langchain-ocr-lib 0.3.0__tar.gz → 0.3.2__tar.gz

{langchain_ocr_lib-0.3.0 → langchain_ocr_lib-0.3.2}/PKG-INFO

@@ -1,7 +1,7 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: langchain-ocr-lib
-Version: 0.3.0
-Summary: 
+Version: 0.3.2
+Summary: Modular, vision-LLM-powered chain to convert image and PDF documents into clean Markdown.
 License: MIT
 Author: Andreas Klos
 Author-email: aklos@outlook.de
@@ -25,9 +25,13 @@ Requires-Dist: pytest-asyncio (>=0.25.0,<0.26.0)
 Requires-Dist: pyyaml (>=6.0.2,<7.0.0)
 Description-Content-Type: text/markdown
 
-# langchain_ocr_lib
+# langchain-ocr-lib
 
-**langchain_ocr_lib** is the OCR processing engine behind LangChain-OCR. It provides a modular, vision-LLM-powered Chain to convert image and PDF documents into clean Markdown. Designed for direct CLI usage or integration into larger applications.
+**langchain-ocr-lib** is the OCR processing engine behind LangChain-OCR. It provides a modular, vision-LLM-powered Chain to convert image and PDF documents into clean Markdown. Designed for direct CLI usage or integration into larger applications.
+
+<div align="center">
+  <img src="./images/logo.png" alt="Logo" style="width:30%;">
+</div>
 
 ## Table of Contents
 
@@ -137,7 +141,7 @@ class Converter:
         return self._converter.convert2markdown(filename=filename)
 
 converter = Converter()
-markdown = converter.convert("../docs/invoice.pdf") # Adjust the file path as needed
+markdown = converter.convert("../examples/invoice.pdf") # Adjust the file path as needed
 print(markdown)
 ```
 
@@ -174,7 +178,7 @@ class Converter:
         self._converter.convert(filename=filename)
 
 converter = Converter()
-converter.convert("../docs/invoice.pdf") # Adjust the file path as needed
+converter.convert("../examples/invoice.pdf") # Adjust the file path as needed
 ```
 
 ### 4.3 Docker
@@ -183,6 +187,6 @@ Run OCR via Docker without local Python setup:
 
 ```bash
 docker build -t ocr -f langchain_ocr_lib/Dockerfile .
-docker run --net=host -it --rm -v ./docs:/app/docs:ro ocr docs/invoice.png
+docker run --net=host -it --rm -v ./examples:/app/examples:ro ocr examples/invoice.png
 ```
 

{langchain_ocr_lib-0.3.0 → langchain_ocr_lib-0.3.2}/README.md

@@ -1,6 +1,10 @@
-# langchain_ocr_lib
+# langchain-ocr-lib
 
-**langchain_ocr_lib** is the OCR processing engine behind LangChain-OCR. It provides a modular, vision-LLM-powered Chain to convert image and PDF documents into clean Markdown. Designed for direct CLI usage or integration into larger applications.
+**langchain-ocr-lib** is the OCR processing engine behind LangChain-OCR. It provides a modular, vision-LLM-powered Chain to convert image and PDF documents into clean Markdown. Designed for direct CLI usage or integration into larger applications.
+
+<div align="center">
+  <img src="./images/logo.png" alt="Logo" style="width:30%;">
+</div>
 
 ## Table of Contents
 
@@ -110,7 +114,7 @@ class Converter:
         return self._converter.convert2markdown(filename=filename)
 
 converter = Converter()
-markdown = converter.convert("../docs/invoice.pdf") # Adjust the file path as needed
+markdown = converter.convert("../examples/invoice.pdf") # Adjust the file path as needed
 print(markdown)
 ```
 
@@ -147,7 +151,7 @@ class Converter:
         self._converter.convert(filename=filename)
 
 converter = Converter()
-converter.convert("../docs/invoice.pdf") # Adjust the file path as needed
+converter.convert("../examples/invoice.pdf") # Adjust the file path as needed
 ```
 
 ### 4.3 Docker
@@ -156,5 +160,5 @@ Run OCR via Docker without local Python setup:
 
 ```bash
 docker build -t ocr -f langchain_ocr_lib/Dockerfile .
-docker run --net=host -it --rm -v ./docs:/app/docs:ro ocr docs/invoice.png
+docker run --net=host -it --rm -v ./examples:/app/examples:ro ocr examples/invoice.png
 ```

{langchain_ocr_lib-0.3.0 → langchain_ocr_lib-0.3.2}/pyproject.toml

@@ -1,5 +1,5 @@
 [build-system]
-requires = ["poetry-core==1.8.5"]
+requires = ["poetry-core==2.1.2"]
 build-backend = "poetry.core.masonry.api"
 
 [tool.poetry.scripts]
@@ -7,8 +7,8 @@ langchain-ocr = "langchain_ocr_lib.main:main"
 
 [tool.poetry]
 name = "langchain-ocr-lib"
-version = "0.3.0"
-description = ""
+version = "0.3.2"
+description = "Modular, vision-LLM-powered chain to convert image and PDF documents into clean Markdown."
 authors = ["Andreas Klos <aklos@outlook.de>"]
 readme = "README.md"
 packages = [{ include = "langchain_ocr_lib", from = "src" }]

{langchain_ocr_lib-0.3.0 → langchain_ocr_lib-0.3.2}/src/langchain_ocr_lib/di_config.py

@@ -14,6 +14,7 @@ from langchain_ocr_lib.di_binding_keys.binding_keys import (
 from langchain_ollama import ChatOllama
 from langchain_openai import ChatOpenAI
 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
@@ -50,16 +51,17 @@ def lib_di_config(binder: Binder):
 
     if llm_class_type_settings.llm_type == "ollama":
         settings = OllamaSettings()
-        llm_instance = llm_provider(settings, ChatOllama)
+        partial_llm_provider = partial(llm_provider,settings, ChatOllama)
     elif llm_class_type_settings.llm_type == "openai":
         settings = OpenAISettings()
-        llm_instance = llm_provider(settings, ChatOpenAI)
+        partial_llm_provider = partial(llm_provider,settings, ChatOpenAI)
     elif llm_class_type_settings.llm_type == "vllm":
         settings = VllmSettings()
-        llm_instance = llm_provider(settings, ChatOpenAI)
+        partial_llm_provider = partial(llm_provider,settings, ChatOpenAI)
     else:
         raise NotImplementedError("Configured LLM is not implemented")
-    binder.bind(LargeLanguageModelKey, llm_instance)
+    
+    binder.bind_to_provider(LargeLanguageModelKey, partial_llm_provider)
 
     prompt = ocr_prompt_template_builder(language=language_settings.language, model_name=settings.model)
 
@@ -78,17 +80,19 @@ def lib_di_config(binder: Binder):
             managed_prompts={
                 OcrChain.__name__: prompt,
             },
+            enabled=langfuse_settings.enabled,
         ),
     )
 
-    binder.bind(OcrChainKey, OcrChain())
+    binder.bind(OcrChainKey if langfuse_settings.enabled else LangfuseTracedChainKey, OcrChain())
 
-    binder.bind(
-        LangfuseTracedChainKey,
-        LangfuseTracedChain(
-            settings=langfuse_settings,
-        ),
-    )
+    if langfuse_settings.enabled:
+        binder.bind(
+            LangfuseTracedChainKey,
+            LangfuseTracedChain(
+                settings=langfuse_settings,
+            ),
+        )
 
     binder.bind(PdfConverterKey, Pdf2MarkdownConverter())
     binder.bind(ImageConverterKey, Image2MarkdownConverter())

{langchain_ocr_lib-0.3.0 → langchain_ocr_lib-0.3.2}/src/langchain_ocr_lib/impl/langfuse_manager/langfuse_manager.py

@@ -32,22 +32,10 @@ class LangfuseManager:
     def __init__(
         self,
         managed_prompts: dict[str, str],
+        enabled: bool = True,
     ):
         self._managed_prompts = managed_prompts
-
-    def init_prompts(self) -> None:
-        """
-        Initialize the prompts managed by the LangfuseManager.
-
-        This method iterates over the keys of the managed prompts and retrieves
-        each prompt using the `get_langfuse_prompt` method.
-
-        Returns
-        -------
-        None
-        """
-        for key in list(self._managed_prompts.keys()):
-            self.get_langfuse_prompt(key)
+        self._enabled = enabled
 
     def get_langfuse_prompt(self, base_prompt_name: str) -> Optional[ChatPromptClient]:
         """
@@ -70,6 +58,9 @@ class LangfuseManager:
         Exception
             If an error occurs while retrieving the prompt template from Langfuse.
         """
+        if not self._enabled:
+            logger.info("Langfuse is not enabled. Using fallback prompt.")
+            return None
         try:
             langfuse_prompt = self._langfuse.get_prompt(base_prompt_name)
         except NotFoundError:
@@ -86,11 +77,7 @@ class LangfuseManager:
             )
             langfuse_prompt = self._langfuse.get_prompt(base_prompt_name)
         except Exception as error:
-            logger.error(
-                "Error occured while getting prompt template from langfuse. Error:\n{error}",
-                extra={error: error},
-            )
-            return None
+            logger.error(f"Error occurred while getting prompt template from langfuse. Error:\n{error}")
         return langfuse_prompt
 
     def get_base_llm(self, name: str) -> LLM:
@@ -108,9 +95,12 @@ class LangfuseManager:
             The base Large Language Model. If the Langfuse prompt is not found,
             returns the LLM with a fallback configuration.
         """
+        if not self._enabled:
+            logger.info("Langfuse is not enabled. Using fallback LLM.")
+            return self._llm
         langfuse_prompt = self.get_langfuse_prompt(name)
         if not langfuse_prompt:
-            logger.error("Using fallback for llm")
+            logger.warning("Could not retrieve prompt template from langfuse. Using fallback LLM.")
             return self._llm
 
         return self._llm.with_config({"configurable": langfuse_prompt.config})
@@ -135,7 +125,8 @@ class LangfuseManager:
         """
         langfuse_prompt = self.get_langfuse_prompt(name)
         if not langfuse_prompt:
-            logger.error("Could not retrieve prompt template from langfuse. Using fallback value.")
+            if self._enabled:
+                logger.warning("Could not retrieve prompt template from langfuse. Using fallback value.")
             fallback = self._managed_prompts[name]
             if isinstance(fallback, ChatPromptTemplate):
                 return fallback

{langchain_ocr_lib-0.3.0 → langchain_ocr_lib-0.3.2}/src/langchain_ocr_lib/impl/settings/langfuse_settings.py

@@ -27,3 +27,7 @@ class LangfuseSettings(BaseSettings):
     secret_key: str = Field(default="", description="The secret key for Langfuse.")
     public_key: str = Field(default="", description="The public key for Langfuse.")
     host: str = Field(default="https://api.langchain.com", description="The host for Langfuse.")
+    enabled: bool = Field(
+        default=True,
+        description="Whether to enable Langfuse. If set to False, Langfuse will not be used.",
+    )

{langchain_ocr_lib-0.3.0 → langchain_ocr_lib-0.3.2}/src/langchain_ocr_lib/impl/settings/ollama_chat_settings.py

@@ -35,7 +35,7 @@ class OllamaSettings(BaseSettings):
         env_prefix = "OLLAMA_"
         case_sensitive = False
 
-    model: str = Field(default="gemma3:4b-it-q4_K_M")
+    model: str = Field(default="gemma3:4b-it-q4_K_M", title="LLM Model")
     base_url: str = Field(default="http://localhost:11434")
     top_k: int = Field(default=0, title="LLM Top K")
     top_p: float = Field(default=0, title="LLM Top P")

{langchain_ocr_lib-0.3.0 → langchain_ocr_lib-0.3.2}/src/langchain_ocr_lib/impl/settings/openai_chat_settings.py

@@ -28,10 +28,10 @@ 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")
+    model: str = Field(default="gpt-4o-mini-search-preview-2025-03-11", 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")
-    temperature: float = Field(default=0, description="What sampling temperature to use")
+    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",
         description="The base URL for the OpenAI API endpoint",

{langchain_ocr_lib-0.3.0 → langchain_ocr_lib-0.3.2}/src/langchain_ocr_lib/impl/settings/vllm_chat_settings.py

@@ -28,10 +28,10 @@ class VllmSettings(BaseSettings):
         env_prefix = "VLLM_"
         case_sensitive = False
 
-    model: str = Field(default="", description="The model identifier")
+    model: str = Field(default="", 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")
-    temperature: float = Field(default=0, description="What sampling temperature to use")
+    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",
         description="The base URL for the Vllm API endpoint",