Deepseek data generation

app/cache/prefetch_cache.py

@@ -24,5 +24,6 @@ class PrefetchCache(BaselineCache):
             return True
         return False
 
-    def set_relations(self):
+    def set_relations(self, key: str, related_key: str, related_val: str):
+        self.key_relations[key] = related_key | related_val
         return

app/database.py

@@ -1,5 +1,6 @@
 
 from tinydb import TinyDB, Query
+from generate_data import generate_data
 
 # Initialize TinyDB as a NoSQL key-value store
 DB_FILE = "database.json"
@@ -11,9 +12,9 @@ def get_user_profile(user_id):
     result = db.search(User.user_id == user_id)
     return result[0] if result else None
 
-def update_user_profile(user_id, name, followers, bio, posts):
+def update_user_profile(user_id, name, followers, bio, posts, friends):
     """Update user profile in TinyDB"""
-    db.upsert({"user_id": user_id, "name": name, "followers": followers, "bio": bio, "posts": posts}, User.user_id == user_id)
+    db.upsert({"user_id": user_id, "name": name, "followers": followers, "bio": bio, "posts": posts, "friends": friends}, User.user_id == user_id)
 
 def init_db():
     """Ensure TinyDB is initialized before FastAPI starts and prepopulate some data"""
@@ -22,8 +23,5 @@ def init_db():
 
     # Prepopulate database with some sample users if empty
     if len(db) == 0:
-        db.insert_multiple([
-            {"user_id": "1", "name": "Alice", "followers": 100, "bio": "Love coding!", "posts": "Hello, world!"},
-            {"user_id": "2", "name": "Bob", "followers": 200, "bio": "Tech enthusiast", "posts": "AI is amazing!"},
-            {"user_id": "3", "name": "Charlie", "followers": 50, "bio": "Blogger", "posts": "Check out my latest post!"}
-        ])
+        data = generate_data(100)
+        db.insert_multiple(data)

app/generate_data.py

@@ -0,0 +1,66 @@
+import os
+from langchain_huggingface import HuggingFaceEndpoint
+from langchain_core.prompts import PromptTemplate, ChatPromptTemplate
+import warnings
+warnings.filterwarnings('ignore')
+import re
+import random
+
+HUGGINGFACEHUB_API_TOKEN = None
+os.environ["HUGGINGFACEHUB_API_TOKEN"] = HUGGINGFACEHUB_API_TOKEN
+
+def parse_profile(text, user_id, num_users):
+    match = re.search(r"([A-Za-z ]+)\|([A-Za-z &\-!]+)\|([A-Za-z .',!?&\-]+)", text)
+    if not match:
+        return None  # Skip invalid responses
+
+    name, bio, posts = match.groups()
+    
+    # Generate mock followers count (randomized for realism)
+    followers = random.randint(10, 5000)
+
+    # Generate mock friends (users with nearby IDs)
+    friend_ids = [str(fid) for fid in range(num_users) if fid != user_id]
+    random.shuffle(friend_ids)
+    friends = friend_ids[:random.randint(1, num_users-1)]  # Each user gets 1-5 friends
+
+    return {
+        "user_id": str(user_id),
+        "name": name.strip(),
+        "followers": followers,
+        "bio": bio.strip(),
+        "posts": posts.strip(),
+        "friends": friends
+    }
+
+def generate_data(num_users):
+    system_message = """You are a data generator creating user profiles for a social media app. 
+    Always provide user profiles in this format: Name | Interest | Recent Activity.
+    Do not include numbers, IDs, or assistant labels. Only return a properly formatted response.
+
+    Example: Alice Wonderland | Exploring the world one frame at a time! | Just captured a stunning sunset."""
+    # prompt = PromptTemplate.from_template(template)
+    prompt = ChatPromptTemplate ([
+        ("system", system_message),
+        ("user", "Generate a user profile for user {user_id}")
+    ])
+
+    llm = HuggingFaceEndpoint(
+        task='text-generation',
+        model="deepseek-ai/DeepSeek-R1",
+        max_new_tokens=150,
+        do_sample=True,
+        top_k=60,
+        temperature=1.0,
+        top_p=0.9,
+        huggingfacehub_api_token=HUGGINGFACEHUB_API_TOKEN,
+    )
+    llm_chain = prompt | llm
+    data = []
+    for i in range(num_users): 
+        raw_text = llm_chain.invoke({"user_id": i})
+        user_profile = parse_profile(raw_text, i, num_users)
+        if user_profile:
+            data.append(user_profile)
+            
+    return data

app/main.py

@@ -13,7 +13,7 @@ app = FastAPI()
 if CACHE_STRATEGY == "Baseline":
     cache = BaselineCache(limit=CACHE_LIMIT)
 elif CACHE_STRATEGY == "Prefetch":
-    cache = PrefetchCache()
+    cache = PrefetchCache(limit=CACHE_LIMIT)
 elif CACHE_STRATEGY == "Tiered":
     cache = TieredCache(limit=CACHE_LIMIT, l2_limit=L2_CACHE_LIMIT)
 elif CACHE_STRATEGY == "Seive":
@@ -37,8 +37,8 @@ def fetch_user_profile(user_id: str):
     return {"user_id": user_id, "profile": profile, "source": "database", "time_ms": (time.time() - start) * 1000}
 
 @app.post("/update_user/")
-def modify_user_profile(user_id: str, name: str, followers: int, bio: str, posts: str):
+def modify_user_profile(user_id: str, name: str, followers: int, bio: str, posts: str, friends: list[str]):
     """Update user profile and refresh cache"""
-    update_user_profile(user_id, name, followers, bio, posts)
+    update_user_profile(user_id, name, followers, bio, posts, friends)
     cache.invalidate(user_id)  # Invalidate old cache
     return {"message": "User profile updated successfully"}