feat: Implement Pinecone vector store integration

- Update config.py with Pinecone settings and model configurations
- Implement VectorStore class with Pinecone backend
- Add comprehensive vector operations (add, search, delete)
- Set up proper error handling and metadata management
- Add .gitignore for Python project

backend/config.py

@@ -0,0 +1,47 @@
+from pydantic_settings import BaseSettings
+from typing import Optional
+import os
+from dotenv import load_dotenv
+
+load_dotenv()
+
+class Settings(BaseSettings):
+    # API Keys
+    COHERE_API_KEY: str = os.getenv('COHERE_API_KEY', '')
+    PINECONE_API_KEY: str = os.getenv('PINECONE_API_KEY', '')
+    
+    # Model Settings
+    MODEL_NAME: str = "facebook/opt-350m"  # Using the finetuned model
+    EMBEDDING_MODEL: str = "embed-english-v3.0"
+    
+    # Vector Store Settings
+    VECTOR_DIMENSION: int = 768  # Default dimension for Cohere embeddings
+    MAX_SEARCH_RESULTS: int = 5
+    
+    # Pinecone Settings
+    PINECONE_ENVIRONMENT: str = os.getenv('PINECONE_ENVIRONMENT', 'us-west1-gcp')
+    PINECONE_INDEX_NAME: str = os.getenv('PINECONE_INDEX_NAME', 'marketing-assistant')
+    
+    # Content Generation Settings
+    MAX_CONTENT_LENGTH: int = 500
+    TEMPERATURE: float = 0.7
+    TOP_P: float = 0.9
+    
+    # Brand Style Settings
+    BRAND_GUIDELINES_PATH: str = "data/style_guidelines/brand_guidelines.json"
+    TONE_KEYWORDS_PATH: str = "data/style_guidelines/tone_keywords.json"
+    
+    # Storage Settings
+    VECTOR_STORE_PATH: str = "data/vector_store"
+    PAST_CAMPAIGNS_PATH: str = "data/past_campaigns"
+    USER_QUERIES_PATH: str = "data/user_queries"
+    
+    # Finetuned Model Settings
+    FINETUNED_MODEL_PATH: str = "../finetuned_model"
+    
+    class Config:
+        env_file = ".env"
+        case_sensitive = True
+
+# Create global settings instance
+settings = Settings()