feat(backend): add response caching and user management

Replace USE_DATABASE toggle with USE_CACHE for smarter LLM response handling:
- Add prompt hashing for efficient cache lookups
- Cache API responses in database to reduce token usage
- Always store responses for analytics (cache or fresh)

Add user authentication infrastructure:
- User table with bcrypt password hashing
- CRUD operations for user management
- Role-based access control (admin/user)

Dependencies: add bcrypt and PyJWT for auth

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
2026-03-14 13:40:34 -04:00
parent 0107691c90
commit af52107ed8
4 changed files with 442 additions and 79 deletions
+107 -69
View File
@@ -9,31 +9,29 @@ from typing import Dict
class LLMAnalyzer:
"""Handles LLM-based analysis of patent content."""
def __init__(self, api_key: str | None = None, test_mode: bool = False, use_database: bool | None = None):
def __init__(self, api_key: str | None = None, test_mode: bool = False, use_cache: bool | None = None):
"""Initialize the LLM analyzer.
Args:
api_key: OpenRouter API key. If None, will attempt to load from config.
test_mode: If True, print prompts instead of making API calls
use_database: If True, store messages in database instead of calling API.
If None, will use config.use_database
use_cache: If True, check database cache before making API calls.
If None, uses config.use_cache (default: True)
"""
self.test_mode = test_mode
self.use_database = use_database if use_database is not None else config.use_database
self.db_client = None
self.use_cache = use_cache if use_cache is not None else config.use_cache
self.model = "anthropic/claude-3.5-sonnet"
# Initialize database client if in database mode
if self.use_database:
self.db_client = DatabaseClient(config.database_url)
self.db_client.initialize_schema()
# Always initialize database client for storage and caching
self.db_client = DatabaseClient(config.database_url)
self.db_client.initialize_schema()
# Initialize OpenRouter client if not in database mode
if (api_key or config.openrouter_api_key) and not test_mode and not self.use_database:
# Initialize OpenRouter client if API key is available
if (api_key or config.openrouter_api_key) and not test_mode:
self.client = OpenAI(
api_key=api_key or config.openrouter_api_key,
base_url="https://openrouter.ai/api/v1"
)
self.model = "anthropic/claude-3.5-sonnet"
else:
self.client = None
@@ -68,22 +66,31 @@ Provide a concise analysis (2-3 paragraphs) focusing on what this patent reveals
print("=" * 80)
return "[TEST MODE - No API call made]"
# Database mode: store the prompt and return a placeholder response
if self.use_database:
response_text = "[DATABASE MODE] Message stored for testing/analytics. Enable API mode to get actual analysis."
self.db_client.store_message(
# Check cache first
if self.use_cache:
cached = self.db_client.get_cached_response(
prompt=prompt,
response=response_text,
company_name=company_name,
analysis_type="single_patent",
model=self.model if hasattr(self, 'model') else None,
metadata={"patent_content_length": len(patent_content)}
analysis_type="single_patent"
)
if cached:
# Log the cache hit
self.db_client.store_message(
prompt=prompt,
response=cached["response"],
company_name=company_name,
analysis_type="single_patent",
model=self.model,
metadata={
"patent_content_length": len(patent_content),
"cache_hit": True,
"original_message_id": cached["id"]
},
is_cached=True
)
return cached["response"]
return response_text
# API mode: send to OpenRouter
# Call API if no cache hit and client is available
if self.client:
response = self.client.chat.completions.create(
model=self.model,
@@ -92,23 +99,34 @@ Provide a concise analysis (2-3 paragraphs) focusing on what this patent reveals
)
response_text = response.choices[0].message.content
# Store in database if db_client is available (for logging even in API mode)
if self.db_client:
self.db_client.store_message(
prompt=prompt,
response=response_text,
company_name=company_name,
analysis_type="single_patent",
model=self.model,
metadata={"patent_content_length": len(patent_content)},
token_usage={
"prompt_tokens": response.usage.prompt_tokens,
"completion_tokens": response.usage.completion_tokens,
"total_tokens": response.usage.total_tokens
} if hasattr(response, 'usage') else None
)
# Store in database for future cache lookups
self.db_client.store_message(
prompt=prompt,
response=response_text,
company_name=company_name,
analysis_type="single_patent",
model=self.model,
metadata={"patent_content_length": len(patent_content)},
token_usage={
"prompt_tokens": response.usage.prompt_tokens,
"completion_tokens": response.usage.completion_tokens,
"total_tokens": response.usage.total_tokens
} if hasattr(response, 'usage') else None
)
return response_text
# No API client available - store prompt for later processing
placeholder = "[NO API] Prompt stored in database. Configure OPENROUTER_API_KEY to enable analysis."
self.db_client.store_message(
prompt=prompt,
response=placeholder,
company_name=company_name,
analysis_type="single_patent",
model=self.model,
metadata={"patent_content_length": len(patent_content), "pending": True}
)
return placeholder
def analyze_patent_portfolio(
self, patents_data: list[Dict[str, str]], company_name: str
@@ -150,46 +168,54 @@ Provide a comprehensive analysis (4-5 paragraphs) with a final verdict on the co
print(prompt)
return "[TEST MODE]"
# Database mode: store the prompt and return a placeholder response
if self.use_database:
response_text = "[DATABASE MODE] Message stored for testing/analytics. Enable API mode to get actual analysis."
metadata = {
"patent_count": len(patents_data),
"patent_ids": [p['patent_id'] for p in patents_data]
}
self.db_client.store_message(
# Check cache first
if self.use_cache:
cached = self.db_client.get_cached_response(
prompt=prompt,
response=response_text,
company_name=company_name,
analysis_type="portfolio",
model=self.model if hasattr(self, 'model') else None,
metadata={
"patent_count": len(patents_data),
"patent_ids": [p['patent_id'] for p in patents_data]
}
analysis_type="portfolio"
)
if cached:
# Log the cache hit
self.db_client.store_message(
prompt=prompt,
response=cached["response"],
company_name=company_name,
analysis_type="portfolio",
model=self.model,
metadata={
**metadata,
"cache_hit": True,
"original_message_id": cached["id"]
},
is_cached=True
)
return cached["response"]
return response_text
# Call API if no cache hit and client is available
if self.client:
try:
response = self.client.chat.completions.create(
model=self.model,
max_tokens=2048,
messages=[{"role": "user", "content": prompt}],
)
# API mode: send to OpenRouter
try:
response = self.client.chat.completions.create(
model=self.model,
max_tokens=2048,
messages=[{"role": "user", "content": prompt}],
)
response_text = response.choices[0].message.content
response_text = response.choices[0].message.content
# Store in database if db_client is available (for logging even in API mode)
if self.db_client:
# Store in database for future cache lookups
self.db_client.store_message(
prompt=prompt,
response=response_text,
company_name=company_name,
analysis_type="portfolio",
model=self.model,
metadata={
"patent_count": len(patents_data),
"patent_ids": [p['patent_id'] for p in patents_data]
},
metadata=metadata,
token_usage={
"prompt_tokens": response.usage.prompt_tokens,
"completion_tokens": response.usage.completion_tokens,
@@ -197,7 +223,19 @@ Provide a comprehensive analysis (4-5 paragraphs) with a final verdict on the co
} if hasattr(response, 'usage') else None
)
return response_text
except AttributeError:
return prompt
return response_text
except AttributeError:
return prompt
# No API client available - store prompt for later processing
placeholder = "[NO API] Prompt stored in database. Configure OPENROUTER_API_KEY to enable analysis."
self.db_client.store_message(
prompt=prompt,
response=placeholder,
company_name=company_name,
analysis_type="portfolio",
model=self.model,
metadata={**metadata, "pending": True}
)
return placeholder