structflo-ner 0.6.0__tar.gz → 0.7.0__tar.gz

structflo_ner-0.6.0/README.md → structflo_ner-0.7.0/PKG-INFO

@@ -1,3 +1,16 @@
+Metadata-Version: 2.5
+Name: structflo-ner
+Version: 0.7.0
+Summary: Drug discovery NER wrapper around LangExtract — zero-config entity extraction for chemistry and biology.
+License: Apache-2.0
+Requires-Python: >=3.10
+Requires-Dist: langextract>=1.7.0
+Requires-Dist: pyyaml>=6.0
+Requires-Dist: rapidfuzz>=3.0
+Provides-Extra: dataframe
+Requires-Dist: pandas>=1.5; extra == 'dataframe'
+Description-Content-Type: text/markdown
+
 
 <h1 align="center">structflo.ner</h1>
 <p align="center">
@@ -343,10 +356,19 @@ Each bioactivity carries its measurement in `attributes`:
 | `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)                     |
+| `target`        | `InhA`                      | protein measured against (`TB` profile only)               |
+| `strain`        | `H37Rv`                     | organism, strain or virus measured against (`TB` only)     |
+| `combination`   | `meropenem`                 | second compound dosed alongside (`TB` profile only)        |
+
+An attribute the text does not state is absent from `attributes`.
+
+A table on one page often names its target only on another. Pass text from
+elsewhere in the document (its title or summary) as `context`; the model uses it
+to fill attributes the page leaves unstated, and extracts nothing from it:
 
-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.
+```python
+result = extractor.extract(page_text, context=document_summary)
+```
 
 
 ## Notebooks

structflo_ner-0.6.0/PKG-INFO → structflo_ner-0.7.0/README.md

@@ -1,16 +1,3 @@
-Metadata-Version: 2.5
-Name: structflo-ner
-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
-Requires-Dist: langextract>=1.6.0
-Requires-Dist: pyyaml>=6.0
-Requires-Dist: rapidfuzz>=3.0
-Provides-Extra: dataframe
-Requires-Dist: pandas>=1.5; extra == 'dataframe'
-Description-Content-Type: text/markdown
-
 
 <h1 align="center">structflo.ner</h1>
 <p align="center">
@@ -356,10 +343,19 @@ Each bioactivity carries its measurement in `attributes`:
 | `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)                     |
+| `target`        | `InhA`                      | protein measured against (`TB` profile only)               |
+| `strain`        | `H37Rv`                     | organism, strain or virus measured against (`TB` only)     |
+| `combination`   | `meropenem`                 | second compound dosed alongside (`TB` profile only)        |
+
+An attribute the text does not state is absent from `attributes`.
+
+A table on one page often names its target only on another. Pass text from
+elsewhere in the document (its title or summary) as `context`; the model uses it
+to fill attributes the page leaves unstated, and extracts nothing from it:
 
-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.
+```python
+result = extractor.extract(page_text, context=document_summary)
+```
 
 
 ## Notebooks

{structflo_ner-0.6.0 → structflo_ner-0.7.0}/pyproject.toml

@@ -6,7 +6,7 @@ readme = "README.md"
 requires-python = ">=3.10"
 license = { text = "Apache-2.0" }
 dependencies = [
-    "langextract>=1.6.0",
+    "langextract>=1.7.0",
     "rapidfuzz>=3.0",
     "PyYAML>=6.0",
 ]

{structflo_ner-0.6.0 → structflo_ner-0.7.0}/structflo/ner/__init__.py

@@ -63,7 +63,7 @@ from structflo.ner.profiles import (
     EntityProfile,
 )
 
-__version__ = "0.6.0"
+__version__ = "0.7.0"
 
 __all__ = [
     # Main classes

{structflo_ner-0.6.0 → structflo_ner-0.7.0}/structflo/ner/_examples.py

@@ -625,6 +625,7 @@ _TB_EXAMPLE_3 = lx.data.ExampleData(
                 "assay_type": "IC50",
                 "compound_name": "Compound 14a",
                 "assay": "biochemical assay",
+                "target": "InhA",
             },
         ),
         lx.data.Extraction(
@@ -853,6 +854,7 @@ _TB_EXAMPLE_5 = lx.data.ExampleData(
                 "unit": "nM",
                 "assay_type": "IC50",
                 "compound_name": "SACC-3060",
+                "target": "DprE1",
             },
         ),
         lx.data.Extraction(
@@ -980,6 +982,99 @@ _TB_EXAMPLE_6 = lx.data.ExampleData(
     ],
 )
 
+# Strain panel: organism column headers are the strain, a protein column the
+# target, a cytotoxicity column the assay; a column dosed with a second drug
+# names the combination partner. The disease stays a disease entity.
+_TB_EXAMPLE_7 = lx.data.ExampleData(
+    text=(
+        "Table 3. Antibacterial activity against hospital-acquired pneumonia isolates\n\n"
+        "| Cpd | ID | E. coli ATCC 25922 | K. pneumoniae BAA-1705 | A. baumannii ATCC 19606 "
+        "| ATCC 19606 + polymyxin B | HepG2 | hERG |\n"
+        "| --- | --- | --- | --- | --- | --- | --- | --- |\n"
+        "| 9c | CHEMBL5311027 | 0.25 | 1 | >64 | 2 | >100 | 12.5 |\n\n"
+        "MIC (µg/mL); polymyxin B at 0.5 µg/mL. HepG2: CC50 (µM). hERG: IC50 (µM)."
+    ),
+    extractions=[
+        lx.data.Extraction(
+            extraction_class="disease",
+            extraction_text="hospital-acquired pneumonia",
+            attributes={"therapeutic_area": "infectious disease"},
+        ),
+        lx.data.Extraction(
+            extraction_class="compound_name",
+            extraction_text="CHEMBL5311027",
+            attributes={"synonyms": "9c"},
+        ),
+        lx.data.Extraction(
+            extraction_class="bioactivity",
+            extraction_text="0.25",
+            attributes={
+                "value": "0.25",
+                "unit": "µg/mL",
+                "assay_type": "MIC",
+                "strain": "E. coli ATCC 25922",
+                "compound_name": "CHEMBL5311027",
+            },
+        ),
+        lx.data.Extraction(
+            extraction_class="bioactivity",
+            extraction_text="1",
+            attributes={
+                "value": "1",
+                "unit": "µg/mL",
+                "assay_type": "MIC",
+                "strain": "K. pneumoniae BAA-1705",
+                "compound_name": "CHEMBL5311027",
+            },
+        ),
+        lx.data.Extraction(
+            extraction_class="bioactivity",
+            extraction_text=">64",
+            attributes={
+                "value": ">64",
+                "unit": "µg/mL",
+                "assay_type": "MIC",
+                "strain": "A. baumannii ATCC 19606",
+                "compound_name": "CHEMBL5311027",
+            },
+        ),
+        lx.data.Extraction(
+            extraction_class="bioactivity",
+            extraction_text="2",
+            attributes={
+                "value": "2",
+                "unit": "µg/mL",
+                "assay_type": "MIC",
+                "strain": "ATCC 19606",
+                "combination": "polymyxin B",
+                "compound_name": "CHEMBL5311027",
+            },
+        ),
+        lx.data.Extraction(
+            extraction_class="bioactivity",
+            extraction_text=">100",
+            attributes={
+                "value": ">100",
+                "unit": "µM",
+                "assay_type": "CC50",
+                "compound_name": "CHEMBL5311027",
+                "assay": "HepG2",
+            },
+        ),
+        lx.data.Extraction(
+            extraction_class="bioactivity",
+            extraction_text="12.5",
+            attributes={
+                "value": "12.5",
+                "unit": "µM",
+                "assay_type": "IC50",
+                "compound_name": "CHEMBL5311027",
+                "target": "hERG",
+            },
+        ),
+    ],
+)
+
 TB_EXAMPLES: list[lx.data.ExampleData] = [
     _TB_EXAMPLE_1,
     _TB_EXAMPLE_2,
@@ -987,6 +1082,7 @@ TB_EXAMPLES: list[lx.data.ExampleData] = [
     _TB_EXAMPLE_4,
     _TB_EXAMPLE_5,
     _TB_EXAMPLE_6,
+    _TB_EXAMPLE_7,
 ]
 
 TB_CHEMISTRY_EXAMPLES: list[lx.data.ExampleData] = [

{structflo_ner-0.6.0 → structflo_ner-0.7.0}/structflo/ner/_mapping.py

@@ -29,6 +29,10 @@ def extraction_to_entity(extraction: lx.data.Extraction) -> NEREntity:
     attributes: dict[str, str] = {}
     if extraction.attributes:
         for key, value in extraction.attributes.items():
+            # Strict-schema providers (OpenAI) must emit every attribute key, so an
+            # unstated one arrives as null; leave it out rather than store "None".
+            if value is None:
+                continue
             if isinstance(value, list):
                 attributes[key] = ", ".join(value)
             else:

{structflo_ner-0.6.0 → structflo_ner-0.7.0}/structflo/ner/_prompts.py

@@ -13,20 +13,41 @@ _BIOACTIVITY_ATTRIBUTES = (
     "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"
+    "- 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"
+)
+_ASSAY_ATTRIBUTE = (
     "- 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"
+)
+# TB gives each kind of context its own slot: what the value was measured in
+# (assay), against (target, strain), and with (combination).
+_TB_SLOT_ATTRIBUTES = (
+    "- assay: the assay system the value was measured in: a cell line, format or read-out "
+    "('MABA', 'LORA', 'HepG2 MTT', 'THP-1 macrophage infection assay', 'asexual blood-stage', "
+    "'AlphaScreen', 'FP', 'NCI-60', 'P. berghei 4-day suppressive test'). null when none is "
+    "stated.\n"
+    "- target: the protein the value was measured against: an enzyme, receptor, channel or "
+    "other molecular target, as written ('InhA', 'DprE1', 'hERG', 'KasA', 'PDE4B', "
+    "'BACE1'). null for whole-cell, organism and cytotoxicity values unless one is named.\n"
+    "- strain: the organism the value was measured against, as written: species, strain, "
+    "isolate or virus (H37Rv, M. tuberculosis, E. coli ATCC 25922, A. baumannii ATCC 19606, "
+    "Pf3D7, Dd2, S. mansoni, HIV-1, norovirus). An organism always goes here, never in assay or target, even "
+    "when it heads a table column or is all that names the assay. null when not stated.\n"
+    "- combination: a second compound dosed together with the one measured (a combination "
+    "or potentiation partner), as written ('avibactam', 'polymyxin B 0.5 µg/mL'). Not a "
+    "reference compound the value is relative to ('% of isoproterenol') or an agonist, substrate "
+    "or tracer the assay uses. null for a single agent.\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')."
+    "otherwise the row label is the compound_name. A column header fills the attribute for "
+    "what it names (an assay or cell line, a protein target, an organism or strain), and the "
+    "endpoint and unit often come from the caption or a footnote ('CC50 in µM')."
 )
 
 CHEMISTRY_PROMPT = (
@@ -49,6 +70,7 @@ BIOACTIVITY_PROMPT = (
     "Extract bioactivity measurements and assay data from the text: potency, selectivity, "
     "cytotoxicity and efficacy values.\n"
     + _BIOACTIVITY_ATTRIBUTES
+    + _ASSAY_ATTRIBUTE
     + _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."
@@ -75,6 +97,7 @@ FULL_PROMPT = (
     "- Diseases and indications: cancer types, disease names, therapeutic areas.\n"
     "- Mechanisms of action: binding modes, inhibition types, selectivity descriptions.\n"
     + _BIOACTIVITY_ATTRIBUTES
+    + _ASSAY_ATTRIBUTE
     + _BIOACTIVITY_TABLES
     + "\nExtract only what is explicitly stated; do not infer or generate values."
 )
@@ -84,8 +107,9 @@ FULL_PROMPT = (
 TB_PROMPT = (
     "Extract drug discovery entities from this tuberculosis research text.\n\n"
     + _BIOACTIVITY_ATTRIBUTES
-    + "- strain: the organism or strain tested (H37Rv, Erdman, Pf3D7, Dd2, K1), "
-    "null when not stated.\n" + _BIOACTIVITY_TABLES + "\n\n"
+    + _TB_SLOT_ATTRIBUTES
+    + _BIOACTIVITY_TABLES
+    + "\n\n"
     "DISAMBIGUATION RULES:\n"
     "- Mycobacterial proteins (e.g. ClpC1, DprE1, InhA, AtpE, MmpL3, QcrB) "
     "are biological targets, NOT compounds.\n"
@@ -102,6 +126,9 @@ TB_PROMPT = (
     "- 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"
+    "- A disease or infection is a disease entity wherever it is named, in prose, a heading "
+    "or a table cell (tuberculosis, HIV infection, malaria, schistosomiasis, glioblastoma in 'U87 (glioblastoma)'), "
+    "even when its organism also fills a bioactivity's strain.\n"
     "- Use target for proteins in a drug-targeting context, gene_name for loci, "
     "protein_name for non-drug-target proteins.\n\n"
     "Extract only what is explicitly stated; do not infer or generate values."
@@ -125,3 +152,13 @@ TB_BIOLOGY_PROMPT = (
     "are functional_category. "
     "Extract only what is explicitly stated; do not infer or generate values."
 )
+
+# Framing for NERExtractor.extract(context=...), rendered by langextract ahead of
+# the examples.
+DOCUMENT_CONTEXT = (
+    "Document context, from elsewhere in the same document. It is not the text to extract "
+    "from: take no entity and no value from it, and do not pair a value in the text with a "
+    "number or claim made here. Use it only to fill a bioactivity attribute the text leaves "
+    "unstated, such as the target or organism of a table, when the context names one for "
+    "the whole document.\n"
+)

{structflo_ner-0.6.0 → structflo_ner-0.7.0}/structflo/ner/extractor.py

@@ -3,15 +3,43 @@
 from __future__ import annotations
 
 import logging
+import re
 
 import langextract as lx
 
+from structflo.ner import _prompts
 from structflo.ner._entities import NERResult
 from structflo.ner._mapping import annotated_doc_to_result
 from structflo.ner.profiles import FULL, EntityProfile
 
 logger = logging.getLogger(__name__)
 
+# A table cell holding only a value: '0.94', '>32', '2.4*', '0.62µM'.
+_VALUE_CELL = re.compile(r"^[<>≤≥~=]*\s*\d[\d,]*\.?\d*\s*\*?\s*(%|[nµu]M|µg/mL|mg/kg)?$")
+
+
+def _bioactivity_count(doc: lx.data.AnnotatedDocument) -> int:
+    return sum(1 for ext in doc.extractions if ext.extraction_class == "bioactivity")
+
+
+def _table_values_dropped(text: str, doc: lx.data.AnnotatedDocument) -> bool:
+    """True when fewer than half of a page's table values came back as bioactivities.
+
+    Models now and then return a complete, valid answer that lists a table's
+    compounds but leaves out its values. On the ChEMBL-gold decks this fires on
+    ~2% of pages and catches ~60% of such dropouts.
+    """
+    # ponytail: markdown tables only; values in prose and qualitative results
+    # are not checked, so those dropouts still pass silently.
+    cells = sum(
+        1
+        for line in text.splitlines()
+        if line.lstrip().startswith("|")
+        for cell in line.strip().strip("|").split("|")
+        if _VALUE_CELL.match(cell.strip())
+    )
+    return cells >= 5 and _bioactivity_count(doc) < 0.5 * cells
+
 
 class NERExtractor:
     """Extract drug discovery entities from text with zero configuration.
@@ -90,12 +118,17 @@ class NERExtractor:
         self,
         text: str | list[str],
         profile: EntityProfile | None = None,
+        context: str | None = None,
     ) -> NERResult | list[NERResult]:
         """Extract drug discovery entities from text.
 
         Args:
             text: Input text (or list of texts) to process.
             profile: Override the default profile for this call only.
+            context: Text from elsewhere in the same document (its title or
+                summary). The model reads it to fill attributes the text leaves
+                unstated, such as the target of a table whose target is named
+                only on another page; no entities are extracted from it.
 
         Returns:
             A :class:`NERResult` for a single string input, or a list of
@@ -107,7 +140,13 @@ class NERExtractor:
 
         results = []
         for single_text in texts:
-            doc = self._run_extraction(single_text, active_profile)
+            doc = self._run_extraction(single_text, active_profile, context)
+            if "bioactivity" in active_profile.entity_classes and _table_values_dropped(
+                single_text, doc
+            ):
+                logger.warning("Table values missing from extraction; retrying once.")
+                retry = self._run_extraction(single_text, active_profile, context)
+                doc = max(doc, retry, key=_bioactivity_count)
             results.append(annotated_doc_to_result(doc, single_text))
 
         return results if is_batch else results[0]
@@ -198,6 +237,7 @@ class NERExtractor:
         self,
         text: str,
         profile: EntityProfile,
+        context: str | None = None,
     ) -> lx.data.AnnotatedDocument:
         """Call lx.extract and return the AnnotatedDocument."""
         examples = self._build_examples(profile)
@@ -206,6 +246,8 @@ class NERExtractor:
         kwargs: dict = dict(self._langextract_kwargs)
         kwargs.setdefault("use_schema_constraints", True)
         kwargs.setdefault("show_progress", False)
+        if context:
+            kwargs["additional_context"] = _prompts.DOCUMENT_CONTEXT + context
 
         if self._provider is not None:
             # Explicit provider → deterministic routing via ModelConfig.
@@ -236,4 +278,29 @@ class NERExtractor:
 
         # Post-process: drop extractions with hallucinated entity classes
         allowed = set(profile.entity_classes)
-        return self._filter_extractions(doc, allowed)
+        doc = self._filter_extractions(doc, allowed)
+        if context:
+            doc = self._drop_context_copies(doc, context)
+        return doc
+
+    @staticmethod
+    def _drop_context_copies(
+        doc: lx.data.AnnotatedDocument,
+        context: str,
+    ) -> lx.data.AnnotatedDocument:
+        """Drop extractions the model took from the context instead of the text.
+
+        The prompt forbids it, but models still extract from the context now and
+        then. Such an extraction does not align to the text, and its text occurs
+        in the context but not in the text (an unaligned one that is in the text
+        is a missed alignment, not a copy).
+        """
+        ctx, text = context.casefold(), doc.text.casefold()
+        kept = [
+            ext
+            for ext in doc.extractions
+            if ext.char_interval is not None
+            or ext.extraction_text.casefold() not in ctx
+            or ext.extraction_text.casefold() in text
+        ]
+        return lx.data.AnnotatedDocument(text=doc.text, extractions=kept)

{structflo_ner-0.6.0 → structflo_ner-0.7.0}/tests/test_extractor.py

@@ -122,6 +122,50 @@ class TestNERExtractorExtract:
         result = extractor.extract("My source text")
         assert result.source_text == "My source text"
 
+    _TABLE = "| cpd | MIC | CC50 |\n| --- | --- | --- |\n" + "".join(
+        f"| C{i} | {i}.5 | >50 |\n" for i in range(5)
+    )
+
+    def _bio_doc(self, n: int) -> lx.data.AnnotatedDocument:
+        return _make_annotated_doc(
+            [
+                lx.data.Extraction(extraction_class="bioactivity", extraction_text=f"{i}.5")
+                for i in range(n)
+            ]
+        )
+
+    def test_retries_once_when_table_values_are_missing(self):
+        extractor = NERExtractor(profile=TB)
+        extractor._run_extraction = MagicMock(side_effect=[self._bio_doc(0), self._bio_doc(10)])
+        result = extractor.extract(self._TABLE)
+        assert extractor._run_extraction.call_count == 2
+        assert len(result.bioactivities) == 10
+
+    def test_no_retry_when_table_values_came_back(self):
+        extractor = NERExtractor(profile=TB)
+        extractor._run_extraction = MagicMock(return_value=self._bio_doc(10))
+        extractor.extract(self._TABLE)
+        assert extractor._run_extraction.call_count == 1
+
+    def test_no_retry_for_profiles_without_bioactivity(self):
+        extractor = NERExtractor(profile=CHEMISTRY)
+        extractor._run_extraction = MagicMock(return_value=self._bio_doc(0))
+        extractor.extract(self._TABLE)
+        assert extractor._run_extraction.call_count == 1
+
+    def test_null_attributes_are_absent_not_none_strings(self):
+        # OpenAI strict mode returns every schema key, null when unstated.
+        extractor = self._extractor_with_mock(
+            [
+                lx.data.Extraction(
+                    extraction_class="bioactivity",
+                    extraction_text="IC50 = 3 nM",
+                    attributes={"value": "3", "strain": None, "assay": None},
+                )
+            ]
+        )
+        assert extractor.extract("text").bioactivities[0].attributes == {"value": "3"}
+
 
 class TestProviderRouting:
     """Explicit provider selection routes deterministically via ModelConfig,
@@ -181,6 +225,24 @@ class TestProviderRouting:
         assert pk["base_url"] == "http://ollama:11434"
         assert pk["num_ctx"] == 8192
 
+    def test_context_reaches_langextract_framed(self, monkeypatch):
+        from structflo.ner import extractor as extractor_mod
+
+        captured = {}
+
+        def fake_extract(**kwargs):
+            captured.update(kwargs)
+            return _make_annotated_doc([])
+
+        monkeypatch.setattr(extractor_mod.lx, "extract", fake_extract)
+        NERExtractor().extract("IC50s table", context="Deck on InhA inhibitors.")
+        ctx = captured["additional_context"]
+        assert ctx.startswith("Document context") and ctx.endswith("Deck on InhA inhibitors.")
+
+    def test_no_context_passes_no_additional_context(self, monkeypatch):
+        captured = self._run_and_capture(monkeypatch)
+        assert "additional_context" not in captured
+
     def test_cloud_provider_kwargs_carry_api_key(self, monkeypatch):
         captured = self._run_and_capture(
             monkeypatch, provider="openai", model_id="gpt-4o", api_key="sk-test"
@@ -235,6 +297,27 @@ class TestFilterExtractions:
         assert len(filtered.extractions) == 0
 
 
+class TestDropContextCopies:
+    def test_drops_only_unaligned_extractions_found_in_context(self):
+        aligned = lx.data.Extraction(
+            extraction_class="target",
+            extraction_text="InhA",
+            char_interval=lx.data.CharInterval(start_pos=0, end_pos=4),
+        )
+        copied = lx.data.Extraction(extraction_class="compound_name", extraction_text="Isoniazid")
+        unaligned = lx.data.Extraction(extraction_class="compound_name", extraction_text="7a")
+        # In the context too, but also on the page: a missed alignment, not a copy.
+        on_page = lx.data.Extraction(extraction_class="disease", extraction_text="malaria")
+        doc = lx.data.AnnotatedDocument(
+            text="InhA IC50s for 7a; malaria panel",
+            extractions=[aligned, copied, unaligned, on_page],
+        )
+        kept = NERExtractor._drop_context_copies(
+            doc, "InhA inhibitors that match isoniazid, and a malaria screen"
+        )
+        assert kept.extractions == [aligned, unaligned, on_page]
+
+
 class TestBuildExamples:
     def test_extra_examples_appended(self):
         extra = lx.data.ExampleData(text="extra", extractions=[])
@@ -298,8 +381,20 @@ class TestTBProfile:
             }
             assert {"value", "unit", "assay_type", "compound_name", "assay"} <= keys, profile.name
 
+    def test_tb_bioactivity_schema_has_context_slots(self):
+        """TB gives what a value was measured against (target, strain) and with
+        (combination) their own slots, apart from assay."""
+        keys = {
+            k
+            for ex in TB.examples
+            for e in ex.extractions
+            if e.extraction_class == "bioactivity"
+            for k in (e.attributes or {})
+        }
+        assert {"target", "strain", "combination"} <= keys
+
     def test_tb_examples_count(self):
-        assert len(TB.examples) == 6
+        assert len(TB.examples) == 7
         assert len(TB_CHEMISTRY.examples) == 2
         assert len(TB_BIOLOGY.examples) == 2
 

{structflo_ner-0.6.0 → structflo_ner-0.7.0}/uv.lock

@@ -2170,7 +2170,7 @@ dev = [
 
 [package.metadata]
 requires-dist = [
-    { name = "langextract", specifier = ">=1.6.0" },
+    { name = "langextract", specifier = ">=1.7.0" },
     { name = "pandas", marker = "extra == 'dataframe'", specifier = ">=1.5" },
     { name = "pyyaml", specifier = ">=6.0" },
     { name = "rapidfuzz", specifier = ">=3.0" },