add fiels

.env

@@ -0,0 +1,2 @@
+GEMINI_API_KEY=AIzaSyAkFsaN3BKoSQmRW4FzTahhZXbq-ldsDZ4
+GEMINI_MODEL_NAME=gemini-2.5-flash

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+    "git.ignoreLimitWarning": true
+}

Data/database/sql_connector.py

@@ -0,0 +1,60 @@
+from sqlalchemy import create_engine
+import pandas as pd
+import urllib
+import json
+
+SERVER = "innotrack-sql-server.database.windows.net"
+DATABASE = "InnoTrackDB"
+USERNAME = "innotrackadmin"
+PASSWORD = "Innotrack@admin233"
+
+params = urllib.parse.quote_plus(
+    f"DRIVER={{ODBC Driver 18 for SQL Server}};"
+    f"SERVER={SERVER};"
+    f"DATABASE={DATABASE};"
+    f"UID={USERNAME};"
+    f"PWD={PASSWORD};"
+    "Encrypt=yes;"
+    "TrustServerCertificate=no;"
+    "Connection Timeout=30;"
+)
+
+connection_string = (
+    f"mssql+pyodbc:///?odbc_connect={params}"
+)
+
+engine = create_engine(connection_string)
+
+try:
+
+    with engine.connect() as conn:
+        print("SQL Connected Successfully")
+
+except Exception as e:
+    print("Connection Failed")
+    print(e)
+
+
+
+
+
+def load_preprocessed_projects():
+
+    query = """
+    SELECT *
+    FROM PreProcessed_Projects
+    """
+
+    df = pd.read_sql(
+        query,
+        engine
+    )
+
+    if "features" in df.columns:
+
+        df["features"] = (
+            df["features"]
+            .apply(json.loads)
+        )
+
+    return df

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.11-slim
+
+RUN useradd -m -u 1000 user
+
+USER user
+
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH \
+    PYTHONUNBUFFERED=1
+
+WORKDIR $HOME/app
+
+COPY --chown=user requirements.txt requirements.txt
+
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt
+
+COPY --chown=user . .
+
+CMD ["uvicorn", "api.main:app", "--host", "0.0.0.0", "--port", "7860"]

api/__init__.py

@@ -0,0 +1,2 @@
+# __init__.py
+# empty file is totally fine

api/main.py

@@ -0,0 +1,70 @@
+# api/main.py
+
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+
+from api.schemas import AnalyzeRequest, ChatRequest, ChatResponse
+from api.services import analyze_project, chat_with_llm
+
+# =====================================================
+# Create App
+# =====================================================
+app = FastAPI(
+    title="Graduation Project Similarity API",
+    version="1.0.0",
+    description="AI system for project similarity and originality detection"
+)
+
+# =====================================================
+# CORS
+# =====================================================
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# =====================================================
+# Routes
+# =====================================================
+
+@app.get("/")
+def home():
+    return {
+        "message": "API is running successfully"
+    }
+
+
+@app.get("/health")
+def health():
+    return {
+        "status": "healthy"
+    }
+
+
+@app.post("/analyze")
+def analyze(data: AnalyzeRequest):
+
+    result = analyze_project(
+        title=data.title,
+        description=data.description,
+        abstract=data.abstract,
+        features=data.features,
+        top_k=data.top_k
+    )
+
+    return result
+
+
+@app.post("/chat", response_model=ChatResponse)
+def chat(data: ChatRequest):
+
+    result = chat_with_llm(
+        user_id=data.user_id,
+        message=data.message
+    )
+
+    return result
+

api/schemas.py

@@ -0,0 +1,49 @@
+# api/schemas.py
+
+from typing import List, Optional
+from pydantic import BaseModel, Field
+
+
+# =====================================================
+# Request Schema
+# =====================================================
+class AnalyzeRequest(BaseModel):
+    title: str = Field(..., min_length=3)
+    description: str = Field(..., min_length=5)
+
+    abstract: Optional[str] = ""
+    features: Optional[List[str]] = []
+    top_k: Optional[int] = 5
+
+
+class ChatRequest(BaseModel):
+    user_id: str = Field("default_user", min_length=1)
+    message: str = Field(..., min_length=1)
+
+
+class ChatResponse(BaseModel):
+    user_id: str
+    response: str
+
+
+# =====================================================
+# Result Item
+# =====================================================
+class SimilarProject(BaseModel):
+    project_id: int
+    project_title: str
+
+    semantic_score: float
+    feature_score: float
+    hybrid_score: float
+
+    originality_score: float
+    duplicate_risk: str
+
+
+# =====================================================
+# Response Schema
+# =====================================================
+class AnalyzeResponse(BaseModel):
+    extracted_features: List[str]
+    results: List[SimilarProject]

api/services.py

@@ -0,0 +1,249 @@
+# # api/services.py
+
+# import pandas as pd
+
+# from src.similarity_engine import find_similar_projects
+# from src.preprocessing import extract_features
+
+
+# # =====================================================
+# # Main Analyze Service
+# # =====================================================
+# def analyze_project(
+#     title: str,
+#     description: str,
+#     abstract: str = "",
+#     features=None,
+#     top_k: int = 5
+# ):
+#     """
+#     Full project analysis service
+#     """
+
+#     if features is None:
+#         features = []
+
+#     # ---------------------------------------------
+#     # Build text for auto feature extraction
+#     # ---------------------------------------------
+#     full_text = f"{title}. {abstract}. {description}"
+
+#     auto_features = extract_features(full_text)
+
+#     # merge manual + auto
+#     merged = []
+#     seen = set()
+
+#     for item in features + auto_features:
+#         val = str(item).strip().lower()
+
+#         if val and val not in seen:
+#             seen.add(val)
+#             merged.append(val)
+
+#     # ---------------------------------------------
+#     # Run similarity engine
+#     # ---------------------------------------------
+#     results = find_similar_projects(
+#         title=title,
+#         description=f"{abstract} {description}",
+#         features=merged,
+#         top_k=top_k
+#     )
+
+#     # ---------------------------------------------
+#     # Convert dataframe to json records
+#     # ---------------------------------------------
+#     if isinstance(results, pd.DataFrame):
+#         rows = results.to_dict(orient="records")
+#     else:
+#         rows = []
+
+#     return {
+#         "extracted_features": merged,
+#         "results": rows
+#     }
+
+
+# api/services.py
+
+# import pandas as pd
+
+# from src.similarity_model import find_similar_projects
+# from src.similarity_model import extract_features
+
+
+# # =====================================================
+# # Main Analyze Service
+# # =====================================================
+# def analyze_project(
+#     title: str,
+#     description: str,
+#     abstract: str = "",
+#     features=None,
+#     top_k: int = 5
+# ):
+#     """
+#     Final clean API response
+#     Returns only user-needed metrics
+#     """
+
+#     if features is None:
+#         features = []
+
+#     # -------------------------------------------------
+#     # Build full text for automatic feature extraction
+#     # -------------------------------------------------
+#     full_text = f"{title}. {abstract}. {description}"
+
+#     auto_features = extract_features(full_text)
+
+#     # -------------------------------------------------
+#     # Merge manual + extracted features
+#     # -------------------------------------------------
+#     merged = []
+#     seen = set()
+
+#     for item in features + auto_features:
+#         val = str(item).strip().lower()
+
+#         if val and val not in seen:
+#             seen.add(val)
+#             merged.append(val)
+
+#     # -------------------------------------------------
+#     # Run similarity model
+#     # -------------------------------------------------
+#     results = find_similar_projects(
+#         title=title,
+#         description=f"{abstract} {description}",
+#         features=merged,
+#         top_k=top_k
+#     )
+
+#     # -------------------------------------------------
+#     # No results found
+#     # -------------------------------------------------
+#     if not isinstance(results, pd.DataFrame) or len(results) == 0:
+#         return {
+#             "message": "No similar projects found",
+#             "extracted_features": merged
+#         }
+
+#     # -------------------------------------------------
+#     # Take top matched project only
+#     # -------------------------------------------------
+#     top = results.iloc[0]
+
+#     return {
+#         "extracted_features": merged,
+
+#         "matched_features": top.get(
+#             "matched_features", []
+#         ),
+
+#         "unique_features": top.get(
+#             "unique_query_features", []
+#         ),
+
+#         "hybrid_similarity": round(
+#             float(top.get("hybrid_score", 0)),
+#             4
+#         ),
+
+#         "final_originality_score": round(
+#             float(top.get("originality_score", 0)),
+#             4
+#         )
+#     }
+
+import pandas as pd
+from fastapi import HTTPException
+
+from src.similarity_model import find_similar_projects
+from src.similarity_model import extract_features
+
+
+def analyze_project(
+    title: str,
+    description: str,
+    abstract: str = "",
+    features=None,
+    top_k: int = 5
+):
+
+    if features is None:
+        features = []
+
+    full_text = f"{title}. {abstract}. {description}"
+
+    auto_features = extract_features(full_text)
+
+    merged = []
+    seen = set()
+
+    for item in features + auto_features:
+        val = str(item).strip().lower()
+
+        if val and val not in seen:
+            seen.add(val)
+            merged.append(val)
+
+    results = find_similar_projects(
+        title=title,
+        description=f"{abstract} {description}",
+        features=merged,
+        top_k=top_k
+    )
+
+    if not isinstance(results, pd.DataFrame) or len(results) == 0:
+        return {
+            "message": "No similar projects found",
+            "extracted_features": merged
+        }
+
+    # -----------------------------------
+    # رجع Top K كله
+    # -----------------------------------
+    top_projects = []
+
+    for _, row in results.iterrows():
+        top_projects.append({
+            "project_title": row.get("project_title", ""),
+            "matched_features": row.get("matched_features", []),
+            "unique_features": row.get("unique_query_features", []),
+            "similarity_score": round(float(row.get("hybrid_score", 0)), 4),
+            "final_originality_score": round(float(row.get("originality_score", 0)), 4)
+        })
+
+    return {
+        "extracted_features": merged,
+        "top_similar_projects": top_projects
+    }
+
+
+def chat_with_llm(user_id: str, message: str):
+    try:
+        from src.recommendation_engine.chatbot_engine import chatbot
+        from src.recommendation_engine.llm_client import LLMProviderError
+    except Exception as exc:
+        raise HTTPException(
+            status_code=503,
+            detail=f"LLM service could not start: {exc}"
+        )
+
+    try:
+        response = chatbot(
+            user_id=user_id,
+            user_input=message
+        )
+    except LLMProviderError as exc:
+        raise HTTPException(
+            status_code=exc.status_code,
+            detail=exc.message
+        )
+
+    return {
+        "user_id": user_id,
+        "response": response
+    }

models/faiss_index.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfe09be00eb70151711b1603dcd8a2b67c102f4218647b2a5bb405a2a1932863
+size 392266

models/metadata.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40d299cdc20636faf33e0acd77ca5b5322ef3de7e6e539b183a25f4e6bdf96cc
+size 794293

models/project_embeddings.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c486ea5b29da2d28dec9567e250f365956726afcbcc675fb3d8d6ce43a9986a
+size 49280

models/trained_metadata.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0450233a4ccc918dd567da002ce44dfe56848ae171e8c66238b18e48b94c35b9
+size 195883

requirements.txt

@@ -0,0 +1,18 @@
+fastapi
+uvicorn[standard]
+pandas
+numpy
+scikit-learn
+scipy
+sentence-transformers
+faiss-cpu
+keybert
+transformers
+torch
+python-dotenv
+google-genai
+requests
+pyarrow
+sqlalchemy
+pyodbc
+git clone https://bat-6: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@https://huggingface.co/spaces/bat-6/Graduation_Project-v1.2