refactor: rephrasing chain and chat graph (#145)

Adjust the rephrasing chain prompt, increase fault tolerance and adjust
chat graph connections, so that the nodes are executed sequentially. Adjust determine language node in answer graph. Its now based on llms and has as fallback langdetect and as fallback from langdetect, 'en'.

Author: robodev-r2d2

libs/README.md

@@ -90,12 +90,14 @@ Uploaded documents are required to contain the following metadata:
 | composed_retriever | [`rag_core_api.retriever.retriever.Retriever`](./rag-core-api/src/rag_core_api/retriever/retriever.py) | [`rag_core_api.impl.retriever.composite_retriever.CompositeRetriever`](./rag-core-api/src/rag_core_api/impl/retriever/composite_retriever.py) | Handles retrieval, re-ranking, etc. |
 | large_language_model | `langchain_core.language_models.llms.BaseLLM` | `langchain_community.llms.vllm.VLLMOpenAI`, `langchain_community.llms.Ollama` or `langchain_community.llms.FakeListLLM` | The LLm that is used for all LLM tasks. The default depends on the value of `rag_core_lib.impl.settings.rag_class_types_settings.RAGClassTypeSettings.llm_type`. The FakeListLLM is used for testing |
 | prompt | `str` | [`rag_core_api.prompt_templates.answer_generation_prompt.ANSWER_GENERATION_PROMPT`](./rag-core-api/src/rag_core_api/prompt_templates/answer_generation_prompt.py) | The prompt used for answering the question. |
-| rephrasing_prompt | `str` |  [`rag_core_api.prompt_templates.question_rephrasing_prompt.ANSWER_REPHRASING_PROMPT`](./rag-core-api/src/rag_core_api/prompt_templates/question_rephrasing_prompt.py) | The prompt used for rephrasing the question. The rephrased question (and the *original* question are both used for retrival of the documents)|
+| rephrasing_prompt | `str` |  [`rag_core_api.prompt_templates.question_rephrasing_prompt.ANSWER_REPHRASING_PROMPT`](./rag-core-api/src/rag_core_api/prompt_templates/question_rephrasing_prompt.py) | The prompt used for rephrasing the question. The rephrased question (and the *original* question are both used for retrival of the documents) |
+| language_detection_prompt | `str` | [`rag_core_api.prompt_templates.language_detection_prompt.LANGUAGE_DETECTION_PROMPT`](./rag-core-api/src/rag_core_api/prompt_templates/language_detection_prompt.py) | Prompt for detecting input language. Enforces structured JSON output `{ "language": "<iso639-1>" }` and defaults to `en` when uncertain. |
 | langfuse_manager | [`rag_core_lib.impl.langfuse_manager.langfuse_manager.LangfuseManager`](./rag-core-lib/src/rag_core_lib/impl/langfuse_manager/langfuse_manager.py) | [`rag_core_lib.impl.langfuse_manager.langfuse_manager.LangfuseManager`](./rag-core-lib/src/rag_core_lib/impl/langfuse_manager/langfuse_manager.py) | Retrieves additional settings, as well as the prompt from langfuse if available. |
-| answer_generation_chain | [`rag_core_lib.chains.async_chain.AsyncChain[rag_core_api.impl.graph.graph_state.graph_state.AnswerGraphState, str]`](./rag-core-lib/src/rag_core_lib/chains/async_chain.py) | [`rag_core_api.impl.answer_generation_chains.answer_generation_chain.AnswerGenerationChain`](./rag-core-api/src/rag_core_api/impl/answer_generation_chains/answer_generation_chain.py) | LangChain chain used for answering the question. Is part of the *chat_graph*, |
-| rephrasing_chain | [`rag_core_lib.chains.async_chain.AsyncChain[rag_core_api.impl.graph.graph_state.graph_state.AnswerGraphState, str]`](./rag-core-lib/src/rag_core_lib/chains/async_chain.py) | [`rag_core_api.impl.answer_generation_chains.rephrasing_chain.RephrasingChain`](./rag-core-api/src/rag_core_api/impl/answer_generation_chains/rephrasing_chain.py) | LangChain chain used for rephrasing the question. Is part of the *chat_graph*. |
+| answer_generation_chain | [`rag_core_lib.chains.runnables.AsyncRunnable[rag_core_api.impl.graph.graph_state.graph_state.AnswerGraphState, str]`](./rag-core-lib/src/rag_core_lib/runnables/async_runnable.py) | [`rag_core_api.impl.answer_generation_chains.answer_generation_chain.AnswerGenerationChain`](./rag-core-api/src/rag_core_api/impl/answer_generation_chains/answer_generation_chain.py) | LangChain chain used for answering the question. Is part of the *chat_graph*, |
+| rephrasing_chain | [`rag_core_lib.chains.runnables.AsyncRunnable[rag_core_api.impl.graph.graph_state.graph_state.AnswerGraphState, str]`](./rag-core-lib/src/rag_core_lib/runnables/async_runnable.py) | [`rag_core_api.impl.answer_generation_chains.rephrasing_chain.RephrasingChain`](./rag-core-api/src/rag_core_api/impl/answer_generation_chains/rephrasing_chain.py) | LangChain chain used for rephrasing the question. Is part of the *chat_graph*. |
+| language_detection_chain | [`rag_core_lib.chains.runnables.AsyncRunnable[rag_core_api.impl.graph.graph_state.graph_state.AnswerGraphState, str]`](./rag-core-lib/src/rag_core_lib/runnables/async_runnable.py) | [`rag_core_api.impl.answer_generation_chains.language_detection_chain.LanguageDetectionChain`](./rag-core-api/src/rag_core_api/impl/answer_generation_chains/language_detection_chain.py) | Detects the language of the question and returns an ISO 639-1 code (e.g., `en`, `de`). Uses structured-output guidance and robust parsing with fallback to `en`. Part of the *chat_graph*. |
 | chat_graph | [`rag_core_api.graph.graph_base.GraphBase`](./rag-core-api/src/rag_core_api/graph/graph_base.py) | [`rag_core_api.impl.graph.chat_graph.DefaultChatGraph`](./rag-core-api/src/rag_core_api/impl/graph/chat_graph.py) | Langgraph graph that contains the entire logic for question answering. |
-| traced_chat_graph | [`rag_core_lib.chains.async_chain.AsyncChain[Any, Any]`](./rag-core-lib/src/rag_core_lib/chains/async_chain.py)| [`rag_core_lib.impl.tracers.langfuse_traced_chain.LangfuseTracedGraph`](./rag-core-lib/src/rag_core_lib/impl/tracers/langfuse_traced_chain.py) | Wraps around the *chat_graph* and add langfuse tracing. |
+| traced_chat_graph | [`rag_core_lib.chains.runnables.AsyncRunnable[Any, Any]`](./rag-core-lib/src/rag_core_lib/runnables/async_runnable.py)| [`rag_core_lib.impl.tracers.langfuse_traced_chain.LangfuseTracedGraph`](./rag-core-lib/src/rag_core_lib/impl/tracers/langfuse_traced_chain.py) | Wraps around the *chat_graph* and add langfuse tracing. |
 | evaluator | [`rag_core_api.impl.evaluator.langfuse_ragas_evaluator.LangfuseRagasEvaluator`](./rag-core-api/src/rag_core_api/impl/evaluator/langfuse_ragas_evaluator.py) | [`rag_core_api.impl.evaluator.langfuse_ragas_evaluator.LangfuseRagasEvaluator`](./rag-core-api/src/rag_core_api/impl/evaluator/langfuse_ragas_evaluator.py) | The evaulator used in the evaluate endpoint. |
 | chat_endpoint | [`rag_core_api.api_endpoints.chat.Chat`](./rag-core-api/src/rag_core_api/api_endpoints/chat.py) | [`rag_core_api.impl.api_endpoints.default_chat.DefaultChat`](./rag-core-api/src/rag_core_api/impl/api_endpoints/default_chat.py) | Implementation of the chat endpoint. Default implementation just calls the *traced_chat_graph* |
 | ragas_llm | `langchain_core.language_models.chat_models.BaseChatModel` | `langchain_openai.ChatOpenAI` or `langchain_ollama.ChatOllama` | The LLM used for the ragas evaluation. |
@@ -191,7 +193,7 @@ The extracted information will be summarized using LLM. The summary, as well as
 | langfuse_manager | [`rag_core_lib.impl.langfuse_manager.langfuse_manager.LangfuseManager`](./rag-core-lib/src/rag_core_lib/impl/langfuse_manager/langfuse_manager.py) | [`rag_core_lib.impl.langfuse_manager.langfuse_manager.LangfuseManager`](./rag-core-lib/src/rag_core_lib/impl/langfuse_manager/langfuse_manager.py) | Retrieves additional settings, as well as the prompt from langfuse if available. |
 | summarizer |  [`admin_api_lib.summarizer.summarizer.Summarizer`](./admin-api-lib/src/admin_api_lib/summarizer/summarizer.py) | [`admin_api_lib.impl.summarizer.langchain_summarizer.LangchainSummarizer`](./admin-api-lib/src/admin_api_lib/impl/summarizer/langchain_summarizer.py) | Creates the summaries. Uses the shared retry decorator with optional per-summarizer overrides (see 2.4). |
 | untraced_information_enhancer |[`admin_api_lib.information_enhancer.information_enhancer.InformationEnhancer`](./admin-api-lib/src/admin_api_lib/information_enhancer/information_enhancer.py) | [`admin_api_lib.impl.information_enhancer.general_enhancer.GeneralEnhancer`](./admin-api-lib/src/admin_api_lib/impl/information_enhancer/general_enhancer.py) |  Uses the *summarizer* to enhance the extracted documents. |
-| information_enhancer |  [`rag_core_lib.chains.async_chain.AsyncChain[Any, Any]`](./rag-core-lib/src/rag_core_lib/chains/async_chain.py)| [`rag_core_lib.impl.tracers.langfuse_traced_chain.LangfuseTracedGraph`](./rag-core-lib/src/rag_core_lib/impl/tracers/langfuse_traced_chain.py) |Wraps around the *untraced_information_enhancer* and adds langfuse tracing. |
+| information_enhancer |  [`rag_core_lib.chains.runnables.AsyncRunnable[Any, Any]`](./rag-core-lib/src/rag_core_lib/runnables/async_runnable.py)| [`rag_core_lib.impl.tracers.langfuse_traced_chain.LangfuseTracedGraph`](./rag-core-lib/src/rag_core_lib/impl/tracers/langfuse_traced_chain.py) |Wraps around the *untraced_information_enhancer* and adds langfuse tracing. |
 | document_deleter |[`admin_api_lib.api_endpoints.document_deleter.DocumentDeleter`](./admin-api-lib/src/admin_api_lib/api_endpoints/document_deleter.py) | [`admin_api_lib.impl.api_endpoints.default_document_deleter.DefaultDocumentDeleter`](./admin-api-lib/src/admin_api_lib/impl/api_endpoints/default_document_deleter.py) |  Handles deletion of sources. |
 | documents_status_retriever |  [`admin_api_lib.api_endpoints.documents_status_retriever.DocumentsStatusRetriever`](./admin-api-lib/src/admin_api_lib/api_endpoints/documents_status_retriever.py) | [`admin_api_lib.impl.api_endpoints.default_documents_status_retriever.DefaultDocumentsStatusRetriever`](./admin-api-lib/src/admin_api_lib/impl/api_endpoints/default_documents_status_retriever.py) |Handles return of source status. |
 | source_uploader | [`admin_api_lib.api_endpoints.source_uploader.SourceUploader`](./admin-api-lib/src/admin_api_lib/api_endpoints/source_uploader.py) | [`admin_api_lib.impl.api_endpoints.default_source_uploader.DefaultSourceUploader`](./admin-api-lib/src/admin_api_lib/impl/api_endpoints/default_source_uploader.py)| Handles data loading and extraction from various non-file sources. |

libs/admin-api-lib/src/admin_api_lib/impl/file_services/s3_service.py

@@ -1,7 +1,6 @@
 """Class to handle I/O with S3 storage."""
 
 import logging
-import traceback
 from pathlib import Path
 from typing import BinaryIO
 
@@ -125,7 +124,7 @@ def delete_file(self, file_name: str) -> None:
         try:
             file_name = f"/{file_name}" if not file_name.startswith("/") else file_name
             self._s3_client.delete_object(Bucket=self._s3_settings.bucket, Key=file_name)
-            logger.info(f"File {file_name} successfully deleted.")
-        except Exception as e:
-            logger.error("Error deleting file %s: %s %s" % (file_name, e, traceback.format_exc()))
+            logger.info("File %s successfully deleted.", file_name)
+        except Exception:
+            logger.exception("Error deleting file %s", file_name)
             raise

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

@@ -154,8 +154,8 @@ async def aextract_content(self, file_path: Path, name: str) -> list[InternalInf
                     )
                     pdf_elements += new_pdf_elements
 
-        logger.info(f"Extraction completed. Found {len(pdf_elements)} information pieces.")
-        return pdf_elements
+            logger.info("Extraction completed. Found %d information pieces.", len(pdf_elements))
+            return pdf_elements
 
     def _is_text_based(self, page: Page) -> bool:
         """Classify whether a page is text-based, scanned.
@@ -200,8 +200,8 @@ def _extract_tables_from_text_page(
                 table_df = pd.DataFrame(table_data)
                 try:
                     converted_table = self._dataframe_converter.convert(table_df)
-                except TypeError as e:
-                    logger.error(f"Error while converting table to string: {e}")
+                except TypeError:
+                    logger.exception("Error while converting table to string")
                     continue
                 if not converted_table.strip():
                     continue
@@ -215,8 +215,8 @@ def _extract_tables_from_text_page(
                         information_id=hash_datetime(),
                     )
                 )
-        except Exception as e:
-            logger.warning(f"Failed to find tables on page {page_index}: {e}")
+        except Exception:
+            logger.warning("Failed to find tables on page %d", page_index, exc_info=True)
 
         return table_elements
 
@@ -321,19 +321,19 @@ def _extract_tables_from_scanned_page(
                                     },
                                 )
                             )
-                    except Exception as e:
-                        logger.warning(f"Failed to convert Camelot table {i + 1}: {e}")
+                    except Exception:
+                        logger.warning("Failed to convert Camelot table %d", i + 1, exc_info=True)
 
-        except Exception as e:
-            logger.debug(f"Camelot table extraction failed for page {page_index}: {e}")
+        except Exception:
+            logger.debug("Camelot table extraction failed for page %d", page_index, exc_info=True)
 
         return table_elements
 
     def _extract_text_from_text_page(self, page: Page) -> str:
         try:
             return page.extract_text() or ""
-        except Exception as e:
-            logger.warning(f"Failed to extract text with pdfplumber: {e}")
+        except Exception:
+            logger.warning("Failed to extract text with pdfplumber", exc_info=True)
             return ""
 
     def _extract_content_from_page(

libs/extractor-api-lib/tests/pdf_extractor_test.py

@@ -551,8 +551,8 @@ async def test_end_to_end_extraction(self, pdf_extractor, test_pdf_files):
             text_count = sum(1 for elem in result if elem.type == ContentType.TEXT)
             table_count = sum(1 for elem in result if elem.type == ContentType.TABLE)
 
-            logger.info(f"  Text elements: {text_count}")
-            logger.info(f"  Table elements: {table_count}")
+            logger.info("  Text elements: %d", text_count)
+            logger.info("  Table elements: %d", table_count)
 
             # Verify metadata completeness
             for i, element in enumerate(result):

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

@@ -19,6 +19,7 @@
     AnswerGenerationChain,
 )
 from rag_core_api.impl.answer_generation_chains.rephrasing_chain import RephrasingChain
+from rag_core_api.impl.answer_generation_chains.language_detection_chain import LanguageDetectionChain
 from rag_core_api.impl.api_endpoints.default_chat import DefaultChat
 from rag_core_api.impl.api_endpoints.default_information_pieces_remover import (
     DefaultInformationPiecesRemover,
@@ -57,6 +58,7 @@
 from rag_core_api.prompt_templates.question_rephrasing_prompt import (
     QUESTION_REPHRASING_PROMPT,
 )
+from rag_core_api.prompt_templates.language_detection_prompt import LANGUAGE_DETECTION_PROMPT
 from rag_core_lib.impl.data_types.content_type import ContentType
 from rag_core_lib.impl.langfuse_manager.langfuse_manager import LangfuseManager
 from rag_core_lib.impl.llms.llm_factory import chat_model_provider
@@ -180,6 +182,7 @@ class DependencyContainer(DeclarativeContainer):
 
     prompt = ANSWER_GENERATION_PROMPT
     rephrasing_prompt = QUESTION_REPHRASING_PROMPT
+    language_detection_prompt = LANGUAGE_DETECTION_PROMPT
 
     langfuse = Singleton(
         Langfuse,
@@ -194,6 +197,7 @@ class DependencyContainer(DeclarativeContainer):
         managed_prompts={
             AnswerGenerationChain.__name__: prompt,
             RephrasingChain.__name__: rephrasing_prompt,
+            LanguageDetectionChain.__name__: language_detection_prompt,
         },
         llm=large_language_model,
     )
@@ -208,10 +212,16 @@ class DependencyContainer(DeclarativeContainer):
         langfuse_manager=langfuse_manager,
     )
 
+    language_detection_chain = Singleton(
+        LanguageDetectionChain,
+        langfuse_manager=langfuse_manager,
+    )
+
     chat_graph = Singleton(
         DefaultChatGraph,
         composed_retriever=composed_retriever,
         rephrasing_chain=rephrasing_chain,
+        language_detection_chain=language_detection_chain,
         mapper=information_piece_mapper,
         answer_generation_chain=answer_generation_chain,
         error_messages=error_messages,