langchain-ocr-lib 0.3.2__tar.gz → 0.4.0__tar.gz

{langchain_ocr_lib-0.3.2 → langchain_ocr_lib-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: langchain-ocr-lib
-Version: 0.3.2
+Version: 0.4.0
 Summary: Modular, vision-LLM-powered chain to convert image and PDF documents into clean Markdown.
 License: MIT
 Author: Andreas Klos
@@ -16,6 +16,7 @@ Requires-Dist: inject (>=5.2.1,<6.0.0)
 Requires-Dist: langchain-community (>=0.3.19,<0.4.0)
 Requires-Dist: langchain-ollama (>=0.2.0,<0.3.0)
 Requires-Dist: langchain-openai (>=0.3.8,<0.4.0)
+Requires-Dist: langchain-together (>=0.3.0,<0.4.0)
 Requires-Dist: langfuse (>=2.59.7,<3.0.0)
 Requires-Dist: openai (>=1.42.0,<2.0.0)
 Requires-Dist: pdf2image (>=1.17.0,<2.0.0)

{langchain_ocr_lib-0.3.2 → langchain_ocr_lib-0.4.0}/pyproject.toml

@@ -7,7 +7,7 @@ langchain-ocr = "langchain_ocr_lib.main:main"
 
 [tool.poetry]
 name = "langchain-ocr-lib"
-version = "0.3.2"
+version = "0.4.0"
 description = "Modular, vision-LLM-powered chain to convert image and PDF documents into clean Markdown."
 authors = ["Andreas Klos <aklos@outlook.de>"]
 readme = "README.md"
@@ -28,6 +28,7 @@ langfuse = "^2.59.7"
 pycountry = "^24.6.1"
 pdf2image = "^1.17.0"
 inject = "^5.2.1"
+langchain-together = "^0.3.0"
 
 [tool.poetry.group.dev.dependencies]
 debugpy = "^1.8.1"

{langchain_ocr_lib-0.3.2 → langchain_ocr_lib-0.4.0}/src/langchain_ocr_lib/di_config.py

@@ -13,11 +13,13 @@ from langchain_ocr_lib.di_binding_keys.binding_keys import (
 )
 from langchain_ollama import ChatOllama
 from langchain_openai import ChatOpenAI
+from langchain_together import ChatTogether
 from langfuse import Langfuse
 from functools import partial
 
 from langchain_ocr_lib.impl.chains.ocr_chain import OcrChain
 from langchain_ocr_lib.impl.settings.ollama_chat_settings import OllamaSettings
+from langchain_ocr_lib.impl.settings.together_ai_chat_settings import TogetherAISettings
 from langchain_ocr_lib.impl.settings.vllm_chat_settings import VllmSettings
 from langchain_ocr_lib.impl.settings.openai_chat_settings import OpenAISettings
 from langchain_ocr_lib.impl.settings.llm_class_type_settings import LlmClassTypeSettings
@@ -48,22 +50,29 @@ def lib_di_config(binder: Binder):
     langfuse_settings = LangfuseSettings()
     llm_class_type_settings = LlmClassTypeSettings()
     language_settings = LanguageSettings()
-
+    model_name = ""
     if llm_class_type_settings.llm_type == "ollama":
         settings = OllamaSettings()
-        partial_llm_provider = partial(llm_provider,settings, ChatOllama)
+        model_name = settings.model
+        partial_llm_provider = partial(llm_provider, settings, ChatOllama)
     elif llm_class_type_settings.llm_type == "openai":
         settings = OpenAISettings()
-        partial_llm_provider = partial(llm_provider,settings, ChatOpenAI)
+        model_name = settings.model_name
+        partial_llm_provider = partial(llm_provider, settings, ChatOpenAI)
     elif llm_class_type_settings.llm_type == "vllm":
         settings = VllmSettings()
-        partial_llm_provider = partial(llm_provider,settings, ChatOpenAI)
+        model_name = settings.model_name
+        partial_llm_provider = partial(llm_provider, settings, ChatOpenAI)
+    elif llm_class_type_settings.llm_type == "together-ai":
+        settings = TogetherAISettings()
+        model_name = settings.model_name
+        partial_llm_provider = partial(llm_provider, settings, ChatTogether)
     else:
         raise NotImplementedError("Configured LLM is not implemented")
-    
+
     binder.bind_to_provider(LargeLanguageModelKey, partial_llm_provider)
 
-    prompt = ocr_prompt_template_builder(language=language_settings.language, model_name=settings.model)
+    prompt = ocr_prompt_template_builder(language=language_settings.language, model_name=model_name)
 
     binder.bind(
         LangfuseClientKey,

{langchain_ocr_lib-0.3.2 → langchain_ocr_lib-0.4.0}/src/langchain_ocr_lib/impl/langfuse_manager/langfuse_manager.py

@@ -58,9 +58,10 @@ class LangfuseManager:
         Exception
             If an error occurs while retrieving the prompt template from Langfuse.
         """
+        langfuse_prompt = None
         if not self._enabled:
             logger.info("Langfuse is not enabled. Using fallback prompt.")
-            return None
+            return langfuse_prompt
         try:
             langfuse_prompt = self._langfuse.get_prompt(base_prompt_name)
         except NotFoundError:

{langchain_ocr_lib-0.3.2 → langchain_ocr_lib-0.4.0}/src/langchain_ocr_lib/impl/llms/llm_factory.py

@@ -43,6 +43,7 @@ def get_configurable_fields_from(settings: BaseSettings) -> dict[str, Configurab
         settings_of_interest = settings.model_fields[field_name]
         if settings_of_interest.title is not None:
             _fields[field_name] = ConfigurableField(id=field_name, name=settings_of_interest.title)
+
     return _fields
 
 

{langchain_ocr_lib-0.3.2 → langchain_ocr_lib-0.4.0}/src/langchain_ocr_lib/impl/llms/llm_type.py

@@ -10,3 +10,4 @@ class LLMType(StrEnum):
     OLLAMA = "ollama"
     OPENAI = "openai"
     VLLM = "vllm"
+    TOGETHER_AI = "together-ai"

{langchain_ocr_lib-0.3.2 → langchain_ocr_lib-0.4.0}/src/langchain_ocr_lib/impl/settings/openai_chat_settings.py

@@ -10,7 +10,7 @@ class OpenAISettings(BaseSettings):
 
     Attributes
     ----------
-    model : str
+    model_name : str
         The model identifier.
     api_key : str
         The API key for authentication.
@@ -28,9 +28,16 @@ class OpenAISettings(BaseSettings):
         env_prefix = "OPENAI_"
         case_sensitive = False
 
-    model: str = Field(default="gpt-4o-mini-search-preview-2025-03-11", description="The model identifier", title="LLM Model")
+    model_name: str = Field(
+        default="gpt-4o-mini-search-preview-2025-03-11",
+        env="MODEL",
+        description="The model identifier",
+        title="LLM Model",
+    )
     api_key: str = Field(default="", description="The API key for authentication")
-    top_p: float = Field(default=1.0, description="Total probability mass of tokens to consider at each step", title="Top P")
+    top_p: float = Field(
+        default=1.0, description="Total probability mass of tokens to consider at each step", title="Top P"
+    )
     temperature: float = Field(default=0, description="What sampling temperature to use", title="Temperature")
     base_url: str = Field(
         default="https://api.openai.com/v1",

langchain_ocr_lib-0.4.0/src/langchain_ocr_lib/impl/settings/together_ai_chat_settings.py

@@ -0,0 +1,45 @@
+"""Module contains settings regarding the Together AI API."""
+
+from pydantic import Field
+from pydantic_settings import BaseSettings
+
+
+class TogetherAISettings(BaseSettings):
+    """
+    Contains settings regarding the Together AI API.
+
+    Attributes
+    ----------
+    model_name : str
+        The Together AI model identifier.
+    together_api_key : str
+        The API key for authentication.
+    top_p : float
+        Total probability mass of tokens to consider at each step.
+    temperature : float
+        What sampling temperature to use.
+    together_api_base : str
+        The base URL for the Together AI API endpoint.
+    """
+
+    class Config:
+        """Config class for reading fields from environment variables."""
+
+        env_prefix = "TOGETHER_"
+        case_sensitive = False
+
+    model_name: str = Field(
+        default="",
+        description="The Together AI model identifier",
+        title="Together AI Model",
+    )
+    together_api_key: str = Field(default="", description="The API key for authentication")
+    top_p: float = Field(
+        default=1.0, description="Total probability mass of tokens to consider at each step", title="Top P"
+    )
+    temperature: float = Field(default=0, description="What sampling temperature to use", title="Temperature")
+    together_api_base: str = Field(
+        default="https://api.together.xyz/v1/",
+        env="API_BASE",
+        description="The base URL for the Together AI API endpoint",
+    )

{langchain_ocr_lib-0.3.2 → langchain_ocr_lib-0.4.0}/src/langchain_ocr_lib/impl/settings/vllm_chat_settings.py

@@ -10,7 +10,7 @@ class VllmSettings(BaseSettings):
 
     Attributes
     ----------
-    model : str
+    model_name : str
         The model identifier.
     api_key : str
         The API key for authentication.
@@ -28,9 +28,16 @@ class VllmSettings(BaseSettings):
         env_prefix = "VLLM_"
         case_sensitive = False
 
-    model: str = Field(default="", description="The model identifier", title="LLM Model")
+    model_name: str = Field(
+        default="",
+        env="MODEL",
+        description="The model identifier",
+        title="LLM Model",
+    )
     api_key: str = Field(default="", description="The API key for authentication")
-    top_p: float = Field(default=1.0, description="Total probability mass of tokens to consider at each step", title="Top P")
+    top_p: float = Field(
+        default=1.0, description="Total probability mass of tokens to consider at each step", title="Top P"
+    )
     temperature: float = Field(default=0, description="What sampling temperature to use", title="Temperature")
     base_url: str = Field(
         default="http://localhost:8000/v1",