Upload 4 files

Dockerfile

@@ -0,0 +1,17 @@
+# Use an official Python runtime as a parent image
+FROM python:3.10
+
+# Set the working directory in the container
+WORKDIR /code
+
+# Copy the requirements file into the container
+COPY ./requirements.txt /code/requirements.txt
+
+# Install the packages
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+# Copy your entire project's source code into the container
+COPY . /code/
+
+# Run the app using Gunicorn, a production-ready server
+CMD ["gunicorn", "-w", "4", "-k", "uvicorn.workers.UvicornWorker", "main:app", "--bind", "0.0.0.0:7860"]

encoder.py

@@ -0,0 +1,15 @@
+from sentence_transformers import SentenceTransformer
+
+class SentenceEncoder:
+    def __init__(self, model_name='l3cube-pune/indic-sentence-similarity-sbert'):
+        try:
+            self.model = SentenceTransformer(model_name)
+            print(f"✅ Model '{model_name}' loaded successfully.")
+        except Exception as e:
+            print(f"❌ Error loading model: {e}")
+            self.model = None
+
+    def encode(self, texts, batch_size=32, show_progress_bar=False):
+        if self.model is None:
+            return None
+        return self.model.encode(texts, batch_size=batch_size, show_progress_bar=show_progress_bar, convert_to_tensor=True)

main.py

@@ -0,0 +1,172 @@
+import os
+import json
+import chromadb
+from fastapi import FastAPI, HTTPException, Depends
+from pydantic import BaseModel, Field
+from typing import List
+import firebase_admin
+from firebase_admin import credentials, firestore
+
+from encoder import SentenceEncoder
+
+# --- Pydantic Models ---
+class UserProfile(BaseModel):
+    user_id: str
+    skills: List[str] = Field(..., example=["python", "data analysis"])
+    interests: List[str] = Field(..., example=["machine learning", "web development"])
+
+class SearchQuery(BaseModel):
+    query: str = Field(..., example="marketing internship in mumbai")
+
+# --- SCHEMA CHANGED HERE ---
+# Reverted to use 'id' and 'skills'
+class InternshipData(BaseModel):
+    id: str = Field(..., example="int_021")
+    title: str
+    description: str
+    skills: List[str]
+    duration: int
+    createdAt: str
+    stipend: int = None
+
+class RecommendationResponse(BaseModel):
+    recommendations: List[dict]
+
+class StatusResponse(BaseModel):
+    status: str
+    internship_id: str
+
+# --- FastAPI App & Firebase Initialization ---
+app = FastAPI(
+    title="Internship Recommendation API",
+    description="An API using Firestore for metadata, and ChromaDB for vector search.",
+    version="2.1.0"
+)
+
+# Initialize Firebase ONCE at startup
+try:
+    if 'FIREBASE_CREDS_JSON' in os.environ:
+        creds_dict = json.loads(os.environ.get('FIREBASE_CREDS_JSON'))
+        cred = credentials.Certificate(creds_dict)
+    else:
+        cred = credentials.Certificate('serviceAccountKey.json')
+    
+    firebase_admin.initialize_app(cred)
+    db = firestore.client()
+    print("✅ Firebase connection initialized.")
+except Exception as e:
+    print(f"❌ Could not initialize Firebase. Error: {e}")
+    db = None
+
+# Dependency to provide the db client
+def get_db():
+    if db is None:
+        raise HTTPException(status_code=503, detail="Firestore connection not available.")
+    return db
+
+# --- Global Variables for Model and ChromaDB ---
+encoder = None
+chroma_collection = None
+
+@app.on_event("startup")
+def load_model_and_data():
+    global encoder, chroma_collection
+    
+    print("🚀 Loading sentence encoder model...")
+    encoder = SentenceEncoder()
+    
+    client = chromadb.PersistentClient(path="/content/chroma_db")
+    chroma_collection = client.get_or_create_collection(name="internships")
+    
+    print("✅ ChromaDB client initialized and collection is ready.")
+    print(f"   - Internships in DB: {chroma_collection.count()}")
+
+# --- API Endpoints ---
+@app.get("/")
+def read_root():
+    return {"message": "Welcome to the Internship Recommendation API!"}
+
+@app.post("/add-internship", response_model=StatusResponse)
+def add_internship(internship: InternshipData, db_client: firestore.Client = Depends(get_db)):
+    if chroma_collection is None or encoder is None:
+        raise HTTPException(status_code=503, detail="Server is not ready.")
+
+    # --- SCHEMA CHANGED HERE ---
+    # Using internship.id
+    doc_ref = db_client.collection('internships').document(internship.id)
+    if doc_ref.get().exists:
+        raise HTTPException(status_code=400, detail="Internship ID already exists.")
+
+    # Save to Firestore
+    doc_ref.set(internship.dict())
+
+    # --- SCHEMA CHANGED HERE ---
+    # Using internship.skills
+    text_to_encode = f"{internship.title}. {internship.description}. Skills: {', '.join(internship.skills)}"
+    embedding = encoder.encode([text_to_encode])[0].tolist()
+
+    # --- CRITICAL FIX RE-APPLIED HERE ---
+    # Prepare metadata for ChromaDB, converting skills list to a JSON string
+    metadata_for_chroma = internship.dict()
+    metadata_for_chroma['skills'] = json.dumps(metadata_for_chroma['skills'])
+
+    chroma_collection.add(
+        # --- SCHEMA CHANGED HERE ---
+        # Using internship.id
+        ids=[internship.id],
+        embeddings=[embedding],
+        metadatas=[metadata_for_chroma]
+    )
+
+    print(f"✅ Added internship to Firestore and ChromaDB: {internship.id}")
+    # --- SCHEMA CHANGED HERE ---
+    return {"status": "success", "internship_id": internship.id}
+
+@app.post("/profile-recommendations", response_model=RecommendationResponse)
+def get_profile_recommendations(profile: UserProfile):
+    if chroma_collection is None or encoder is None:
+        raise HTTPException(status_code=503, detail="Server is not ready.")
+
+    query_text = f"Skills: {', '.join(profile.skills)}. Interests: {', '.join(profile.interests)}"
+    query_embedding = encoder.encode([query_text])[0].tolist()
+    
+    results = chroma_collection.query(
+        query_embeddings=[query_embedding],
+        n_results=3
+    )
+    
+    recommendations = []
+    ids = results.get('ids', [[]])[0]
+    distances = results.get('distances', [[]])[0]
+
+    for i, internship_id in enumerate(ids):
+        recommendations.append({
+            "internship_id": internship_id,
+            "score": 1 - distances[i]
+        })
+
+    return {"recommendations": recommendations}
+
+@app.post("/search", response_model=RecommendationResponse)
+def search_internships(search: SearchQuery):
+    if chroma_collection is None or encoder is None:
+        raise HTTPException(status_code=503, detail="Server is not ready.")
+
+    query_embedding = encoder.encode([search.query])[0].tolist()
+    
+    results = chroma_collection.query(
+        query_embeddings=[query_embedding],
+        n_results=3
+    )
+    
+    recommendations = []
+    ids = results.get('ids', [[]])[0]
+    distances = results.get('distances', [[]])[0]
+
+    for i, internship_id in enumerate(ids):
+        recommendations.append({
+            "internship_id": internship_id,
+            "score": 1 - distances[i]
+        })
+        
+    return {"recommendations": recommendations}

requirements.txt

@@ -0,0 +1,8 @@
+fastapi
+uvicorn[standard]
+pydantic
+sentence-transformers
+torch
+numpy
+scikit-learn
+firebase-admin