test: add function tests for the rag core api

Author: a-klos

libs/.gitignore

@@ -0,0 +1 @@
+.vscode

libs/README.md

@@ -83,7 +83,7 @@ Uploaded documents are required to contain the following metadata:
 | vector_database | [`rag_core_api.vector_databases.vector_database.VectorDatabase`](./rag-core-api/src/rag_core_api/vector_databases/vector_database.py) | [`rag_core_api.impl.vector_databases.qdrant_database.QdrantDatabase`](./rag-core-api/src/rag_core_api/impl/vector_databases/qdrant_database.py) | |
 | reranker | [`rag_core_api.reranking.reranker.Reranker`](./rag-core-api/src/rag_core_api/reranking/reranker.py)  | [`rag_core_api.impl.reranking.flashrank_reranker.FlashrankReranker`](./rag-core-api/src/rag_core_api/impl/reranking/flashrank_reranker.py) | Used in the *composed_retriever* |
 | 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` or `langchain_community.llms.Ollama` | 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` |
+| 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)|
 | 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. |

libs/extractor-api-lib/src/openapi_server/impl/__init__.py

@@ -111,7 +111,7 @@ celerybeat.pid
 
 # Environments
 .env
-.venv
+.venv*
 env/
 venv/
 ENV/

libs/rag-core-api/.gitignore

@@ -0,0 +1 @@
+3.11.11

libs/rag-core-api/.python-version

@@ -27,6 +27,7 @@ openai = "^1.42.0"
 langgraph = "^0.2.23"
 pillow = "^11.0.0"
 langchain-ollama = "^0.2.0"
+pytest-asyncio = "^0.25.0"
 
 [tool.poetry.group.dev.dependencies]
 debugpy = "^1.8.1"
@@ -78,7 +79,8 @@ per-file-ignores = """
   ./src/rag_core_api/prompt_templates/*: E501,
   ./src/rag_core_api/dependency_container.py: CCE002,CCE001,
   ./src/rag_core_api/apis/rag_api_base.py: WOT001,
-  ./tests/*: S101,
+  ./tests/rag_api_test.py: E402,S101,S105,I252,D409,
+  ./tests/*: S101,S105,I252,D409,
 """
 
 [tool.black]
@@ -114,4 +116,6 @@ max-line-length = 120
 [tool.pytest.ini_options]
 log_cli = 1
 log_cli_level = "DEBUG"
+pythonpath = "src"
+testpaths = "src/tests"
 

libs/rag-core-api/poetry.lock

@@ -9,12 +9,14 @@
     Singleton,
 )
 from langchain_community.document_compressors.flashrank_rerank import FlashrankRerank
-from langchain_community.embeddings import OllamaEmbeddings
+from langchain_community.embeddings.ollama import OllamaEmbeddings
+from langchain_community.embeddings.fake import FakeEmbeddings
 from langchain_community.llms.ollama import Ollama
 from langchain_community.llms.vllm import VLLMOpenAI
+from langchain_community.llms.fake import FakeListLLM
 from langchain_ollama import ChatOllama
 from langchain_openai import ChatOpenAI
-from langchain_qdrant import Qdrant
+from langchain_qdrant import QdrantVectorStore
 from langfuse import Langfuse
 
 from rag_core_api.impl.answer_generation_chains.answer_generation_chain import (
@@ -31,6 +33,8 @@
 from rag_core_api.impl.embeddings.langchain_community_embedder import (
     LangchainCommunityEmbedder,
 )
+
+
 from rag_core_api.impl.embeddings.stackit_embedder import StackitEmbedder
 from rag_core_api.impl.evaluator.langfuse_ragas_evaluator import LangfuseRagasEvaluator
 from rag_core_api.impl.graph.chat_graph import DefaultChatGraph
@@ -65,6 +69,8 @@
 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.utils.async_threadsafe_semaphore import AsyncThreadsafeSemaphore
+from rag_core_lib.impl.settings.fake_llm_settings import FakeLlmSettings
+from rag_core_api.impl.settings.fake_embedder_settings import FakeEmbedderSettings
 
 
 class DependencyContainer(DeclarativeContainer):
@@ -78,8 +84,10 @@ class DependencyContainer(DeclarativeContainer):
     retriever_settings = RetrieverSettings()
     ollama_settings = OllamaSettings()
     ollama_embedder_settings = OllamaEmbedderSettings()
+    fake_embedder_settings = FakeEmbedderSettings()
     langfuse_settings = LangfuseSettings()
     stackit_vllm_settings = StackitVllmSettings()
+    fake_llm_settings = FakeLlmSettings()
     error_messages = ErrorMessages()
     rag_class_type_settings = RAGClassTypeSettings()
     ragas_settings = RagasSettings()
@@ -97,17 +105,21 @@ class DependencyContainer(DeclarativeContainer):
             LangchainCommunityEmbedder, embedder=Singleton(OllamaEmbeddings, **ollama_embedder_settings.model_dump())
         ),
         stackit=Singleton(StackitEmbedder, stackit_embedder_settings),
+        fake=Singleton(
+            LangchainCommunityEmbedder, embedder=Singleton(FakeEmbeddings, **fake_embedder_settings.model_dump())
+        ),
     )
 
     vectordb_client = Singleton(
         qdrant_client.QdrantClient,
-        url=vector_database_settings.url,
+        location=vector_database_settings.location,
     )
     vectorstore = Singleton(
-        Qdrant,
+        QdrantVectorStore,
         client=vectordb_client,
         collection_name=vector_database_settings.collection_name,
-        embeddings=embedder,
+        embedding=embedder,
+        validate_collection_config=False,
     )
 
     vector_database = Singleton(
@@ -165,6 +177,7 @@ class DependencyContainer(DeclarativeContainer):
         class_selector_config.llm_type,
         ollama=Singleton(llm_provider, ollama_settings, Ollama),
         stackit=Singleton(llm_provider, stackit_vllm_settings, VLLMOpenAI),
+        fake=Singleton(llm_provider, fake_llm_settings, FakeListLLM),
     )
 
     prompt = ANSWER_GENERATION_PROMPT

libs/rag-core-api/pyproject.toml

@@ -9,3 +9,4 @@ class EmbedderType(StrEnum):
 
     OLLAMA = "ollama"
     STACKIT = "stackit"
+    FAKE = "fake"

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

@@ -100,7 +100,7 @@ async def ainvoke(
                 continue
             return_val.append(result)
 
-        if self._reranker:
+        if self._reranker and results:
             return_val = await self._reranker.ainvoke((return_val, retriever_input), config=config)
 
         return return_val