allow execution without using the "--mapping" parameter

bsllmner2/cli_extract.py

@@ -2,7 +2,6 @@
 import asyncio
 import sys
 from pathlib import Path
-from typing import List, Tuple
 
 from bsllmner2.client.ollama import ner
 from bsllmner2.config import (LOGGER, PROMPT_EXTRACT_FILE_PATH, Config,
@@ -14,7 +13,7 @@
                              load_prompt_file, to_result)
 
 
-def parse_args(args: List[str]) -> Tuple[Config, CliExtractArgs]:
+def parse_args(args: list[str]) -> tuple[Config, CliExtractArgs]:
     """
     Parse command-line arguments for the bsllmner2 CLI extract mode.
 
@@ -33,8 +32,9 @@ def parse_args(args: List[str]) -> Tuple[Config, CliExtractArgs]:
     parser.add_argument(
         "--mapping",
         type=Path,
-        required=True,
+        required=False,
         help="Path to the mapping file in TSV format.",
+        default = Path.cwd()
     )
     parser.add_argument(
         "--prompt",

bsllmner2/schema.py

@@ -1,5 +1,5 @@
 from pathlib import Path
-from typing import Any, Dict, List, Literal, Optional
+from typing import Any, Literal, Optional
 
 from ollama import ChatResponse
 from pydantic import BaseModel, Field
@@ -10,7 +10,6 @@
 
 API_VERSION = "1.0.0"
 
-
 class CliExtractArgs(BaseModel):
     """
     Command-line arguments for the bsllmner2 CLI extract mode.
@@ -67,7 +66,7 @@ class Prompt(BaseModel):
     )
 
 
-BsEntries = List[Dict[str, Any]]
+BsEntries = list[dict[str, Any]]
 
 
 class MappingValue(BaseModel):
@@ -77,13 +76,13 @@ class MappingValue(BaseModel):
     mapping_answer_label: Optional[str]
 
 
-Mapping = Dict[str, MappingValue]  # key: bs_entry accession
+Mapping = dict[str, MappingValue]  # key: bs_entry accession
 
 
 class WfInput(BaseModel):
     bs_entries: BsEntries
     mapping: Mapping
-    prompt: List[Prompt]
+    prompt: list[Prompt]
     model: str
     thinking: Optional[bool] = None
     format: Optional[JsonSchemaValue] = None
@@ -95,7 +94,7 @@ class LlmOutput(BaseModel):
     accession: str
     output: Optional[Any] = None
     output_full: Optional[str] = None
-    characteristics: Optional[Dict[str, Any]] = None
+    characteristics: Optional[dict[str, Any]] = None
     taxId: Optional[Any] = None
     chat_response: ChatResponse
 
@@ -135,8 +134,8 @@ class ErrorLog(BaseModel):
 
 class Result(BaseModel):
     input: WfInput
-    output: List[LlmOutput] = []
-    evaluation: List[Evaluation] = []
-    metrics: Optional[List[Metrics]] = None
+    output: list[LlmOutput] = []
+    evaluation: list[Evaluation] = []
+    metrics: Optional[list[Metrics]] = None
     run_metadata: RunMetadata
     error_log: Optional[ErrorLog] = None

bsllmner2/utils.py

@@ -76,10 +76,13 @@ def load_mapping(path: Path) -> Mapping:
 
     mapping: Mapping = {}
 
-    with path.open("r", encoding="utf-8") as f:
-        lines = [line.rstrip("\n") for line in f if line.strip()]
-    if not lines:
-        return {}
+    if path.is_file():
+        with path.open("rt", encoding="utf-8") as f:
+            lines = [line.rstrip("\n") for line in f if line.strip()]
+            if not lines:
+                return mapping
+    else:
+        return mapping
 
     header_fields = lines[0].split("\t")
     if header_fields != HEADERS: