Improve Information Extraction Tools and extract common utilities

libs/upstage/.gitignore

@@ -1 +1,3 @@
 __pycache__
+.mypy_cache
+.mypy_cache_test

libs/upstage/langchain_upstage/__init__.py

@@ -2,10 +2,10 @@
 from langchain_upstage.document_parse import UpstageDocumentParseLoader
 from langchain_upstage.document_parse_parsers import UpstageDocumentParseParser
 from langchain_upstage.embeddings import UpstageEmbeddings
-from langchain_upstage.prebuilt_information_extraction import (
+from langchain_upstage.tools.prebuilt_information_extraction import (
     UpstagePrebuiltInformationExtraction,
 )
-from langchain_upstage.universal_information_extraction import (
+from langchain_upstage.tools.universal_information_extraction import (
     UpstageUniversalInformationExtraction,
 )
 

libs/upstage/langchain_upstage/document_parse.py

@@ -15,6 +15,7 @@
     SplitType,
     UpstageDocumentParseParser,
 )
+from langchain_upstage.utils.value_retriever import get_from_param_or_env
 
 logger = logging.getLogger("pypdf")
 logger.setLevel(logging.ERROR)
@@ -37,27 +38,6 @@ def validate_file_path(file_path: Union[str, Path, List[str], List[Path]]) -> No
         raise FileNotFoundError(f"File not found: {file_path}")
 
 
-def get_from_param_or_env(
-    key: str,
-    param: Optional[str] = None,
-    env_key: Optional[str] = None,
-    default: Optional[str] = None,
-) -> str:
-    """Get a value from a param or an environment variable."""
-    if param is not None:
-        return param
-    elif env_key and env_key in os.environ and os.environ[env_key]:
-        return os.environ[env_key]
-    elif default is not None:
-        return default
-    else:
-        raise ValueError(
-            f"Did not find {key}, please add an environment variable"
-            f" `{env_key}` which contains it, or pass"
-            f"  `{key}` as a named parameter."
-        )
-
-
 class UpstageDocumentParseLoader(BaseLoader):
     """Upstage Document Parse Loader.
 

libs/upstage/langchain_upstage/document_parse_parsers.py

@@ -9,7 +9,8 @@
 from pypdf import PdfReader, PdfWriter
 from pypdf.errors import PdfReadError
 
-from langchain_upstage.tools.response_generator import make_request
+from langchain_upstage.utils.response_generator import make_request
+from langchain_upstage.utils.value_retriever import get_from_param_or_env
 
 logger = logging.getLogger("pypdf")
 logger.setLevel(logging.ERROR)
@@ -62,27 +63,6 @@ def parse_output(data: dict, output_format: OutputFormat) -> str:
         raise ValueError(f"Invalid output type: {output_format}")
 
 
-def get_from_param_or_env(
-    key: str,
-    param: Optional[str] = None,
-    env_key: Optional[str] = None,
-    default: Optional[str] = None,
-) -> str:
-    """Get a value from a param or an environment variable."""
-    if param is not None:
-        return param
-    elif env_key and env_key in os.environ and os.environ[env_key]:
-        return os.environ[env_key]
-    elif default is not None:
-        return default
-    else:
-        raise ValueError(
-            f"Did not find {key}, please add an environment variable"
-            f" `{env_key}` which contains it, or pass"
-            f"  `{key}` as a named parameter."
-        )
-
-
 class UpstageDocumentParseParser(BaseBlobParser):
     """Upstage Document Parse Parser.