKLyCPZTP7wvne8v_yvIahcsz-4sX8I0rY,14
-sparrow_parse-0.3.3.dist-info/RECORD,,
+sparrow_parse-0.3.4.dist-info/METADATA,sha256=L7qXKxktk42gUQlBlZAdzHQqfORoC6vBwRCd-VSwv3Y,7444
+sparrow_parse-0.3.4.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+sparrow_parse-0.3.4.dist-info/entry_points.txt,sha256=8CrvTVTTcz1YuZ8aRCYNOH15ZOAaYLlcbYX3t28HwJY,54
+sparrow_parse-0.3.4.dist-info/top_level.txt,sha256=n6b-WtT91zKLyCPZTP7wvne8v_yvIahcsz-4sX8I0rY,14
+sparrow_parse-0.3.4.dist-info/RECORD,,