from pydantic import BaseModel, Field from typing import List, Optional, Dict, Any class QueryRequest(BaseModel): question: str = Field(..., description="The question to answer") chat_history: Optional[List[Dict[str, str]]] = Field(None, description="Conversation history") k: Optional[int] = Field(50, description="Number of documents to retrieve for reranking") class QueryResponse(BaseModel): answer: str = Field(..., description="The generated answer") sources: List[Dict[str, Any]] = Field(..., description="Source documents used") context_preview: Optional[str] = Field(None, description="Preview of the context used") llm_model: Optional[str] = Field(None, description="The LLM model used to generate the answer") class SearchRequest(BaseModel): query: str = Field(..., description="Search query") k: Optional[int] = Field(10, description="Number of results to return") class SearchResponse(BaseModel): results: List[Dict[str, Any]] = Field(..., description="Search results") total_results: int = Field(..., description="Total number of results") class DocumentUploadResponse(BaseModel): message: str = Field(..., description="Status message") documents_processed: int = Field(..., description="Number of files processed") chunks_added: int = Field(..., description="Number of document chunks added") class CollectionStatsResponse(BaseModel): total_documents: int = Field(..., description="Total documents in collection") collection_name: str = Field(..., description="Collection name") metadata: Optional[Dict[str, Any]] = Field(None, description="Collection metadata") class HealthResponse(BaseModel): status: str = Field(..., description="Service status") vector_store: bool = Field(..., description="Vector store status") chroma_directory: str = Field(..., description="Chroma persistence directory") embeddings_model: Optional[str] = Field(None, description="Embeddings model in use")