Feature: Add openai_api_model attribute to Doctran models (#7868)

- Description: Added the ability to define the open AI model.
- Issue: Currently the Doctran instance uses gpt-4 by default, this does
not work if the user has no access to gpt -4.
  - rlancemartin, @eyurtsev, @baskaryan

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>

langchain/document_transformers/doctran_text_extract.py

@@ -53,11 +53,15 @@ class DoctranPropertyExtractor(BaseDocumentTransformer):
         self,
         properties: List[dict],
         openai_api_key: Optional[str] = None,
+        openai_api_model: Optional[str] = None,
     ) -> None:
         self.properties = properties
         self.openai_api_key = openai_api_key or get_from_env(
             "openai_api_key", "OPENAI_API_KEY"
         )
+        self.openai_api_model = openai_api_model or get_from_env(
+            "openai_api_model", "OPENAI_API_MODEL"
+        )
 
     def transform_documents(
         self, documents: Sequence[Document], **kwargs: Any
@@ -71,7 +75,9 @@ class DoctranPropertyExtractor(BaseDocumentTransformer):
         try:
             from doctran import Doctran, ExtractProperty
 
-            doctran = Doctran(openai_api_key=self.openai_api_key)
+            doctran = Doctran(
+                openai_api_key=self.openai_api_key, openai_model=self.openai_api_model
+            )
         except ImportError:
             raise ImportError(
                 "Install doctran to use this parser. (pip install doctran)"

langchain/document_transformers/doctran_text_qa.py

@@ -21,10 +21,17 @@ class DoctranQATransformer(BaseDocumentTransformer):
             transformed_document = await qa_transformer.atransform_documents(documents)
     """
 
-    def __init__(self, openai_api_key: Optional[str] = None) -> None:
+    def __init__(
+        self,
+        openai_api_key: Optional[str] = None,
+        openai_api_model: Optional[str] = None,
+    ) -> None:
         self.openai_api_key = openai_api_key or get_from_env(
             "openai_api_key", "OPENAI_API_KEY"
         )
+        self.openai_api_model = openai_api_model or get_from_env(
+            "openai_api_model", "OPENAI_API_MODEL"
+        )
 
     def transform_documents(
         self, documents: Sequence[Document], **kwargs: Any
@@ -38,7 +45,9 @@ class DoctranQATransformer(BaseDocumentTransformer):
         try:
             from doctran import Doctran
 
-            doctran = Doctran(openai_api_key=self.openai_api_key)
+            doctran = Doctran(
+                openai_api_key=self.openai_api_key, openai_model=self.openai_api_model
+            )
         except ImportError:
             raise ImportError(
                 "Install doctran to use this parser. (pip install doctran)"

langchain/document_transformers/doctran_text_translate.py

@@ -23,11 +23,17 @@ class DoctranTextTranslator(BaseDocumentTransformer):
     """
 
     def __init__(
-        self, openai_api_key: Optional[str] = None, language: str = "english"
+        self,
+        openai_api_key: Optional[str] = None,
+        language: str = "english",
+        openai_api_model: Optional[str] = None,
     ) -> None:
         self.openai_api_key = openai_api_key or get_from_env(
             "openai_api_key", "OPENAI_API_KEY"
         )
+        self.openai_api_model = openai_api_model or get_from_env(
+            "openai_api_model", "OPENAI_API_MODEL"
+        )
         self.language = language
 
     def transform_documents(
@@ -42,7 +48,9 @@ class DoctranTextTranslator(BaseDocumentTransformer):
         try:
             from doctran import Doctran
 
-            doctran = Doctran(openai_api_key=self.openai_api_key)
+            doctran = Doctran(
+                openai_api_key=self.openai_api_key, openai_model=self.openai_api_model
+            )
         except ImportError:
             raise ImportError(
                 "Install doctran to use this parser. (pip install doctran)"