support 2 new endpoints

main.py

@@ -34,10 +34,19 @@ app = FastAPI(
     version="1.0",
     lifespan=lifespan,
     openapi_tags=[
-        {"name": "Health", "description": "Health check endpoints"},
-        {"name": "Authentication", "description": "User authentication and token management"},
-        {"name": "Prediction", "description": "Predict and process CSV files"},
-    ]
+        {
+            "name": "Health",
+            "description": "Health check endpoints",
+        },
+        {
+            "name": "Authentication",
+            "description": "User authentication and token management",
+        },
+        {
+            "name": "AI Model",
+            "description": "AI model endpoints for prediction and embedding",
+        },
+    ],
 )
 
 # Include Routers

models.py

@@ -21,3 +21,30 @@ class UserInDB(User):
 class UserCreate(BaseModel):
     username: str
     password: str
+
+
+class EmbeddingRequest(BaseModel):
+    sentences: list[str]
+
+
+class PredictRecord(BaseModel):
+    subject: str
+    sub_subject: str
+    name_category: str
+    name: str
+    abstract: str | None = None
+    memo: str | None = None
+
+
+class PredictResult(BaseModel):
+    standard_subject: str
+    standard_name: str
+    anchor_name: str
+
+
+class PredictRawRequest(BaseModel):
+    records: list[PredictRecord]
+
+
+class PredictRawResponse(BaseModel):
+    results: list[PredictResult]

routes/predict.py

@@ -2,7 +2,7 @@ import os
 import time
 import shutil
 from pathlib import Path
-from fastapi import APIRouter, UploadFile, File, HTTPException, Depends
+from fastapi import APIRouter, UploadFile, File, HTTPException, Depends, Body
 from fastapi.responses import FileResponse
 from auth import get_current_user
 from services.sentence_transformer_service import SentenceTransformerService, sentence_transformer_service
@@ -10,6 +10,14 @@ from data_lib.input_name_data import InputNameData
 from data_lib.base_name_data import COL_NAME_SENTENCE
 from mapping_lib.name_mapper import NameMapper
 from config import UPLOAD_DIR, OUTPUT_DIR
+from models import (
+    EmbeddingRequest,
+    PredictRawRequest,
+    PredictRawResponse,
+    PredictRecord,
+    PredictResult,
+)
+import pandas as pd
 
 router = APIRouter()
 
@@ -85,3 +93,101 @@ async def predict(
     except Exception as e:
         print(f"Error processing file: {e}")
         raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.post("/embeddings")
+async def create_embeddings(
+    request: EmbeddingRequest,
+    current_user=Depends(get_current_user),
+    sentence_service: SentenceTransformerService = Depends(
+        lambda: sentence_transformer_service
+    ),
+):
+    """
+    Create embeddings for a list of input sentences (requires authentication)
+    """
+    try:
+        embeddings = sentence_service.sentenceTransformerHelper.create_embeddings(
+            request.sentences
+        )
+        # Convert numpy array to list for JSON serialization
+        embeddings_list = embeddings.tolist()
+        return {"embeddings": embeddings_list}
+    except Exception as e:
+        print(f"Error creating embeddings: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+@router.post("/predict-raw", response_model=PredictRawResponse)
+async def predict_raw(
+    request: PredictRawRequest,
+    current_user=Depends(get_current_user),
+    sentence_service: SentenceTransformerService = Depends(
+        lambda: sentence_transformer_service
+    ),
+):
+    """
+    Process raw input records and return standardized names (requires authentication)
+    """
+    try:
+        # Convert input records to DataFrame
+        records_dict = {
+            "科目": [],
+            "中科目": [],
+            "分類": [],
+            "名称": [],
+            "摘要": [],
+            "備考": [],
+            "シート名": [],  # Required by BaseNameData but not used
+            "行": [],  # Required by BaseNameData but not used
+        }
+
+        for record in request.records:
+            records_dict["科目"].append(record.subject)
+            records_dict["中科目"].append(record.sub_subject)
+            records_dict["分類"].append(record.name_category)
+            records_dict["名称"].append(record.name)
+            records_dict["摘要"].append(record.abstract or "")
+            records_dict["備考"].append(record.memo or "")
+            records_dict["シート名"].append("")  # Placeholder
+            records_dict["行"].append("")  # Placeholder
+
+        df = pd.DataFrame(records_dict)
+
+        # Process input data
+        try:
+            inputData = InputNameData(sentence_service.dic_standard_subject)
+            # Use _add_raw_data instead of direct assignment
+            inputData._add_raw_data(df)
+            inputData.process_data(sentence_service.sentenceTransformerHelper)
+        except Exception as e:
+            print(f"Error processing input data: {e}")
+            raise HTTPException(status_code=500, detail=str(e))
+
+        # Map standard names
+        try:
+            nameMapper = NameMapper(
+                sentence_service.sentenceTransformerHelper,
+                sentence_service.standardNameMapData,
+                top_count=3,
+            )
+            df_predicted = nameMapper.predict(inputData)
+        except Exception as e:
+            print(f"Error mapping standard names: {e}")
+            raise HTTPException(status_code=500, detail=str(e))
+
+        # Convert results to response format
+        results = []
+        for _, row in df_predicted.iterrows():
+            result = PredictResult(
+                standard_subject=row["標準科目"],
+                standard_name=row["標準項目名"],
+                anchor_name=row["基準名称"],
+            )
+            results.append(result)
+
+        return PredictRawResponse(results=results)
+
+    except Exception as e:
+        print(f"Error processing records: {e}")
+        raise HTTPException(status_code=500, detail=str(e))