Merge with origin and resolve conflicts

src/curate_gpt/cli.py

@@ -415,7 +415,7 @@ def search(query, path, collection, show_documents, database_type, **kwargs):
     db = get_store(database_type, path)
     results = db.search(query, collection=collection, **kwargs)
     i = 0
-    for obj, distance, meta in results:
+    for obj, distance, _meta in results:
         i += 1
         print(f"## {i} DISTANCE: {distance}")
         print(yaml.dump(obj, sort_keys=False))
@@ -537,7 +537,7 @@ def matches(id, path, collection, database_type):
     print(obj)
     results = db.matches(obj, collection=collection)
     i = 0
-    for obj, distance, meta in results:
+    for obj, distance, _meta in results:
         i += 1
         print(f"## ID:- {obj['id']}")
         print(f"## DISTANCE- {distance}")

src/curate_gpt/store/chromadb_adapter.py

@@ -18,10 +18,10 @@
 from linkml_runtime.utils.yamlutils import YAMLRoot
 from oaklib.utilities.iterator_utils import chunk
 from pydantic import BaseModel
-from curate_gpt.store.metadata import CollectionMetadata
 
-from curate_gpt.store.vocab import OBJECT, QUERY, PROJECTION, SEARCH_RESULT
 from curate_gpt.store.db_adapter import DBAdapter
+from curate_gpt.store.metadata import CollectionMetadata
+from curate_gpt.store.vocab import OBJECT, PROJECTION, QUERY, SEARCH_RESULT
 from curate_gpt.utils.vector_algorithms import mmr_diversified_search
 
 logger = logging.getLogger(__name__)

src/curate_gpt/store/db_adapter.py

@@ -5,7 +5,7 @@
 from abc import ABC, abstractmethod
 from dataclasses import dataclass
 from pathlib import Path
-from typing import ClassVar, Dict, Iterable, Iterator, List, Optional, TextIO, Tuple, Union
+from typing import ClassVar, Dict, Iterable, Iterator, List, Optional, TextIO, Union
 
 import pandas as pd
 import yaml
@@ -15,15 +15,15 @@
 from curate_gpt.store.metadata import CollectionMetadata
 from curate_gpt.store.schema_proxy import SchemaProxy
 from curate_gpt.store.vocab import (
-    OBJECT,
-    SEARCH_RESULT,
-    QUERY,
-    PROJECTION,
-    FILE_LIKE,
-    EMBEDDINGS,
+    DEFAULT_COLLECTION,
     DOCUMENTS,
+    EMBEDDINGS,
+    FILE_LIKE,
     METADATAS,
-    DEFAULT_COLLECTION,
+    OBJECT,
+    PROJECTION,
+    QUERY,
+    SEARCH_RESULT,
 )
 
 logger = logging.getLogger(__name__)

src/curate_gpt/store/db_metadata.py

@@ -2,6 +2,7 @@
 
 from pydantic import BaseModel, ConfigDict
 import yaml
+from pydantic import BaseModel
 
 
 class DBSettings(BaseModel):
@@ -19,7 +20,7 @@ class DBSettings(BaseModel):
 
     ef_construction: int = 128
     """
-    Construction parameter for hnsw index. 
+    Construction parameter for hnsw index.
     Higher values are more accurate but slower.
     """
 

src/curate_gpt/store/duckdb_adapter.py

@@ -9,7 +9,6 @@
 import re
 import time
 from dataclasses import dataclass, field
-from pathlib import Path
 from typing import Any, Callable, ClassVar, Dict, Iterable, Iterator, List, Mapping, Optional, Union
 
 import duckdb
@@ -27,21 +26,21 @@
 from curate_gpt.store.db_adapter import DBAdapter
 from curate_gpt.store.duckdb_result import DuckDBSearchResult
 from curate_gpt.store.metadata import CollectionMetadata
-from curate_gpt.utils.vector_algorithms import mmr_diversified_search
 from curate_gpt.store.vocab import (
-    OBJECT,
-    QUERY,
-    PROJECTION,
-    EMBEDDINGS,
+    DISTANCES,
     DOCUMENTS,
+    EMBEDDINGS,
+    IDS,
     METADATAS,
     MODEL_DIMENSIONS,
     MODELS,
+    OBJECT,
     OPENAI_MODEL_DIMENSIONS,
-    IDS,
+    PROJECTION,
+    QUERY,
     SEARCH_RESULT,
-    DISTANCES,
 )
+from curate_gpt.utils.vector_algorithms import mmr_diversified_search
 
 logger = logging.getLogger(__name__)
 

src/curate_gpt/store/duckdb_result.py

@@ -1,8 +1,5 @@
-import json
-from typing import Any, Dict, List, Optional, Set, Iterator, Tuple
+from typing import Any, Dict, Iterator, List, Optional, Set, Tuple
 
-import jsonlines
-import yaml
 from pydantic import BaseModel, ConfigDict
 
 SEARCH_RESULT = Tuple[Dict[str, Any], Dict, float, Optional[Dict]]

src/curate_gpt/store/vocab.py

@@ -1,5 +1,5 @@
 from pathlib import Path
-from typing import Union, Dict, List, Tuple, Optional, TextIO
+from typing import Dict, List, Optional, TextIO, Tuple, Union
 
 from linkml_runtime.utils.yamlutils import YAMLRoot
 from pydantic import BaseModel

src/curate_gpt/wrappers/general/github_wrapper.py

@@ -1,4 +1,4 @@
-"""Chat with a Google Drive."""
+"""Chat with issues from a GitHub repository."""
 
 import logging
 import os
@@ -193,6 +193,10 @@ def issue_comments(self, issue_number: str) -> Iterator[Dict]:
             url = response.links.get("next", {}).get("url")
 
     def transform_issue(self, obj: Dict) -> Issue:
+
+        if not obj.get("body"):
+            obj["body"] = ""
+
         issue = Issue(
             id=obj.get("url"),
             number=obj.get("number"),

tests/agents/conftest.py

@@ -1,8 +1,8 @@
 import pytest
+
 from curate_gpt import ChromaDBAdapter
 from curate_gpt.store import SchemaProxy
 from curate_gpt.wrappers.ontology import ONTOLOGY_MODEL_PATH
-
 from tests import INPUT_DBS
 
 

tests/agents/test_chat.py

@@ -1,6 +1,7 @@
 import re
 
 import pytest
+
 from curate_gpt.agents.chat_agent import ChatAgent
 from curate_gpt.extract import BasicExtractor
 

tests/agents/test_concept_recognizer.py

@@ -1,5 +1,6 @@
 import pytest
 import yaml
+
 from curate_gpt.agents.concept_recognition_agent import AnnotationMethod, ConceptRecognitionAgent
 from curate_gpt.extract.basic_extractor import BasicExtractor
 

tests/agents/test_dase.py

@@ -1,5 +1,6 @@
 import pytest
 import yaml
+
 from curate_gpt.agents.dase_agent import DatabaseAugmentedStructuredExtraction
 from curate_gpt.agents.dragon_agent import DragonAgent
 from curate_gpt.extract.basic_extractor import BasicExtractor

tests/agents/test_dragon.py

@@ -1,5 +1,6 @@
 import pytest
 import yaml
+
 from curate_gpt.agents.dragon_agent import DragonAgent
 from curate_gpt.extract.basic_extractor import BasicExtractor
 

tests/agents/test_mapper.py

@@ -1,4 +1,5 @@
 import pytest
+
 from curate_gpt.agents import MappingAgent
 from curate_gpt.agents.mapping_agent import MappingPredicate
 from curate_gpt.extract import BasicExtractor

tests/cli/test_chat_cli.py

@@ -1,5 +1,4 @@
 from curate_gpt.cli import main
-
 from tests import INPUT_DIR
 
 ONT_DB = str(INPUT_DIR / "go-nucleus.db")

tests/cli/test_store_cli.py

@@ -1,5 +1,4 @@
 from curate_gpt.cli import main
-
 from tests import INPUT_DIR
 
 ONT_DB = str(INPUT_DIR / "go-nucleus.db")

tests/evaluation/conftest.py

@@ -1,9 +1,9 @@
 import pytest
+from oaklib import get_adapter
+
 from curate_gpt import ChromaDBAdapter
 from curate_gpt.store import SchemaProxy
 from curate_gpt.wrappers.ontology import ONTOLOGY_MODEL_PATH, OntologyWrapper
-from oaklib import get_adapter
-
 from tests import INPUT_DBS, INPUT_DIR
 
 

tests/evaluation/test_calculate_statistics.py

@@ -1,4 +1,5 @@
 import pytest
+
 from curate_gpt.evaluation.calc_statistics import (
     aggregate_metrics,
     calculate_metrics,

tests/evaluation/test_runner.py

@@ -1,8 +1,8 @@
 import pytest
 import yaml
+
 from curate_gpt.evaluation.evaluation_datamodel import Task
 from curate_gpt.evaluation.runner import run_task
-
 from tests import OUTPUT_DIR
 
 

tests/extract/test_extractor.py

@@ -1,13 +1,14 @@
 from typing import List
 
 import pytest
+from linkml_runtime.utils.schema_builder import SchemaBuilder
+from pydantic import BaseModel, ConfigDict
+
 from curate_gpt.extract.basic_extractor import BasicExtractor
 from curate_gpt.extract.extractor import AnnotatedObject
 from curate_gpt.extract.openai_extractor import OpenAIExtractor
 from curate_gpt.extract.recursive_extractor import RecursiveExtractor
 from curate_gpt.store.schema_proxy import SchemaProxy
-from linkml_runtime.utils.schema_builder import SchemaBuilder
-from pydantic import BaseModel, ConfigDict
 
 
 class Occupation(BaseModel):

tests/store/test_chromadb_adapter.py

@@ -1,18 +1,14 @@
-import json
 import shutil
-from dataclasses import dataclass
-from pathlib import Path
-from typing import Dict, Iterator
+from typing import Dict
 
 import pytest
 import yaml
-from curate_gpt.store.chromadb_adapter import ChromaDBAdapter
-from curate_gpt.store.schema_proxy import SchemaProxy
-from curate_gpt.wrappers.general.json_wrapper import JSONWrapper
-from curate_gpt.wrappers.ontology import ONTOLOGY_MODEL_PATH, OntologyWrapper
 from linkml_runtime.utils.schema_builder import SchemaBuilder
 from oaklib import get_adapter
 
+from curate_gpt.store.chromadb_adapter import ChromaDBAdapter
+from curate_gpt.store.schema_proxy import SchemaProxy
+from curate_gpt.wrappers.ontology import ONTOLOGY_MODEL_PATH, OntologyWrapper
 from tests import INPUT_DBS, INPUT_DIR, OUTPUT_CHROMA_DB_PATH, OUTPUT_DIR
 
 EMPTY_DB_PATH = OUTPUT_DIR / "empty_db"

tests/store/test_duckdb_adapter.py

@@ -1,21 +1,15 @@
-import itertools
 import os
 import shutil
-import time
-from dataclasses import dataclass
-from pathlib import Path
 from typing import Dict
 
 import pytest
 import yaml
+from linkml_runtime.utils.schema_builder import SchemaBuilder
+from oaklib import get_adapter
 
-from curate_gpt.store import CollectionMetadata
 from curate_gpt.store.duckdb_adapter import DuckDBAdapter
 from curate_gpt.store.schema_proxy import SchemaProxy
 from curate_gpt.wrappers.ontology import OntologyWrapper
-from linkml_runtime.utils.schema_builder import SchemaBuilder
-from oaklib import get_adapter
-
 from tests import INPUT_DBS, INPUT_DIR, OUTPUT_DIR, OUTPUT_DUCKDB_PATH
 
 EMPTY_DB_PATH = os.path.join(OUTPUT_DIR, "empty_duckdb")
@@ -165,7 +159,7 @@ def test_ontology_matches(ontology_db):
 
     first_obj = results[0][0]
     print("the id", first_obj["id"])
-    first_meta = results[0][2]
+    # first_meta = results[0][2]
     new_id, new_definition = "Palm Beach", "A beach with palm trees"
     updated_obj = {
         "id": new_id,

tests/store/test_in_memory_adapter.py

@@ -1,11 +1,11 @@
 from typing import Dict
 
 import pytest
+from linkml_runtime.utils.schema_builder import SchemaBuilder
+
 from curate_gpt import DBAdapter
 from curate_gpt.store import get_store
 from curate_gpt.store.schema_proxy import SchemaProxy
-from linkml_runtime.utils.schema_builder import SchemaBuilder
-
 from tests import OUTPUT_DIR
 
 EMPTY_DB_PATH = OUTPUT_DIR / "empty_db"

tests/utils/test_search.py

@@ -1,5 +1,6 @@
 import numpy as np
 import pytest
+
 from curate_gpt.utils.vector_algorithms import mmr_diversified_search
 
 vectors = np.array(

tests/wrappers/test_bioportal.py

@@ -1,11 +1,11 @@
 import logging
 
 import pytest
+
 from curate_gpt import ChromaDBAdapter
 from curate_gpt.extract import BasicExtractor
 from curate_gpt.wrappers.ontology.bioportal_wrapper import BioportalWrapper
 from curate_gpt.wrappers.ontology.ontology_wrapper import OntologyWrapper
-
 from tests import OUTPUT_DIR
 
 TEMP_OAKVIEW_DB = OUTPUT_DIR / "bioportal_tmp"

tests/wrappers/test_clinvar.py

@@ -4,12 +4,12 @@
 
 import pytest
 import yaml
+
 from curate_gpt import ChromaDBAdapter
 from curate_gpt.agents.chat_agent import ChatAgent
 from curate_gpt.agents.dragon_agent import DragonAgent
 from curate_gpt.extract import BasicExtractor
 from curate_gpt.wrappers.clinical.clinvar_wrapper import ClinVarWrapper
-
 from tests import INPUT_DIR, OUTPUT_DIR
 
 TEMP_DB = OUTPUT_DIR / "obj_tmp"

tests/wrappers/test_evidence_agent.py

@@ -4,12 +4,12 @@
 
 import pytest
 import yaml
+
 from curate_gpt import ChromaDBAdapter
 from curate_gpt.agents.evidence_agent import EvidenceAgent
 from curate_gpt.extract import BasicExtractor
 from curate_gpt.wrappers import BaseWrapper
 from curate_gpt.wrappers.literature import PubmedWrapper, WikipediaWrapper
-
 from tests import OUTPUT_DIR
 
 TEMP_PUBMED_DB = OUTPUT_DIR / "pmid_tmp"

tests/wrappers/test_gocam.py

@@ -2,8 +2,8 @@
 
 import pytest
 import yaml
-from curate_gpt.wrappers.bio.gocam_wrapper import GOCAMWrapper
 
+from curate_gpt.wrappers.bio.gocam_wrapper import GOCAMWrapper
 from tests import INPUT_DIR
 
 

tests/wrappers/test_hpoa.py

@@ -2,8 +2,8 @@
 
 import pytest
 import yaml
-from curate_gpt.wrappers.clinical.hpoa_wrapper import HPOAWrapper
 
+from curate_gpt.wrappers.clinical.hpoa_wrapper import HPOAWrapper
 from tests import INPUT_DIR, OUTPUT_DIR
 
 TEMP_DB = OUTPUT_DIR / "obj_tmp"

tests/wrappers/test_json.py

@@ -1,5 +1,4 @@
 from curate_gpt.wrappers import get_wrapper
-
 from tests import INPUT_DIR