Merge branch 'refactor/langchain_summarizer' into refactor/embedder

Author: a-klos

libs/admin-api-lib/src/admin_api_lib/dependency_container.py

@@ -66,7 +66,7 @@
 from rag_core_lib.impl.settings.rag_class_types_settings import RAGClassTypeSettings
 from rag_core_lib.impl.settings.retry_decorator_settings import RetryDecoratorSettings
 from rag_core_lib.impl.settings.stackit_vllm_settings import StackitVllmSettings
-from rag_core_lib.impl.tracers.langfuse_traced_chain import LangfuseTracedGraph
+from rag_core_lib.impl.tracers.langfuse_traced_runnable import LangfuseTracedRunnable
 from rag_core_lib.impl.utils.async_threadsafe_semaphore import AsyncThreadsafeSemaphore
 
 
@@ -151,7 +151,7 @@ class DependencyContainer(DeclarativeContainer):
         summary_enhancer,
     )
     information_enhancer = Singleton(
-        LangfuseTracedGraph,
+        LangfuseTracedRunnable,
         inner_chain=untraced_information_enhancer,
         settings=langfuse_settings,
     )

libs/admin-api-lib/src/admin_api_lib/information_enhancer/information_enhancer.py

@@ -6,13 +6,13 @@
 from langchain_core.documents import Document
 from langchain_core.runnables import RunnableConfig
 
-from rag_core_lib.chains.async_chain import AsyncChain
+from rag_core_lib.runnables.async_runnable import AsyncRunnable
 
 RetrieverInput = list[Document]
 RetrieverOutput = list[Document]
 
 
-class InformationEnhancer(AsyncChain[RetrieverInput, RetrieverOutput], ABC):
+class InformationEnhancer(AsyncRunnable[RetrieverInput, RetrieverOutput], ABC):
     """The base class for an information enhancer."""
 
     @abstractmethod

libs/admin-api-lib/src/admin_api_lib/summarizer/summarizer.py

@@ -5,13 +5,13 @@
 
 from langchain_core.runnables import RunnableConfig
 
-from rag_core_lib.chains.async_chain import AsyncChain
+from rag_core_lib.runnables.async_runnable import AsyncRunnable
 
 SummarizerInput = str
 SummarizerOutput = str
 
 
-class Summarizer(AsyncChain[SummarizerInput, SummarizerOutput], ABC):
+class Summarizer(AsyncRunnable[SummarizerInput, SummarizerOutput], ABC):
     """Baseclass for summarizers."""
 
     @abstractmethod

libs/extractor-api-lib/src/extractor_api_lib/impl/extractors/confluence_extractor.py

@@ -1,5 +1,6 @@
 """Module for the DefaultConfluenceExtractor class."""
 
+import logging
 from langchain_community.document_loaders import ConfluenceLoader
 
 from extractor_api_lib.impl.types.extractor_types import ExtractorTypes
@@ -10,6 +11,8 @@
     ConfluenceLangchainDocument2InformationPiece,
 )
 
+logger = logging.getLogger(__name__)
+
 
 class ConfluenceExtractor(InformationExtractor):
     """Implementation of the InformationExtractor interface for confluence."""
@@ -54,6 +57,13 @@ async def aextract_content(
         confluence_loader_parameters = {
             x.key: int(x.value) if x.value.isdigit() else x.value for x in extraction_parameters.kwargs
         }
+        if not confluence_loader_parameters.get("max_pages") or isinstance(
+            confluence_loader_parameters.get("max_pages"), str
+        ):
+            logging.warning(
+                "max_pages parameter is not set or invalid discarding it. ConfluenceLoader will use default value."
+            )
+            confluence_loader_parameters.pop("max_pages")
         # Drop the document_name parameter as it is not used by the ConfluenceLoader
         if "document_name" in confluence_loader_parameters:
             confluence_loader_parameters.pop("document_name", None)

libs/rag-core-api/src/rag_core_api/dependency_container.py

@@ -65,7 +65,7 @@
 from rag_core_lib.impl.settings.rag_class_types_settings import RAGClassTypeSettings
 from rag_core_lib.impl.settings.retry_decorator_settings import RetryDecoratorSettings
 from rag_core_lib.impl.settings.stackit_vllm_settings import StackitVllmSettings
-from rag_core_lib.impl.tracers.langfuse_traced_chain import LangfuseTracedGraph
+from rag_core_lib.impl.tracers.langfuse_traced_runnable import LangfuseTracedRunnable
 from rag_core_lib.impl.utils.async_threadsafe_semaphore import AsyncThreadsafeSemaphore
 
 
@@ -220,7 +220,7 @@ class DependencyContainer(DeclarativeContainer):
 
     # wrap graph in tracer
     traced_chat_graph = Singleton(
-        LangfuseTracedGraph,
+        LangfuseTracedRunnable,
         inner_chain=chat_graph,
         settings=langfuse_settings,
     )

libs/rag-core-api/src/rag_core_api/graph/graph_base.py

@@ -7,10 +7,10 @@
 from langchain_core.runnables.utils import Input, Output
 from langgraph.graph import StateGraph
 
-from rag_core_lib.chains.async_chain import AsyncChain
+from rag_core_lib.runnables.async_runnable import AsyncRunnable
 
 
-class GraphBase(AsyncChain[Input, Output], ABC):
+class GraphBase(AsyncRunnable[Input, Output], ABC):
     """
     Base class for a langgraph graph.
 

libs/rag-core-api/src/rag_core_api/impl/answer_generation_chains/answer_generation_chain.py

@@ -7,14 +7,14 @@
 from langchain_core.output_parsers import StrOutputParser
 
 from rag_core_api.impl.graph.graph_state.graph_state import AnswerGraphState
-from rag_core_lib.chains.async_chain import AsyncChain
+from rag_core_lib.runnables.async_runnable import AsyncRunnable
 from rag_core_lib.impl.langfuse_manager.langfuse_manager import LangfuseManager
 
 RunnableInput = AnswerGraphState
 RunnableOutput = str
 
 
-class AnswerGenerationChain(AsyncChain[RunnableInput, RunnableOutput]):
+class AnswerGenerationChain(AsyncRunnable[RunnableInput, RunnableOutput]):
     """Base class for LLM answer generation chain."""
 
     def __init__(self, langfuse_manager: LangfuseManager):

libs/rag-core-api/src/rag_core_api/impl/answer_generation_chains/rephrasing_chain.py

@@ -6,14 +6,14 @@
 from langchain_core.runnables import Runnable, RunnableConfig
 
 from rag_core_api.impl.graph.graph_state.graph_state import AnswerGraphState
-from rag_core_lib.chains.async_chain import AsyncChain
+from rag_core_lib.runnables.async_runnable import AsyncRunnable
 from rag_core_lib.impl.langfuse_manager.langfuse_manager import LangfuseManager
 
 RunnableInput = AnswerGraphState
 RunnableOutput = str
 
 
-class RephrasingChain(AsyncChain[RunnableInput, RunnableOutput]):
+class RephrasingChain(AsyncRunnable[RunnableInput, RunnableOutput]):
     """Base class for rephrasing of the input question."""
 
     def __init__(self, langfuse_manager: LangfuseManager):

libs/rag-core-api/src/rag_core_api/impl/api_endpoints/default_chat.py

@@ -5,13 +5,13 @@
 from rag_core_api.api_endpoints.chat import Chat
 from rag_core_api.models.chat_request import ChatRequest
 from rag_core_api.models.chat_response import ChatResponse
-from rag_core_lib.tracers.traced_chain import TracedGraph
+from rag_core_lib.tracers.traced_runnable import TracedRunnable
 
 
 class DefaultChat(Chat):
     """DefaultChat is a class that handles chat interactions using a traced graph."""
 
-    def __init__(self, chat_graph: TracedGraph):
+    def __init__(self, chat_graph: TracedRunnable):
         """
         Initialize the DefaultChat instance.
 

…ib/impl/tracers/langfuse_traced_chain.py …impl/tracers/langfuse_traced_runnable.pylibs/rag-core-lib/src/rag_core_lib/impl/tracers/langfuse_traced_chain.py renamed to libs/rag-core-lib/src/rag_core_lib/impl/tracers/langfuse_traced_runnable.py libs/rag-core-lib/src/rag_core_lib/impl/tracers/langfuse_traced_chain.py renamed to libs/rag-core-lib/src/rag_core_lib/impl/tracers/langfuse_traced_runnable.py

@@ -6,10 +6,10 @@
 from langfuse.langchain import CallbackHandler
 
 from rag_core_lib.impl.settings.langfuse_settings import LangfuseSettings
-from rag_core_lib.tracers.traced_chain import TracedGraph
+from rag_core_lib.tracers.traced_runnable import TracedRunnable
 
 
-class LangfuseTracedGraph(TracedGraph):
+class LangfuseTracedRunnable(TracedRunnable):
     """A class to trace the execution of a Runnable using Langfuse.
 
     This class wraps an inner Runnable and adds tracing capabilities using the Langfuse tracer.