indian-address-parser 0.1.0__tar.gz

indian_address_parser-0.1.0/.gitignore

@@ -0,0 +1,7 @@
+__pycache__/
+*.pyc
+.pytest_cache/
+dist/
+build/
+*.egg-info/
+.venv/

indian_address_parser-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

indian_address_parser-0.1.0/PKG-INFO

@@ -0,0 +1,100 @@
+Metadata-Version: 2.4
+Name: indian-address-parser
+Version: 0.1.0
+Summary: Parse raw Indian address strings into structured fields using a fine-tuned Qwen3 LoRA adapter
+Project-URL: Homepage, https://github.com/innerkorehq/indian-address-parser
+Project-URL: Repository, https://github.com/innerkorehq/indian-address-parser
+Project-URL: Model, https://huggingface.co/gagan1985/qwen3-0.6b-indian-address-parser
+Author: Gagandeep
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: address-parsing,india,lora,named-entity-recognition,nlp,qwen
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.9
+Requires-Dist: huggingface-hub>=0.25.0
+Requires-Dist: peft>=0.12.0
+Requires-Dist: torch>=2.0.0
+Requires-Dist: transformers>=4.45.0
+Provides-Extra: test
+Requires-Dist: pytest>=7.0.0; extra == 'test'
+Description-Content-Type: text/markdown
+
+# indian-address-parser
+
+Parse raw, unstructured Indian address strings into 13 structured fields using a
+Qwen3-0.6B model fine-tuned with LoRA. Model weights are downloaded automatically from
+[Hugging Face](https://huggingface.co/gagan1985/qwen3-0.6b-indian-address-parser) — this
+package ships only inference code, no weights.
+
+```
+Input:  "FLAT NO.32, UTTARA TOWERS, MG ROAD GUWAHATI , Kamrup Unclassified AS 781029"
+Output: {"houseNumber": "FLAT NO.32", "houseName": "UTTARA TOWERS", "poi": null,
+         "street": "MG ROAD", "subsubLocality": null, "subLocality": null, "locality": null,
+         "village": null, "subDistrict": null, "district": "Kamrup", "city": "GUWAHATI",
+         "state": "AS", "pincode": "781029"}
+```
+
+## Install
+
+```bash
+pip install indian-address-parser
+```
+
+## Usage
+
+### Python
+
+```python
+from indian_address_parser import AddressParser
+
+parser = AddressParser()  # downloads model weights from HF on first use
+result = parser.parse("FLAT NO.32, UTTARA TOWERS, MG ROAD GUWAHATI , Kamrup Unclassified AS 781029")
+print(result)
+
+# Batch
+results = parser.parse_batch([addr1, addr2, addr3])
+```
+
+### CLI
+
+```bash
+# Single address
+indian-address-parser "FLAT NO.32, UTTARA TOWERS, MG ROAD GUWAHATI , Kamrup Unclassified AS 781029"
+
+# Batch from stdin
+cat addresses.txt | indian-address-parser --stdin
+
+# Batch from a file, JSONL output
+indian-address-parser --file addresses.txt --out results.jsonl
+```
+
+## Fields
+
+```
+houseNumber, houseName, poi, street, subsubLocality, subLocality,
+locality, village, subDistrict, district, city, state, pincode
+```
+
+Any field not present in the address is `null`. If the model output can't be parsed as
+JSON, all fields are `null` and a `_parse_error` key holds the raw model output.
+
+## Model details, evaluation metrics, and known limitations
+
+See the [model card](https://huggingface.co/gagan1985/qwen3-0.6b-indian-address-parser)
+for training data, LoRA config, per-field evaluation results (100% JSON parse rate, 82.4%
+mean field accuracy on held-out test data), and known limitations (locality/subLocality/
+subsubLocality/village field-boundary ambiguity, etc.).
+
+## Apple Silicon (MLX) users
+
+This package uses `transformers`+`peft`, which works on CUDA, MPS, and CPU but is not the
+fastest path on Apple Silicon. For MLX-native inference, see the `mlx/` subfolder of the
+[Hugging Face repo](https://huggingface.co/gagan1985/qwen3-0.6b-indian-address-parser/tree/main/mlx)
+instead.
+
+## License
+
+Apache 2.0 (matching the base model, Qwen/Qwen3-0.6B).

indian_address_parser-0.1.0/README.md

@@ -0,0 +1,76 @@
+# indian-address-parser
+
+Parse raw, unstructured Indian address strings into 13 structured fields using a
+Qwen3-0.6B model fine-tuned with LoRA. Model weights are downloaded automatically from
+[Hugging Face](https://huggingface.co/gagan1985/qwen3-0.6b-indian-address-parser) — this
+package ships only inference code, no weights.
+
+```
+Input:  "FLAT NO.32, UTTARA TOWERS, MG ROAD GUWAHATI , Kamrup Unclassified AS 781029"
+Output: {"houseNumber": "FLAT NO.32", "houseName": "UTTARA TOWERS", "poi": null,
+         "street": "MG ROAD", "subsubLocality": null, "subLocality": null, "locality": null,
+         "village": null, "subDistrict": null, "district": "Kamrup", "city": "GUWAHATI",
+         "state": "AS", "pincode": "781029"}
+```
+
+## Install
+
+```bash
+pip install indian-address-parser
+```
+
+## Usage
+
+### Python
+
+```python
+from indian_address_parser import AddressParser
+
+parser = AddressParser()  # downloads model weights from HF on first use
+result = parser.parse("FLAT NO.32, UTTARA TOWERS, MG ROAD GUWAHATI , Kamrup Unclassified AS 781029")
+print(result)
+
+# Batch
+results = parser.parse_batch([addr1, addr2, addr3])
+```
+
+### CLI
+
+```bash
+# Single address
+indian-address-parser "FLAT NO.32, UTTARA TOWERS, MG ROAD GUWAHATI , Kamrup Unclassified AS 781029"
+
+# Batch from stdin
+cat addresses.txt | indian-address-parser --stdin
+
+# Batch from a file, JSONL output
+indian-address-parser --file addresses.txt --out results.jsonl
+```
+
+## Fields
+
+```
+houseNumber, houseName, poi, street, subsubLocality, subLocality,
+locality, village, subDistrict, district, city, state, pincode
+```
+
+Any field not present in the address is `null`. If the model output can't be parsed as
+JSON, all fields are `null` and a `_parse_error` key holds the raw model output.
+
+## Model details, evaluation metrics, and known limitations
+
+See the [model card](https://huggingface.co/gagan1985/qwen3-0.6b-indian-address-parser)
+for training data, LoRA config, per-field evaluation results (100% JSON parse rate, 82.4%
+mean field accuracy on held-out test data), and known limitations (locality/subLocality/
+subsubLocality/village field-boundary ambiguity, etc.).
+
+## Apple Silicon (MLX) users
+
+This package uses `transformers`+`peft`, which works on CUDA, MPS, and CPU but is not the
+fastest path on Apple Silicon. For MLX-native inference, see the `mlx/` subfolder of the
+[Hugging Face repo](https://huggingface.co/gagan1985/qwen3-0.6b-indian-address-parser/tree/main/mlx)
+instead.
+
+## License
+
+Apache 2.0 (matching the base model, Qwen/Qwen3-0.6B).

indian_address_parser-0.1.0/pyproject.toml

@@ -0,0 +1,44 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "indian-address-parser"
+version = "0.1.0"
+description = "Parse raw Indian address strings into structured fields using a fine-tuned Qwen3 LoRA adapter"
+readme = "README.md"
+license = "Apache-2.0"
+requires-python = ">=3.9"
+authors = [
+    { name = "Gagandeep" }
+]
+keywords = ["nlp", "address-parsing", "india", "named-entity-recognition", "lora", "qwen"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: OS Independent",
+    "Topic :: Text Processing :: Linguistic",
+]
+dependencies = [
+    "torch>=2.0.0",
+    "transformers>=4.45.0",
+    "peft>=0.12.0",
+    "huggingface_hub>=0.25.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/innerkorehq/indian-address-parser"
+Repository = "https://github.com/innerkorehq/indian-address-parser"
+Model = "https://huggingface.co/gagan1985/qwen3-0.6b-indian-address-parser"
+
+[project.scripts]
+indian-address-parser = "indian_address_parser.cli:main"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/indian_address_parser"]
+
+[tool.pytest.ini_options]
+markers = ["slow: requires network access, downloads real model weights"]
+
+[project.optional-dependencies]
+test = ["pytest>=7.0.0"]

indian_address_parser-0.1.0/src/indian_address_parser/__init__.py

@@ -0,0 +1,4 @@
+from .parser import ALL_FIELDS, DEFAULT_ADAPTER_REPO, DEFAULT_BASE_MODEL, SYSTEM_PROMPT, AddressParser
+
+__all__ = ["AddressParser", "ALL_FIELDS", "SYSTEM_PROMPT", "DEFAULT_ADAPTER_REPO", "DEFAULT_BASE_MODEL"]
+__version__ = "0.1.0"

indian_address_parser-0.1.0/src/indian_address_parser/cli.py

@@ -0,0 +1,56 @@
+"""CLI for indian-address-parser.
+
+Usage:
+    indian-address-parser "FLAT NO.32, UTTARA TOWERS, MG ROAD GUWAHATI , Kamrup Unclassified AS 781029"
+    cat addresses.txt | indian-address-parser --stdin
+    indian-address-parser --file addresses.txt --out results.jsonl
+"""
+from __future__ import annotations
+
+import argparse
+import json
+import sys
+
+from .parser import DEFAULT_ADAPTER_REPO, DEFAULT_BASE_MODEL, AddressParser
+
+
+def main():
+    p = argparse.ArgumentParser(description="Parse Indian addresses into structured fields")
+    p.add_argument("address", nargs="?", help="Single address to parse")
+    p.add_argument("--stdin", action="store_true", help="Read addresses from stdin, one per line")
+    p.add_argument("--file", help="Read addresses from a text file, one per line")
+    p.add_argument("--out", help="Write JSONL output to file (default: stdout)")
+    p.add_argument("--adapter-repo", default=DEFAULT_ADAPTER_REPO, help="HF Hub repo for the LoRA adapter")
+    p.add_argument("--base-model", default=DEFAULT_BASE_MODEL, help="HF Hub repo for the base model")
+    args = p.parse_args()
+
+    if args.address:
+        addresses = [args.address]
+    elif args.stdin:
+        addresses = [line.rstrip("\n") for line in sys.stdin if line.strip()]
+    elif args.file:
+        with open(args.file, encoding="utf-8") as f:
+            addresses = [line.rstrip("\n") for line in f if line.strip()]
+    else:
+        p.print_help()
+        return
+
+    parser = AddressParser(adapter_repo=args.adapter_repo, base_model=args.base_model)
+
+    out_f = open(args.out, "w", encoding="utf-8") if args.out else None
+    for addr in addresses:
+        result = parser.parse(addr)
+        result["_raw_address"] = addr
+        line = json.dumps(result, ensure_ascii=False)
+        if out_f:
+            out_f.write(line + "\n")
+        else:
+            print(line)
+
+    if out_f:
+        out_f.close()
+        print(f"Wrote {len(addresses):,} results to {args.out}", file=sys.stderr)
+
+
+if __name__ == "__main__":
+    main()

indian_address_parser-0.1.0/src/indian_address_parser/parser.py

@@ -0,0 +1,118 @@
+"""Core AddressParser class.
+
+Loads a LoRA adapter from Hugging Face Hub on top of a base Qwen3 model and parses
+raw Indian address strings into structured fields. Model tensors are always fetched
+from the Hugging Face repo (default: gagan1985/qwen3-0.6b-indian-address-parser) —
+this package ships only inference code, no weights.
+"""
+from __future__ import annotations
+
+import json
+
+DEFAULT_ADAPTER_REPO = "gagan1985/qwen3-0.6b-indian-address-parser"
+DEFAULT_BASE_MODEL = "Qwen/Qwen3-0.6B"
+
+ALL_FIELDS = (
+    "houseNumber",
+    "houseName",
+    "poi",
+    "street",
+    "subsubLocality",
+    "subLocality",
+    "locality",
+    "village",
+    "subDistrict",
+    "district",
+    "city",
+    "state",
+    "pincode",
+)
+
+SYSTEM_PROMPT = (
+    "You are an Indian address parser. Given a raw address string, extract address "
+    "fields and return them as a JSON object. Use null for fields not present in the "
+    "address. Output only the JSON object, no explanation.\n\n"
+    "Fields: " + ", ".join(ALL_FIELDS)
+)
+
+USER_TEMPLATE = "Parse this address:\n{raw_address}"
+
+
+class AddressParser:
+    """Parses raw Indian address strings into 13 structured fields.
+
+    Example:
+        >>> parser = AddressParser()
+        >>> parser.parse("FLAT NO.32, UTTARA TOWERS, MG ROAD GUWAHATI , Kamrup Unclassified AS 781029")
+        {'houseNumber': 'FLAT NO.32', 'houseName': 'UTTARA TOWERS', 'poi': None, ...}
+    """
+
+    def __init__(
+        self,
+        adapter_repo: str = DEFAULT_ADAPTER_REPO,
+        base_model: str = DEFAULT_BASE_MODEL,
+        device: str | None = None,
+        max_new_tokens: int = 256,
+    ):
+        import torch
+        from peft import PeftModel
+        from transformers import AutoModelForCausalLM, AutoTokenizer
+
+        self.max_new_tokens = max_new_tokens
+        self.tokenizer = AutoTokenizer.from_pretrained(adapter_repo)
+
+        dtype = torch.float32
+        if device is None:
+            if torch.cuda.is_available():
+                device = "cuda"
+                dtype = torch.bfloat16
+            elif torch.backends.mps.is_available():
+                device = "mps"
+                dtype = torch.float16
+            else:
+                device = "cpu"
+
+        base = AutoModelForCausalLM.from_pretrained(base_model, torch_dtype=dtype)
+        self.model = PeftModel.from_pretrained(base, adapter_repo)
+        self.model.to(device)
+        self.model.eval()
+        self.device = device
+
+    def parse(self, raw_address: str) -> dict:
+        """Parse a single raw address string. Returns a dict with all 13 ALL_FIELDS
+        keys (null for fields not present). On generation output that isn't valid
+        JSON, all fields are null and `_parse_error` holds the raw model output."""
+        import torch
+
+        messages = [
+            {"role": "system", "content": SYSTEM_PROMPT},
+            {"role": "user", "content": USER_TEMPLATE.format(raw_address=raw_address)},
+        ]
+        try:
+            text = self.tokenizer.apply_chat_template(
+                messages, tokenize=False, add_generation_prompt=True, enable_thinking=False
+            )
+        except TypeError:
+            text = self.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+        inputs = self.tokenizer(text, return_tensors="pt").to(self.device)
+        with torch.no_grad():
+            out = self.model.generate(
+                **inputs,
+                max_new_tokens=self.max_new_tokens,
+                do_sample=False,
+                pad_token_id=self.tokenizer.eos_token_id,
+            )
+        generated = self.tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
+
+        try:
+            result = json.loads(generated.strip())
+            result = {f: result.get(f) for f in ALL_FIELDS}
+        except json.JSONDecodeError:
+            result = {f: None for f in ALL_FIELDS}
+            result["_parse_error"] = generated.strip()
+        return result
+
+    def parse_batch(self, addresses: list[str]) -> list[dict]:
+        """Parse multiple addresses sequentially. See `parse` for the per-item shape."""
+        return [self.parse(addr) for addr in addresses]

indian_address_parser-0.1.0/tests/test_parser.py

@@ -0,0 +1,45 @@
+"""Tests for indian_address_parser.
+
+test_import_and_constants runs offline. test_parse_real_address actually downloads
+the model from HF Hub and runs real inference — slow (~1-2 min) and requires network,
+but is the only way to verify the package genuinely works end to end.
+"""
+import json
+
+import pytest
+
+
+def test_import_and_constants():
+    from indian_address_parser import ALL_FIELDS, DEFAULT_ADAPTER_REPO, DEFAULT_BASE_MODEL, SYSTEM_PROMPT
+
+    assert len(ALL_FIELDS) == 13
+    assert "pincode" in ALL_FIELDS
+    assert DEFAULT_ADAPTER_REPO == "gagan1985/qwen3-0.6b-indian-address-parser"
+    assert DEFAULT_BASE_MODEL == "Qwen/Qwen3-0.6B"
+    assert "Fields:" in SYSTEM_PROMPT
+
+
+@pytest.mark.slow
+def test_parse_real_address():
+    from indian_address_parser import AddressParser
+
+    parser = AddressParser()
+    result = parser.parse("FLAT NO.32, UTTARA TOWERS, MG ROAD GUWAHATI , Kamrup Unclassified AS 781029")
+
+    assert result["houseNumber"] == "FLAT NO.32"
+    assert result["houseName"] == "UTTARA TOWERS"
+    assert result["pincode"] == "781029"
+    assert "_parse_error" not in result
+
+
+@pytest.mark.slow
+def test_parse_batch():
+    from indian_address_parser import AddressParser
+
+    parser = AddressParser()
+    results = parser.parse_batch([
+        "FLAT NO.32, UTTARA TOWERS, MG ROAD GUWAHATI , Kamrup Unclassified AS 781029",
+        "SHOP NO 5, GANDHI MARKET, NEAR CIVIL HOSPITAL, SILCHAR , Cachar Unclassified AS 788001",
+    ])
+    assert len(results) == 2
+    assert all(json.dumps(r) for r in results)  # each is JSON-serializable