structflo-ner 0.5.0__tar.gz → 0.6.0__tar.gz

{structflo_ner-0.5.0 → structflo_ner-0.6.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.5
 Name: structflo-ner
-Version: 0.5.0
+Version: 0.6.0
 Summary: Drug discovery NER wrapper around LangExtract — zero-config entity extraction for chemistry and biology.
 License: Apache-2.0
 Requires-Python: >=3.10
@@ -347,6 +347,20 @@ df = result.to_dataframe()
 result.to_dict()
 ```
 
+Each bioactivity carries its measurement in `attributes`:
+
+| Attribute       | Example                     | Meaning                                                    |
+| --------------- | --------------------------- | ---------------------------------------------------------- |
+| `value`         | `>20.0`                     | number as reported, qualifier kept                         |
+| `unit`          | `µM`                        | unit as written                                            |
+| `assay_type`    | `CC50`                      | the endpoint (IC50, MIC90, GI50, ED90, ...)                |
+| `assay`         | `HepG2 MTT`                 | assay, cell line or read-out the value was measured in     |
+| `compound_name` | `8t`                        | compound the value belongs to                              |
+| `strain`        | `H37Rv`                     | organism or strain (`TB` profile only)                     |
+
+An attribute the text does not state comes back as the string `"None"` with
+providers that enforce a strict schema (OpenAI), or is absent otherwise.
+
 
 ## Notebooks
 

{structflo_ner-0.5.0 → structflo_ner-0.6.0}/README.md

@@ -334,6 +334,20 @@ df = result.to_dataframe()
 result.to_dict()
 ```
 
+Each bioactivity carries its measurement in `attributes`:
+
+| Attribute       | Example                     | Meaning                                                    |
+| --------------- | --------------------------- | ---------------------------------------------------------- |
+| `value`         | `>20.0`                     | number as reported, qualifier kept                         |
+| `unit`          | `µM`                        | unit as written                                            |
+| `assay_type`    | `CC50`                      | the endpoint (IC50, MIC90, GI50, ED90, ...)                |
+| `assay`         | `HepG2 MTT`                 | assay, cell line or read-out the value was measured in     |
+| `compound_name` | `8t`                        | compound the value belongs to                              |
+| `strain`        | `H37Rv`                     | organism or strain (`TB` profile only)                     |
+
+An attribute the text does not state comes back as the string `"None"` with
+providers that enforce a strict schema (OpenAI), or is absent otherwise.
+
 
 ## Notebooks
 

{structflo_ner-0.5.0 → structflo_ner-0.6.0}/structflo/ner/__init__.py

@@ -63,7 +63,7 @@ from structflo.ner.profiles import (
     EntityProfile,
 )
 
-__version__ = "0.5.0"
+__version__ = "0.6.0"
 
 __all__ = [
     # Main classes

{structflo_ner-0.5.0 → structflo_ner-0.6.0}/structflo/ner/_examples.py

@@ -158,8 +158,8 @@ BIOLOGY_EXAMPLES: list[lx.data.ExampleData] = [
 
 _BIOACTIVITY_EXAMPLE_1 = lx.data.ExampleData(
     text=(
-        "Compound 7 inhibited EGFR with an IC50 of 2.3 nM in a cell-free enzymatic assay "
-        "and showed an EC50 of 45 nM in A549 (human lung adenocarcinoma) cell proliferation assay. "
+        "Compound 7 (CHEMBL5171042) inhibited EGFR with an IC50 of 2.3 nM in a cell-free "
+        "enzymatic assay and showed an EC50 of 45 nM in A549 (human lung adenocarcinoma) cell proliferation assay. "
         "Selectivity over ERBB2 was >100-fold (Ki = 0.8 nM vs 95 nM)."
     ),
     extractions=[
@@ -170,7 +170,8 @@ _BIOACTIVITY_EXAMPLE_1 = lx.data.ExampleData(
                 "value": "2.3",
                 "unit": "nM",
                 "assay_type": "IC50",
-                "compound_name": "Compound 7",
+                "compound_name": "CHEMBL5171042",
+                "assay": "cell-free enzymatic assay",
             },
         ),
         lx.data.Extraction(
@@ -185,7 +186,8 @@ _BIOACTIVITY_EXAMPLE_1 = lx.data.ExampleData(
                 "value": "45",
                 "unit": "nM",
                 "assay_type": "EC50",
-                "compound_name": "Compound 7",
+                "compound_name": "CHEMBL5171042",
+                "assay": "A549 cell proliferation assay",
             },
         ),
         lx.data.Extraction(
@@ -204,7 +206,7 @@ _BIOACTIVITY_EXAMPLE_1 = lx.data.ExampleData(
                 "value": "0.8",
                 "unit": "nM",
                 "assay_type": "Ki",
-                "compound_name": "Compound 7",
+                "compound_name": "CHEMBL5171042",
             },
         ),
     ],
@@ -337,6 +339,7 @@ _FULL_EXAMPLE_1 = lx.data.ExampleData(
                 "unit": "µM",
                 "assay_type": "IC50",
                 "compound_name": "Gefitinib",
+                "assay": "cell-free biochemical assay",
             },
         ),
         lx.data.Extraction(
@@ -357,6 +360,7 @@ _FULL_EXAMPLE_1 = lx.data.ExampleData(
                 "unit": "µM",
                 "assay_type": "IC50",
                 "compound_name": "Gefitinib",
+                "assay": "A431 cells",
             },
         ),
         lx.data.Extraction(
@@ -449,6 +453,7 @@ _TB_EXAMPLE_1 = lx.data.ExampleData(
                 "assay_type": "MIC",
                 "strain": "H37Rv",
                 "compound_name": "Bedaquiline",
+                "assay": "MABA",
             },
         ),
         lx.data.Extraction(
@@ -619,6 +624,7 @@ _TB_EXAMPLE_3 = lx.data.ExampleData(
                 "unit": "nM",
                 "assay_type": "IC50",
                 "compound_name": "Compound 14a",
+                "assay": "biochemical assay",
             },
         ),
         lx.data.Extraction(
@@ -643,6 +649,7 @@ _TB_EXAMPLE_3 = lx.data.ExampleData(
                 "assay_type": "MIC90",
                 "strain": "H37Rv",
                 "compound_name": "Compound 14a",
+                "assay": "REMA",
             },
         ),
         lx.data.Extraction(
@@ -658,6 +665,7 @@ _TB_EXAMPLE_3 = lx.data.ExampleData(
                 "unit": "uM",
                 "assay_type": "EC50",
                 "compound_name": "Compound 14a",
+                "assay": "THP-1 macrophage infection assay",
             },
         ),
         lx.data.Extraction(
@@ -673,6 +681,7 @@ _TB_EXAMPLE_3 = lx.data.ExampleData(
                 "unit": "uM",
                 "assay_type": "MIC",
                 "compound_name": "Compound 14a",
+                "assay": "LORA",
             },
         ),
         lx.data.Extraction(
@@ -688,6 +697,7 @@ _TB_EXAMPLE_3 = lx.data.ExampleData(
                 "unit": "uM",
                 "assay_type": "CC50",
                 "compound_name": "Compound 14a",
+                "assay": "HepG2 cells",
             },
         ),
     ],
@@ -860,12 +870,123 @@ _TB_EXAMPLE_5 = lx.data.ExampleData(
     ],
 )
 
+# Table as Docling emits it: the column header names the assay, the endpoint
+# and unit come from the footnote, and every cell is its own bioactivity. The
+# ID column, not the deck-local row label, names the compound.
+_TB_EXAMPLE_6 = lx.data.ExampleData(
+    text=(
+        "Table 2. Whole-cell activity\n\n"
+        "| Cpd | ID | MABA | THP-1 | Vero |\n"
+        "| --- | --- | --- | --- | --- |\n"
+        "| 21a | SACC-4412 | 0.12 | 0.9 | >50 |\n"
+        "| 21b | CHEMBL5290347 | <0.03 | 2.4* | 18.5 |\n\n"
+        "MABA: MIC90 (µM) against M. tuberculosis H37Rv. THP-1: intracellular EC90 (µM). "
+        "Vero: CC50 (µM). *Single determination."
+    ),
+    extractions=[
+        lx.data.Extraction(
+            extraction_class="assay",
+            extraction_text="MABA",
+            attributes={"assay_format": "whole-cell", "strain": "H37Rv"},
+        ),
+        lx.data.Extraction(
+            extraction_class="assay",
+            extraction_text="THP-1",
+            attributes={"cell_line": "THP-1", "assay_format": "intracellular"},
+        ),
+        lx.data.Extraction(
+            extraction_class="assay",
+            extraction_text="Vero",
+            attributes={"cell_line": "Vero", "assay_format": "cytotoxicity"},
+        ),
+        lx.data.Extraction(
+            extraction_class="compound_name",
+            extraction_text="SACC-4412",
+            attributes={"synonyms": "21a"},
+        ),
+        lx.data.Extraction(
+            extraction_class="bioactivity",
+            extraction_text="0.12",
+            attributes={
+                "value": "0.12",
+                "unit": "µM",
+                "assay_type": "MIC90",
+                "strain": "H37Rv",
+                "compound_name": "SACC-4412",
+                "assay": "MABA",
+            },
+        ),
+        lx.data.Extraction(
+            extraction_class="bioactivity",
+            extraction_text="0.9",
+            attributes={
+                "value": "0.9",
+                "unit": "µM",
+                "assay_type": "EC90",
+                "compound_name": "SACC-4412",
+                "assay": "THP-1",
+            },
+        ),
+        lx.data.Extraction(
+            extraction_class="bioactivity",
+            extraction_text=">50",
+            attributes={
+                "value": ">50",
+                "unit": "µM",
+                "assay_type": "CC50",
+                "compound_name": "SACC-4412",
+                "assay": "Vero",
+            },
+        ),
+        lx.data.Extraction(
+            extraction_class="compound_name",
+            extraction_text="CHEMBL5290347",
+            attributes={"synonyms": "21b"},
+        ),
+        lx.data.Extraction(
+            extraction_class="bioactivity",
+            extraction_text="<0.03",
+            attributes={
+                "value": "<0.03",
+                "unit": "µM",
+                "assay_type": "MIC90",
+                "strain": "H37Rv",
+                "compound_name": "CHEMBL5290347",
+                "assay": "MABA",
+            },
+        ),
+        lx.data.Extraction(
+            extraction_class="bioactivity",
+            extraction_text="2.4",
+            attributes={
+                "value": "2.4",
+                "unit": "µM",
+                "assay_type": "EC90",
+                "compound_name": "CHEMBL5290347",
+                "assay": "THP-1",
+            },
+        ),
+        lx.data.Extraction(
+            extraction_class="bioactivity",
+            extraction_text="18.5",
+            attributes={
+                "value": "18.5",
+                "unit": "µM",
+                "assay_type": "CC50",
+                "compound_name": "CHEMBL5290347",
+                "assay": "Vero",
+            },
+        ),
+    ],
+)
+
 TB_EXAMPLES: list[lx.data.ExampleData] = [
     _TB_EXAMPLE_1,
     _TB_EXAMPLE_2,
     _TB_EXAMPLE_3,
     _TB_EXAMPLE_4,
     _TB_EXAMPLE_5,
+    _TB_EXAMPLE_6,
 ]
 
 TB_CHEMISTRY_EXAMPLES: list[lx.data.ExampleData] = [

{structflo_ner-0.5.0 → structflo_ner-0.6.0}/structflo/ner/_prompts.py

@@ -1,5 +1,34 @@
 """Prompt strings for each built-in EntityProfile."""
 
+# Shared by every prompt that extracts bioactivity values. The attribute names
+# must match the keys used in the few-shot examples: langextract derives the
+# output schema from those keys, not from this text.
+_BIOACTIVITY_ATTRIBUTES = (
+    "For each bioactivity value capture:\n"
+    "- value: the number as reported, keeping qualifiers ('>20.0', '<1.0') and dropping "
+    "footnote markers ('0.3*' → '0.3').\n"
+    "- unit: as written (nM, µM, µg/mL, mg/kg, %, h).\n"
+    "- assay_type: the endpoint only, in plain characters (CC₅₀ → CC50). Common endpoints: "
+    "IC50, IC90, EC50, EC90, pIC50, Ki, Kd, '% inhibition at <concentration>'; "
+    "MIC, MIC50, MIC90, MIC99, MBC, log10 CFU reduction; CC50, TC50, SI (selectivity index); "
+    "GI50, TGI, LC50; DC50, Dmax (degraders); ED50, ED90, %TGI, T/C (in vivo); "
+    "PRR (parasite reduction ratio), parasite clearance half-life.\n"
+    "- assay: the assay, cell line or read-out the value was measured in, e.g. 'MABA', "
+    "'LORA', 'HepG2 MTT', 'THP-1 macrophage infection assay', 'asexual blood-stage', "
+    "'liver-stage', 'gametocyte', 'NCI-60', 'hERG', 'P. berghei 4-day suppressive test'. "
+    "null when no assay is stated.\n"
+    "- compound_name: the compound the value belongs to, by its name or identifier "
+    "(e.g. 'bedaquiline', 'BTZ043', 'CHEMBL1234', 'SACC-3000'); a document-local label "
+    "('7a', 'Compound 9b') only when nothing else names the compound.\n"
+)
+_BIOACTIVITY_TABLES = (
+    "In a data table, extract every cell value as its own bioactivity. An ID or registry "
+    "column, when present, supplies the compound_name and the row label is only its synonym; "
+    "otherwise the row label is the compound_name. A column header naming an assay or cell "
+    "line is the assay, and the endpoint and unit often come from the caption or a footnote "
+    "('CC50 in µM')."
+)
+
 CHEMISTRY_PROMPT = (
     "Extract chemical entities from the text. "
     "Include: compound names (generic names, IUPAC names, code names like 'Compound 5b', "
@@ -17,14 +46,11 @@ BIOLOGY_PROMPT = (
 )
 
 BIOACTIVITY_PROMPT = (
-    "Extract bioactivity measurements and assay data from the text. "
-    "Include: potency values (IC50, MIC, EC50, Ki, Kd, GI50, CC50), selectivity ratios, "
-    "percent inhibition values, and Hill coefficients. "
-    "For each value, capture the numeric value, unit (nM, µM, mM, µg/mL, ng/mL), and measurement type. "
-    "Also capture the compound — its name, code name, or identifier (e.g. 'Compound 7', 'BTZ043', "
-    "'CHEMBL1234', 'SACC-3000') — that the measurement applies to, as a 'compound_name' attribute, "
-    "if it can be identified from the surrounding context. "
-    "Also extract assay descriptions: cell lines used (e.g. 'HeLa', 'A549'), assay formats "
+    "Extract bioactivity measurements and assay data from the text: potency, selectivity, "
+    "cytotoxicity and efficacy values.\n"
+    + _BIOACTIVITY_ATTRIBUTES
+    + _BIOACTIVITY_TABLES
+    + "\nAlso extract assay descriptions: cell lines used (e.g. 'HeLa', 'A549'), assay formats "
     "(e.g. 'cell viability', 'binding assay', 'enzymatic assay'), and organisms."
 )
 
@@ -43,22 +69,23 @@ FULL_PROMPT = (
     "- Chemical entities: compound names (generic, IUPAC, code names, brand names), "
     "SMILES strings (only if explicitly written), CAS numbers, molecular formulas.\n"
     "- Biological targets: protein names, gene names, receptor names, enzyme names, pathways.\n"
-    "- Bioactivity data: IC50, MIC, EC50, Ki, Kd, and other potency/selectivity measurements "
-    "with their numeric values, units, and the compound name or identifier they apply to "
-    "(captured as a 'compound_name' attribute).\n"
+    "- Bioactivity data: potency, selectivity, cytotoxicity and efficacy values "
+    "(attributes below).\n"
     "- Assay information: cell lines, assay formats, experimental organisms.\n"
     "- Diseases and indications: cancer types, disease names, therapeutic areas.\n"
     "- Mechanisms of action: binding modes, inhibition types, selectivity descriptions.\n"
-    "Extract only what is explicitly stated; do not infer or generate values."
+    + _BIOACTIVITY_ATTRIBUTES
+    + _BIOACTIVITY_TABLES
+    + "\nExtract only what is explicitly stated; do not infer or generate values."
 )
 
 # ── Tuberculosis early drug discovery prompts ──────────────────────────
 
 TB_PROMPT = (
     "Extract drug discovery entities from this tuberculosis research text.\n\n"
-    "For each bioactivity measurement (IC50, MIC, MIC90, EC50, CC50, etc.), capture the "
-    "compound name, code, or identifier it belongs to as a 'compound_name' attribute "
-    "(e.g. 'BTZ043 showed a MIC of 1 ng/mL' → compound_name: 'BTZ043').\n\n"
+    + _BIOACTIVITY_ATTRIBUTES
+    + "- strain: the organism or strain tested (H37Rv, Erdman, Pf3D7, Dd2, K1), "
+    "null when not stated.\n" + _BIOACTIVITY_TABLES + "\n\n"
     "DISAMBIGUATION RULES:\n"
     "- Mycobacterial proteins (e.g. ClpC1, DprE1, InhA, AtpE, MmpL3, QcrB) "
     "are biological targets, NOT compounds.\n"
@@ -67,6 +94,11 @@ TB_PROMPT = (
     "- Compound registry and programme identifiers (CHEMBL4521987, ZINC000012345678, "
     "DB00945, SACC-3060, TBDA-01187, GSK3036656) are compound_name; only Rv locus "
     "tags, UniProt IDs, PDB codes and RefSeq IDs are accession_number.\n"
+    "- A compound with both a document-local label (a number with an optional letter: 7a, "
+    "12, 'Compound 9b') and a longer identifier (registry ID; programme, partner or vendor "
+    "code: CHEMBL…, SACC-…, a ChemBridge number) is extracted once, as the identifier, with "
+    "the label in synonyms; its bioactivities use the identifier as compound_name. A label "
+    "is the compound_name only when the document gives nothing else.\n"
     "- Enzyme descriptions like 'enoyl-ACP reductase' are product, not target.\n"
     "- 'cell wall', 'lipid metabolism' are functional_category, not mechanism_of_action.\n"
     "- 'fragment screening', 'biochemical assay' are screening_method, not assay.\n"

{structflo_ner-0.5.0 → structflo_ner-0.6.0}/structflo/ner/fast/README.md

@@ -66,7 +66,7 @@ so a deployment's own gazetteer decides which ones apply:
 | Seed | Auto-derived Pattern | Matches |
 |---|---|---|
 | `Rv0005` | `Rv\d{4}[c]?` | All Rv locus tags |
-| `MT0005` | `MT\w+` | Mycobrowser IDs |
+| `MT0005` | `MT[A-Z]{0,2}\d{2,}\w*` | Mycobrowser IDs (not MTT, MTX) |
 | `P9WGR1` | `[OPQ][0-9][A-Z0-9]{3}[0-9]` | UniProt accessions |
 | `4TZK` | `(?=[A-Z0-9]{0,3}[A-Z])[1-9][A-Z0-9]{3}` | PDB codes |
 | `WP_003407354` | `WP_\d+` | NCBI RefSeq proteins |

{structflo_ner-0.5.0 → structflo_ner-0.6.0}/structflo/ner/fast/_loader.py

@@ -89,8 +89,13 @@ _COMPOUND_ID_PATTERNS: list[IdPattern] = [
 _ACCESSION_PATTERNS: list[tuple[re.Pattern[str], re.Pattern[str], str]] = [
     # Rv locus tags: Rv0005, Rv3854c
     (re.compile(r"^Rv\d{4}[c]?$"), re.compile(r"\bRv\d{4}[c]?\b"), "Rv locus tag"),
-    # Mycobrowser MT IDs: MT0005, MTCI00.01
-    (re.compile(r"^MT\w+$"), re.compile(r"\bMT\w+\b"), "Mycobrowser ID"),
+    # Mycobrowser MT IDs: MT0005, MT18B_0001, MTB000001. The digit run keeps
+    # MTT (viability assay), MTX and MTD from matching.
+    (
+        re.compile(r"^MT[A-Z]{0,2}\d{2,}\w*$"),
+        re.compile(r"\bMT[A-Z]{0,2}\d{2,}\w*\b"),
+        "Mycobrowser ID",
+    ),
     # UniProt accessions: P9WGR1, O53617
     (
         re.compile(r"^[OPQ][0-9][A-Z0-9]{3}[0-9]$"),

{structflo_ner-0.5.0 → structflo_ner-0.6.0}/structflo/ner/fast/_matcher.py

@@ -275,8 +275,9 @@ def _build_position_map(original: str, normalized: str) -> list[int]:
 
         # Advance original pointer to find the matching character
         while orig_idx < len(original):
-            orig_lower = original[orig_idx].lower()
-            if orig_lower == norm_char:
+            # normalize() the char too: a newline became " " and an en dash "-",
+            # and comparing raw chars would desync every position after them.
+            if (normalize(original[orig_idx]) or " ") == norm_char:
                 position_map.append(orig_idx)
                 orig_idx += 1
                 break

{structflo_ner-0.5.0 → structflo_ner-0.6.0}/tests/test_extractor.py

@@ -7,6 +7,7 @@ from unittest.mock import MagicMock
 import langextract as lx
 
 from structflo.ner import (
+    BIOACTIVITY,
     BIOLOGY,
     CHEMISTRY,
     FULL,
@@ -284,8 +285,21 @@ class TestTBProfile:
         for cls in TB_BIOLOGY.entity_classes:
             assert cls in TB.entity_classes
 
+    def test_bioactivity_schema_has_assay(self):
+        """langextract builds the output schema from example attribute keys, so an
+        `assay` slot exists only if some bioactivity example carries one."""
+        for profile in (TB, BIOACTIVITY, FULL):
+            keys = {
+                k
+                for ex in profile.examples
+                for e in ex.extractions
+                if e.extraction_class == "bioactivity"
+                for k in (e.attributes or {})
+            }
+            assert {"value", "unit", "assay_type", "compound_name", "assay"} <= keys, profile.name
+
     def test_tb_examples_count(self):
-        assert len(TB.examples) == 5
+        assert len(TB.examples) == 6
         assert len(TB_CHEMISTRY.examples) == 2
         assert len(TB_BIOLOGY.examples) == 2
 

{structflo_ner-0.5.0 → structflo_ner-0.6.0}/tests/test_fast.py

@@ -180,6 +180,13 @@ class TestDeriveIdPatterns:
         assert not pdb.regex.search("in 2019 the trial")
         assert not pdb.regex.search("n = 1234")
 
+    def test_mycobrowser_pattern_needs_locus_digits(self):
+        """MTT (viability assay), MTX and MTD are not Mycobrowser loci."""
+        mt = next(p for p in _accessions(["MT18B_0001"]) if p.description == "Mycobrowser ID")
+        for locus in ["MT0005", "MT18B_0001", "MTB000001"]:
+            assert mt.regex.fullmatch(locus), locus
+        assert not mt.regex.search("HepG2 MTT, MTX and MTD read-outs")
+
     def test_cas_check_digit_rejects_dates(self):
         cas = next(p for p in derive_id_patterns({}) if p.description == "CAS number")
         assert cas.validate("50-78-2")  # aspirin
@@ -246,6 +253,13 @@ class TestGazetteerMatcher:
         m = inha_matches[0]
         assert text[m.char_start : m.char_end] == "InhA"
 
+    def test_char_offsets_survive_newlines(self):
+        """normalize() folds a newline into a space; offsets after it must not drift."""
+        matcher = self._simple_matcher(fuzzy_threshold=0)
+        text = "Targets:\nINHA and\n\nDPRE1."
+        found = {m.canonical: text[m.char_start : m.char_end] for m in matcher.match(text)}
+        assert found == {"InhA": "INHA", "DprE1": "DPRE1"}
+
     def test_regex_accession_matching(self):
         matcher = GazetteerMatcher(
             gazetteers={"target": ["InhA"]},

{structflo_ner-0.5.0 → structflo_ner-0.6.0}/uv.lock

@@ -917,7 +917,7 @@ wheels = [
 
 [[package]]
 name = "langextract"
-version = "1.6.0"
+version = "1.7.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "absl-py" },
@@ -940,9 +940,9 @@ dependencies = [
     { name = "tqdm" },
     { name = "typing-extensions" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/49/c2/30216c49a53419bf3c124cb3ea6daba95a617a62e5ea4964b9fb11784f1e/langextract-1.6.0.tar.gz", hash = "sha256:ac6412152b173bfb0d6b4e08bf6ace7319b1e734c4f9c6f33d39f0c5915e640d", size = 142637, upload-time = "2026-07-02T06:24:00.632Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/e3/e7/6cf877cdd3d5d3a479c0688ff2b63c665c4319ae35ba00734c9fef36a1d2/langextract-1.7.0.tar.gz", hash = "sha256:cb6dc515583b0fdc0f9eff9dce61b2a3c7c84b0668add4dd4e7be364f4c188ba", size = 147514, upload-time = "2026-09-13T18:58:06.376Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/d7/e0/3475ffd1c7e2a4a49f3d8c186c27869a53c710335742964707dbc499590e/langextract-1.6.0-py3-none-any.whl", hash = "sha256:ffa2d584c29ea25c73a2723cec756f21a76799e8ab76a1d9d92841e27504b057", size = 150147, upload-time = "2026-07-02T06:23:59.25Z" },
+    { url = "https://files.pythonhosted.org/packages/ae/ec/2883a93872701045971ea77e30434d72556a557f188df575b154d179854c/langextract-1.7.0-py3-none-any.whl", hash = "sha256:908f8ec696ab13578cdc3862efcf1a4fda929ae426410d99e86977d50e52136d", size = 154297, upload-time = "2026-09-13T18:58:04.896Z" },
 ]
 
 [[package]]