forked from 0xWheatyz/SPARC
Compare commits
7 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 2e6b8c7445 | |||
| 55c131cb32 | |||
| fbb72fe2a5 | |||
| e484baaf5f | |||
| 069f1c343c | |||
| d366443b38 | |||
| b000146585 |
@@ -40,3 +40,9 @@ JWT_SECRET=your-secure-jwt-secret-change-in-production
|
|||||||
# When USE_CACHE=true: check database for cached responses before making API calls
|
# When USE_CACHE=true: check database for cached responses before making API calls
|
||||||
# When USE_CACHE=false: always make fresh API calls (still stores results in database)
|
# When USE_CACHE=false: always make fresh API calls (still stores results in database)
|
||||||
USE_CACHE=true
|
USE_CACHE=true
|
||||||
|
|
||||||
|
# ---- Webhooks ----
|
||||||
|
|
||||||
|
# Comma-separated list of webhook URLs for job completion and alert notifications
|
||||||
|
# Supports generic HTTP POST and Slack/Discord incoming webhooks
|
||||||
|
# WEBHOOK_URLS=https://hooks.slack.com/services/XXX,https://example.com/webhook
|
||||||
|
|||||||
+21
-16
@@ -5,10 +5,13 @@ to provide company performance estimation based on patent portfolios.
|
|||||||
"""
|
"""
|
||||||
|
|
||||||
import hashlib
|
import hashlib
|
||||||
|
import logging
|
||||||
from concurrent.futures import ThreadPoolExecutor, as_completed
|
from concurrent.futures import ThreadPoolExecutor, as_completed
|
||||||
from typing import Callable
|
from typing import Callable
|
||||||
|
|
||||||
from SPARC import config
|
from SPARC import config
|
||||||
|
|
||||||
|
logger = logging.getLogger(__name__)
|
||||||
from SPARC.database import DatabaseClient
|
from SPARC.database import DatabaseClient
|
||||||
from SPARC.llm import LLMAnalyzer
|
from SPARC.llm import LLMAnalyzer
|
||||||
from SPARC.serp_api import SERP
|
from SPARC.serp_api import SERP
|
||||||
@@ -52,13 +55,13 @@ class CompanyAnalyzer:
|
|||||||
query_hash = hashlib.sha256(company_name.lower().encode()).hexdigest()
|
query_hash = hashlib.sha256(company_name.lower().encode()).hexdigest()
|
||||||
cached_ids = self.db.get_cached_serp_query(query_hash)
|
cached_ids = self.db.get_cached_serp_query(query_hash)
|
||||||
if cached_ids is not None:
|
if cached_ids is not None:
|
||||||
print(f"Using cached SERP results for {company_name} ({len(cached_ids)} patents)")
|
logger.info("Using cached SERP results for %s (%d patents)", company_name, len(cached_ids))
|
||||||
patents = Patents(patents=[
|
patents = Patents(patents=[
|
||||||
Patent(patent_id=pid, pdf_link="")
|
Patent(patent_id=pid, pdf_link="")
|
||||||
for pid in cached_ids
|
for pid in cached_ids
|
||||||
])
|
])
|
||||||
else:
|
else:
|
||||||
print(f"Retrieving patents for {company_name}...")
|
logger.info("Retrieving patents for %s...", company_name)
|
||||||
patents = SERP.query(company_name)
|
patents = SERP.query(company_name)
|
||||||
# Cache the SERP results
|
# Cache the SERP results
|
||||||
if patents.patents:
|
if patents.patents:
|
||||||
@@ -66,12 +69,13 @@ class CompanyAnalyzer:
|
|||||||
company_name=company_name,
|
company_name=company_name,
|
||||||
query_hash=query_hash,
|
query_hash=query_hash,
|
||||||
patent_ids=[p.patent_id for p in patents.patents],
|
patent_ids=[p.patent_id for p in patents.patents],
|
||||||
|
ttl_hours=config.serp_cache_ttl_hours,
|
||||||
)
|
)
|
||||||
|
|
||||||
if not patents.patents:
|
if not patents.patents:
|
||||||
return f"No patents found for {company_name}"
|
return f"No patents found for {company_name}"
|
||||||
|
|
||||||
print(f"Found {len(patents.patents)} patents. Processing...")
|
logger.info("Found %d patents. Processing...", len(patents.patents))
|
||||||
|
|
||||||
# Download, parse, and minimize patents in parallel
|
# Download, parse, and minimize patents in parallel
|
||||||
processed_patents = []
|
processed_patents = []
|
||||||
@@ -87,12 +91,12 @@ class CompanyAnalyzer:
|
|||||||
if result:
|
if result:
|
||||||
processed_patents.append(result)
|
processed_patents.append(result)
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
print(f"Warning: Failed to process {patent.patent_id}: {e}")
|
logger.warning("Failed to process %s: %s", patent.patent_id, e)
|
||||||
|
|
||||||
if not processed_patents:
|
if not processed_patents:
|
||||||
return f"Failed to process any patents for {company_name}"
|
return f"Failed to process any patents for {company_name}"
|
||||||
|
|
||||||
print("Analyzing portfolio with LLM...")
|
logger.info("Analyzing portfolio with LLM...")
|
||||||
|
|
||||||
# Analyze the full portfolio with LLM
|
# Analyze the full portfolio with LLM
|
||||||
analysis = self.llm_analyzer.analyze_patent_portfolio(
|
analysis = self.llm_analyzer.analyze_patent_portfolio(
|
||||||
@@ -122,6 +126,7 @@ class CompanyAnalyzer:
|
|||||||
FileNotFoundError: If the patent PDF is not found at the expected path.
|
FileNotFoundError: If the patent PDF is not found at the expected path.
|
||||||
"""
|
"""
|
||||||
import os
|
import os
|
||||||
|
logger.info("Analyzing patent %s for %s...", patent_id, company_name)
|
||||||
|
|
||||||
patent_path = f"patents/{patent_id}.pdf"
|
patent_path = f"patents/{patent_id}.pdf"
|
||||||
|
|
||||||
@@ -183,7 +188,7 @@ class CompanyAnalyzer:
|
|||||||
|
|
||||||
return {"patent_id": patent.patent_id, "content": minimized_content}
|
return {"patent_id": patent.patent_id, "content": minimized_content}
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
print(f"Warning: Failed to process {patent.patent_id}: {e}")
|
logger.warning("Failed to process %s: %s", patent.patent_id, e)
|
||||||
return None
|
return None
|
||||||
|
|
||||||
def _analyze_company_safe(self, company_name: str) -> CompanyAnalysisResult:
|
def _analyze_company_safe(self, company_name: str) -> CompanyAnalysisResult:
|
||||||
@@ -254,7 +259,7 @@ class CompanyAnalyzer:
|
|||||||
results: list[CompanyAnalysisResult] = []
|
results: list[CompanyAnalysisResult] = []
|
||||||
total = len(companies)
|
total = len(companies)
|
||||||
|
|
||||||
print(f"Starting batch analysis of {total} companies...")
|
logger.info("Starting batch analysis of %d companies...", total)
|
||||||
|
|
||||||
with ThreadPoolExecutor(max_workers=max_workers) as executor:
|
with ThreadPoolExecutor(max_workers=max_workers) as executor:
|
||||||
future_to_company = {
|
future_to_company = {
|
||||||
@@ -271,8 +276,8 @@ class CompanyAnalyzer:
|
|||||||
result = future.result()
|
result = future.result()
|
||||||
results.append(result)
|
results.append(result)
|
||||||
|
|
||||||
status = "✓" if result.success else "✗"
|
status = "OK" if result.success else "FAIL"
|
||||||
print(f"[{completed}/{total}] {status} {company}")
|
logger.info("[%d/%d] %s %s", completed, total, status, company)
|
||||||
|
|
||||||
if progress_callback:
|
if progress_callback:
|
||||||
progress_callback(company, completed, total)
|
progress_callback(company, completed, total)
|
||||||
@@ -287,12 +292,12 @@ class CompanyAnalyzer:
|
|||||||
error=str(e),
|
error=str(e),
|
||||||
)
|
)
|
||||||
)
|
)
|
||||||
print(f"[{completed}/{total}] ✗ {company}: {e}")
|
logger.error("[%d/%d] FAIL %s: %s", completed, total, company, e)
|
||||||
|
|
||||||
successful = sum(1 for r in results if r.success)
|
successful = sum(1 for r in results if r.success)
|
||||||
failed = total - successful
|
failed = total - successful
|
||||||
|
|
||||||
print(f"\nBatch complete: {successful} succeeded, {failed} failed")
|
logger.info("Batch complete: %d succeeded, %d failed", successful, failed)
|
||||||
|
|
||||||
return BatchAnalysisResult(
|
return BatchAnalysisResult(
|
||||||
results=results,
|
results=results,
|
||||||
@@ -318,20 +323,20 @@ class CompanyAnalyzer:
|
|||||||
results: list[CompanyAnalysisResult] = []
|
results: list[CompanyAnalysisResult] = []
|
||||||
total = len(companies)
|
total = len(companies)
|
||||||
|
|
||||||
print(f"Starting sequential analysis of {total} companies...")
|
logger.info("Starting sequential analysis of %d companies...", total)
|
||||||
|
|
||||||
for idx, company in enumerate(companies, 1):
|
for idx, company in enumerate(companies, 1):
|
||||||
print(f"\n[{idx}/{total}] Analyzing {company}...")
|
logger.info("[%d/%d] Analyzing %s...", idx, total, company)
|
||||||
result = self._analyze_company_safe(company)
|
result = self._analyze_company_safe(company)
|
||||||
results.append(result)
|
results.append(result)
|
||||||
|
|
||||||
status = "✓" if result.success else "✗"
|
status = "OK" if result.success else "FAIL"
|
||||||
print(f"[{idx}/{total}] {status} {company}")
|
logger.info("[%d/%d] %s %s", idx, total, status, company)
|
||||||
|
|
||||||
successful = sum(1 for r in results if r.success)
|
successful = sum(1 for r in results if r.success)
|
||||||
failed = total - successful
|
failed = total - successful
|
||||||
|
|
||||||
print(f"\nBatch complete: {successful} succeeded, {failed} failed")
|
logger.info("Batch complete: %d succeeded, %d failed", successful, failed)
|
||||||
|
|
||||||
return BatchAnalysisResult(
|
return BatchAnalysisResult(
|
||||||
results=results,
|
results=results,
|
||||||
|
|||||||
+22
-1
@@ -21,11 +21,13 @@ from SPARC.auth import (
|
|||||||
TokenResponse,
|
TokenResponse,
|
||||||
UserResponse,
|
UserResponse,
|
||||||
check_jwt_secret,
|
check_jwt_secret,
|
||||||
|
close_db_client,
|
||||||
create_tokens,
|
create_tokens,
|
||||||
decode_token,
|
decode_token,
|
||||||
get_current_admin,
|
get_current_admin,
|
||||||
get_current_user,
|
get_current_user,
|
||||||
get_db_client,
|
get_db_client,
|
||||||
|
init_db_client,
|
||||||
)
|
)
|
||||||
from SPARC.types import BatchAnalysisResult, CompanyAnalysisResult
|
from SPARC.types import BatchAnalysisResult, CompanyAnalysisResult
|
||||||
|
|
||||||
@@ -155,6 +157,7 @@ async def lifespan(app: FastAPI):
|
|||||||
"""Initialize resources on startup, clean up on shutdown."""
|
"""Initialize resources on startup, clean up on shutdown."""
|
||||||
global _analyzer
|
global _analyzer
|
||||||
check_jwt_secret()
|
check_jwt_secret()
|
||||||
|
init_db_client()
|
||||||
_analyzer = CompanyAnalyzer()
|
_analyzer = CompanyAnalyzer()
|
||||||
# Mark any jobs that were running/pending before the restart as failed
|
# Mark any jobs that were running/pending before the restart as failed
|
||||||
from SPARC.database import DatabaseClient
|
from SPARC.database import DatabaseClient
|
||||||
@@ -167,8 +170,9 @@ async def lifespan(app: FastAPI):
|
|||||||
logging.getLogger(__name__).warning("Marked %d stale jobs as failed on startup", stale)
|
logging.getLogger(__name__).warning("Marked %d stale jobs as failed on startup", stale)
|
||||||
_db.close()
|
_db.close()
|
||||||
yield
|
yield
|
||||||
# Cleanup if needed
|
# Cleanup
|
||||||
_analyzer = None
|
_analyzer = None
|
||||||
|
close_db_client()
|
||||||
|
|
||||||
|
|
||||||
app = FastAPI(
|
app = FastAPI(
|
||||||
@@ -515,8 +519,25 @@ def _run_batch_job(job_id: str, companies: list[str], max_workers: int):
|
|||||||
progress=100,
|
progress=100,
|
||||||
result_json=_json.dumps(batch_response.model_dump(), default=str),
|
result_json=_json.dumps(batch_response.model_dump(), default=str),
|
||||||
)
|
)
|
||||||
|
# Fire webhook notification
|
||||||
|
from SPARC.webhooks import notify_job_completed
|
||||||
|
notify_job_completed(
|
||||||
|
job_id=job_id,
|
||||||
|
status="completed",
|
||||||
|
total_companies=result.total_companies,
|
||||||
|
successful=result.successful,
|
||||||
|
failed=result.failed,
|
||||||
|
)
|
||||||
except Exception as e:
|
except Exception as e:
|
||||||
db.update_job(job_id, status="failed", error=str(e))
|
db.update_job(job_id, status="failed", error=str(e))
|
||||||
|
from SPARC.webhooks import notify_job_completed
|
||||||
|
notify_job_completed(
|
||||||
|
job_id=job_id,
|
||||||
|
status="failed",
|
||||||
|
total_companies=len(companies),
|
||||||
|
successful=0,
|
||||||
|
failed=len(companies),
|
||||||
|
)
|
||||||
|
|
||||||
|
|
||||||
@app.post("/analyze/batch/async", response_model=JobStatus, tags=["Analysis"])
|
@app.post("/analyze/batch/async", response_model=JobStatus, tags=["Analysis"])
|
||||||
|
|||||||
+29
-4
@@ -146,11 +146,36 @@ def decode_token(token: str) -> Optional[TokenPayload]:
|
|||||||
return None
|
return None
|
||||||
|
|
||||||
|
|
||||||
|
# Shared database client singleton, initialized at startup via init_db_client()
|
||||||
|
_db_client: DatabaseClient | None = None
|
||||||
|
|
||||||
|
|
||||||
|
def init_db_client() -> None:
|
||||||
|
"""Initialize the shared database client. Call once at app startup."""
|
||||||
|
global _db_client
|
||||||
|
_db_client = DatabaseClient(config.database_url)
|
||||||
|
_db_client.connect()
|
||||||
|
|
||||||
|
|
||||||
|
def close_db_client() -> None:
|
||||||
|
"""Close the shared database client. Call at app shutdown."""
|
||||||
|
global _db_client
|
||||||
|
if _db_client:
|
||||||
|
_db_client.close()
|
||||||
|
_db_client = None
|
||||||
|
|
||||||
|
|
||||||
def get_db_client() -> DatabaseClient:
|
def get_db_client() -> DatabaseClient:
|
||||||
"""Get database client for auth operations."""
|
"""Get the shared pooled database client for auth operations.
|
||||||
client = DatabaseClient(config.database_url)
|
|
||||||
client.connect()
|
Returns the module-level singleton DatabaseClient. If not yet initialized
|
||||||
return client
|
(e.g., during tests), creates a new instance as a fallback.
|
||||||
|
"""
|
||||||
|
global _db_client
|
||||||
|
if _db_client is None:
|
||||||
|
_db_client = DatabaseClient(config.database_url)
|
||||||
|
_db_client.connect()
|
||||||
|
return _db_client
|
||||||
|
|
||||||
|
|
||||||
async def get_current_user(
|
async def get_current_user(
|
||||||
|
|||||||
@@ -2,12 +2,20 @@
|
|||||||
|
|
||||||
Loads environment variables from .env file for API keys and other secrets.
|
Loads environment variables from .env file for API keys and other secrets.
|
||||||
"""
|
"""
|
||||||
|
import logging
|
||||||
import os
|
import os
|
||||||
|
|
||||||
from dotenv import load_dotenv
|
from dotenv import load_dotenv
|
||||||
|
|
||||||
load_dotenv()
|
load_dotenv()
|
||||||
|
|
||||||
|
# Logging configuration
|
||||||
|
log_level = os.getenv("LOG_LEVEL", "INFO").upper()
|
||||||
|
logging.basicConfig(
|
||||||
|
level=getattr(logging, log_level, logging.INFO),
|
||||||
|
format="%(asctime)s %(levelname)s %(name)s %(message)s",
|
||||||
|
)
|
||||||
|
|
||||||
# SerpAPI key for patent search
|
# SerpAPI key for patent search
|
||||||
api_key = os.getenv("API_KEY")
|
api_key = os.getenv("API_KEY")
|
||||||
|
|
||||||
@@ -31,6 +39,12 @@ use_database = os.getenv("USE_DATABASE", "false").lower() in ("true", "1", "yes"
|
|||||||
patent_search_days = int(os.getenv("PATENT_SEARCH_DAYS", "90"))
|
patent_search_days = int(os.getenv("PATENT_SEARCH_DAYS", "90"))
|
||||||
patent_thread_workers = int(os.getenv("PATENT_THREAD_WORKERS", "5"))
|
patent_thread_workers = int(os.getenv("PATENT_THREAD_WORKERS", "5"))
|
||||||
|
|
||||||
|
# LLM model to use via OpenRouter (e.g. "anthropic/claude-3.5-sonnet", "openai/gpt-4o")
|
||||||
|
model = os.getenv("MODEL", "anthropic/claude-3.5-sonnet")
|
||||||
|
|
||||||
|
# SERP cache TTL in hours (how long cached search results are considered fresh)
|
||||||
|
serp_cache_ttl_hours = int(os.getenv("SERP_CACHE_TTL_HOURS", "24"))
|
||||||
|
|
||||||
# Root path for running behind a reverse proxy (e.g., "/api" when served at /api/)
|
# Root path for running behind a reverse proxy (e.g., "/api" when served at /api/)
|
||||||
# This ensures OpenAPI docs work correctly when accessed via the proxy
|
# This ensures OpenAPI docs work correctly when accessed via the proxy
|
||||||
root_path = os.getenv("ROOT_PATH", "")
|
root_path = os.getenv("ROOT_PATH", "")
|
||||||
|
|||||||
+152
-165
@@ -222,8 +222,6 @@ class DatabaseClient:
|
|||||||
Returns:
|
Returns:
|
||||||
Cached message dict if found, None otherwise
|
Cached message dict if found, None otherwise
|
||||||
"""
|
"""
|
||||||
self.connect()
|
|
||||||
|
|
||||||
prompt_hash = self.hash_prompt(prompt)
|
prompt_hash = self.hash_prompt(prompt)
|
||||||
|
|
||||||
query = """
|
query = """
|
||||||
@@ -246,10 +244,11 @@ class DatabaseClient:
|
|||||||
|
|
||||||
query += " ORDER BY timestamp DESC LIMIT 1"
|
query += " ORDER BY timestamp DESC LIMIT 1"
|
||||||
|
|
||||||
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
with self.get_conn() as conn:
|
||||||
cursor.execute(query, params)
|
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
||||||
result = cursor.fetchone()
|
cursor.execute(query, params)
|
||||||
return dict(result) if result else None
|
result = cursor.fetchone()
|
||||||
|
return dict(result) if result else None
|
||||||
|
|
||||||
def store_message(
|
def store_message(
|
||||||
self,
|
self,
|
||||||
@@ -277,33 +276,32 @@ class DatabaseClient:
|
|||||||
Returns:
|
Returns:
|
||||||
The ID of the inserted record
|
The ID of the inserted record
|
||||||
"""
|
"""
|
||||||
self.connect()
|
|
||||||
|
|
||||||
prompt_hash = self.hash_prompt(prompt)
|
prompt_hash = self.hash_prompt(prompt)
|
||||||
|
|
||||||
with self.conn.cursor() as cursor:
|
with self.get_conn() as conn:
|
||||||
cursor.execute(
|
with conn.cursor() as cursor:
|
||||||
"""
|
cursor.execute(
|
||||||
INSERT INTO llm_messages
|
"""
|
||||||
(prompt, prompt_hash, response, company_name, analysis_type, model, metadata, token_usage, is_cached)
|
INSERT INTO llm_messages
|
||||||
VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)
|
(prompt, prompt_hash, response, company_name, analysis_type, model, metadata, token_usage, is_cached)
|
||||||
RETURNING id
|
VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s)
|
||||||
""",
|
RETURNING id
|
||||||
(
|
""",
|
||||||
prompt,
|
(
|
||||||
prompt_hash,
|
prompt,
|
||||||
response,
|
prompt_hash,
|
||||||
company_name,
|
response,
|
||||||
analysis_type,
|
company_name,
|
||||||
model,
|
analysis_type,
|
||||||
json.dumps(metadata) if metadata else None,
|
model,
|
||||||
json.dumps(token_usage) if token_usage else None,
|
json.dumps(metadata) if metadata else None,
|
||||||
is_cached,
|
json.dumps(token_usage) if token_usage else None,
|
||||||
),
|
is_cached,
|
||||||
)
|
),
|
||||||
|
)
|
||||||
|
|
||||||
message_id = cursor.fetchone()[0]
|
message_id = cursor.fetchone()[0]
|
||||||
self.conn.commit()
|
conn.commit()
|
||||||
|
|
||||||
return message_id
|
return message_id
|
||||||
|
|
||||||
@@ -325,8 +323,6 @@ class DatabaseClient:
|
|||||||
Returns:
|
Returns:
|
||||||
List of message dictionaries
|
List of message dictionaries
|
||||||
"""
|
"""
|
||||||
self.connect()
|
|
||||||
|
|
||||||
query = "SELECT * FROM llm_messages WHERE 1=1"
|
query = "SELECT * FROM llm_messages WHERE 1=1"
|
||||||
params = []
|
params = []
|
||||||
|
|
||||||
@@ -341,9 +337,10 @@ class DatabaseClient:
|
|||||||
query += " ORDER BY timestamp DESC LIMIT %s OFFSET %s"
|
query += " ORDER BY timestamp DESC LIMIT %s OFFSET %s"
|
||||||
params.extend([limit, offset])
|
params.extend([limit, offset])
|
||||||
|
|
||||||
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
with self.get_conn() as conn:
|
||||||
cursor.execute(query, params)
|
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
||||||
return [dict(row) for row in cursor.fetchall()]
|
cursor.execute(query, params)
|
||||||
|
return [dict(row) for row in cursor.fetchall()]
|
||||||
|
|
||||||
def get_analytics(self, days: int = 30) -> Dict:
|
def get_analytics(self, days: int = 30) -> Dict:
|
||||||
"""Get analytics on message usage.
|
"""Get analytics on message usage.
|
||||||
@@ -354,53 +351,52 @@ class DatabaseClient:
|
|||||||
Returns:
|
Returns:
|
||||||
Dictionary with analytics data
|
Dictionary with analytics data
|
||||||
"""
|
"""
|
||||||
self.connect()
|
with self.get_conn() as conn:
|
||||||
|
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
||||||
|
# Total messages
|
||||||
|
cursor.execute(
|
||||||
|
"""
|
||||||
|
SELECT COUNT(*) as total_messages
|
||||||
|
FROM llm_messages
|
||||||
|
WHERE timestamp >= NOW() - INTERVAL '%s days'
|
||||||
|
""",
|
||||||
|
(days,),
|
||||||
|
)
|
||||||
|
total = cursor.fetchone()["total_messages"]
|
||||||
|
|
||||||
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
# Messages by company
|
||||||
# Total messages
|
cursor.execute(
|
||||||
cursor.execute(
|
"""
|
||||||
"""
|
SELECT company_name, COUNT(*) as count
|
||||||
SELECT COUNT(*) as total_messages
|
FROM llm_messages
|
||||||
FROM llm_messages
|
WHERE timestamp >= NOW() - INTERVAL '%s days'
|
||||||
WHERE timestamp >= NOW() - INTERVAL '%s days'
|
GROUP BY company_name
|
||||||
""",
|
ORDER BY count DESC
|
||||||
(days,),
|
LIMIT 10
|
||||||
)
|
""",
|
||||||
total = cursor.fetchone()["total_messages"]
|
(days,),
|
||||||
|
)
|
||||||
|
by_company = cursor.fetchall()
|
||||||
|
|
||||||
# Messages by company
|
# Messages by type
|
||||||
cursor.execute(
|
cursor.execute(
|
||||||
"""
|
"""
|
||||||
SELECT company_name, COUNT(*) as count
|
SELECT analysis_type, COUNT(*) as count
|
||||||
FROM llm_messages
|
FROM llm_messages
|
||||||
WHERE timestamp >= NOW() - INTERVAL '%s days'
|
WHERE timestamp >= NOW() - INTERVAL '%s days'
|
||||||
GROUP BY company_name
|
GROUP BY analysis_type
|
||||||
ORDER BY count DESC
|
ORDER BY count DESC
|
||||||
LIMIT 10
|
""",
|
||||||
""",
|
(days,),
|
||||||
(days,),
|
)
|
||||||
)
|
by_type = cursor.fetchall()
|
||||||
by_company = cursor.fetchall()
|
|
||||||
|
|
||||||
# Messages by type
|
return {
|
||||||
cursor.execute(
|
"total_messages": total,
|
||||||
"""
|
"by_company": [dict(row) for row in by_company],
|
||||||
SELECT analysis_type, COUNT(*) as count
|
"by_type": [dict(row) for row in by_type],
|
||||||
FROM llm_messages
|
"period_days": days,
|
||||||
WHERE timestamp >= NOW() - INTERVAL '%s days'
|
}
|
||||||
GROUP BY analysis_type
|
|
||||||
ORDER BY count DESC
|
|
||||||
""",
|
|
||||||
(days,),
|
|
||||||
)
|
|
||||||
by_type = cursor.fetchall()
|
|
||||||
|
|
||||||
return {
|
|
||||||
"total_messages": total,
|
|
||||||
"by_company": [dict(row) for row in by_company],
|
|
||||||
"by_type": [dict(row) for row in by_type],
|
|
||||||
"period_days": days,
|
|
||||||
}
|
|
||||||
|
|
||||||
# Patent Cache Methods
|
# Patent Cache Methods
|
||||||
|
|
||||||
@@ -651,25 +647,23 @@ class DatabaseClient:
|
|||||||
Returns:
|
Returns:
|
||||||
Created user dict or None if email exists
|
Created user dict or None if email exists
|
||||||
"""
|
"""
|
||||||
self.connect()
|
|
||||||
|
|
||||||
password_hash = self.hash_password(password)
|
password_hash = self.hash_password(password)
|
||||||
|
|
||||||
try:
|
try:
|
||||||
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
with self.get_conn() as conn:
|
||||||
cursor.execute(
|
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
||||||
"""
|
cursor.execute(
|
||||||
INSERT INTO users (email, password_hash, role)
|
"""
|
||||||
VALUES (%s, %s, %s)
|
INSERT INTO users (email, password_hash, role)
|
||||||
RETURNING id, email, role, created_at
|
VALUES (%s, %s, %s)
|
||||||
""",
|
RETURNING id, email, role, created_at
|
||||||
(email, password_hash, role),
|
""",
|
||||||
)
|
(email, password_hash, role),
|
||||||
user = cursor.fetchone()
|
)
|
||||||
self.conn.commit()
|
user = cursor.fetchone()
|
||||||
|
conn.commit()
|
||||||
return dict(user) if user else None
|
return dict(user) if user else None
|
||||||
except psycopg2.errors.UniqueViolation:
|
except psycopg2.errors.UniqueViolation:
|
||||||
self.conn.rollback()
|
|
||||||
return None
|
return None
|
||||||
|
|
||||||
def authenticate_user(self, email: str, password: str) -> Optional[Dict]:
|
def authenticate_user(self, email: str, password: str) -> Optional[Dict]:
|
||||||
@@ -682,23 +676,22 @@ class DatabaseClient:
|
|||||||
Returns:
|
Returns:
|
||||||
User dict if authenticated, None otherwise
|
User dict if authenticated, None otherwise
|
||||||
"""
|
"""
|
||||||
self.connect()
|
with self.get_conn() as conn:
|
||||||
|
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
||||||
|
cursor.execute(
|
||||||
|
"SELECT * FROM users WHERE email = %s",
|
||||||
|
(email,),
|
||||||
|
)
|
||||||
|
user = cursor.fetchone()
|
||||||
|
|
||||||
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
if user and self.verify_password(password, user["password_hash"]):
|
||||||
cursor.execute(
|
return {
|
||||||
"SELECT * FROM users WHERE email = %s",
|
"id": user["id"],
|
||||||
(email,),
|
"email": user["email"],
|
||||||
)
|
"role": user["role"],
|
||||||
user = cursor.fetchone()
|
"created_at": user["created_at"],
|
||||||
|
}
|
||||||
if user and self.verify_password(password, user["password_hash"]):
|
return None
|
||||||
return {
|
|
||||||
"id": user["id"],
|
|
||||||
"email": user["email"],
|
|
||||||
"role": user["role"],
|
|
||||||
"created_at": user["created_at"],
|
|
||||||
}
|
|
||||||
return None
|
|
||||||
|
|
||||||
def get_user_by_id(self, user_id: int) -> Optional[Dict]:
|
def get_user_by_id(self, user_id: int) -> Optional[Dict]:
|
||||||
"""Get a user by ID.
|
"""Get a user by ID.
|
||||||
@@ -709,15 +702,14 @@ class DatabaseClient:
|
|||||||
Returns:
|
Returns:
|
||||||
User dict or None
|
User dict or None
|
||||||
"""
|
"""
|
||||||
self.connect()
|
with self.get_conn() as conn:
|
||||||
|
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
||||||
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
cursor.execute(
|
||||||
cursor.execute(
|
"SELECT id, email, role, created_at FROM users WHERE id = %s",
|
||||||
"SELECT id, email, role, created_at FROM users WHERE id = %s",
|
(user_id,),
|
||||||
(user_id,),
|
)
|
||||||
)
|
user = cursor.fetchone()
|
||||||
user = cursor.fetchone()
|
return dict(user) if user else None
|
||||||
return dict(user) if user else None
|
|
||||||
|
|
||||||
def get_user_by_email(self, email: str) -> Optional[Dict]:
|
def get_user_by_email(self, email: str) -> Optional[Dict]:
|
||||||
"""Get a user by email.
|
"""Get a user by email.
|
||||||
@@ -728,15 +720,14 @@ class DatabaseClient:
|
|||||||
Returns:
|
Returns:
|
||||||
User dict or None
|
User dict or None
|
||||||
"""
|
"""
|
||||||
self.connect()
|
with self.get_conn() as conn:
|
||||||
|
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
||||||
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
cursor.execute(
|
||||||
cursor.execute(
|
"SELECT id, email, role, created_at FROM users WHERE email = %s",
|
||||||
"SELECT id, email, role, created_at FROM users WHERE email = %s",
|
(email,),
|
||||||
(email,),
|
)
|
||||||
)
|
user = cursor.fetchone()
|
||||||
user = cursor.fetchone()
|
return dict(user) if user else None
|
||||||
return dict(user) if user else None
|
|
||||||
|
|
||||||
def get_all_users(self, limit: int = 100, offset: int = 0) -> List[Dict]:
|
def get_all_users(self, limit: int = 100, offset: int = 0) -> List[Dict]:
|
||||||
"""Get all users (admin only).
|
"""Get all users (admin only).
|
||||||
@@ -748,19 +739,18 @@ class DatabaseClient:
|
|||||||
Returns:
|
Returns:
|
||||||
List of user dicts
|
List of user dicts
|
||||||
"""
|
"""
|
||||||
self.connect()
|
with self.get_conn() as conn:
|
||||||
|
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
||||||
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
cursor.execute(
|
||||||
cursor.execute(
|
"""
|
||||||
"""
|
SELECT id, email, role, created_at
|
||||||
SELECT id, email, role, created_at
|
FROM users
|
||||||
FROM users
|
ORDER BY created_at DESC
|
||||||
ORDER BY created_at DESC
|
LIMIT %s OFFSET %s
|
||||||
LIMIT %s OFFSET %s
|
""",
|
||||||
""",
|
(limit, offset),
|
||||||
(limit, offset),
|
)
|
||||||
)
|
return [dict(row) for row in cursor.fetchall()]
|
||||||
return [dict(row) for row in cursor.fetchall()]
|
|
||||||
|
|
||||||
def update_user_role(self, user_id: int, role: str) -> Optional[Dict]:
|
def update_user_role(self, user_id: int, role: str) -> Optional[Dict]:
|
||||||
"""Update a user's role (admin only).
|
"""Update a user's role (admin only).
|
||||||
@@ -772,20 +762,19 @@ class DatabaseClient:
|
|||||||
Returns:
|
Returns:
|
||||||
Updated user dict or None
|
Updated user dict or None
|
||||||
"""
|
"""
|
||||||
self.connect()
|
with self.get_conn() as conn:
|
||||||
|
with conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
||||||
with self.conn.cursor(cursor_factory=RealDictCursor) as cursor:
|
cursor.execute(
|
||||||
cursor.execute(
|
"""
|
||||||
"""
|
UPDATE users
|
||||||
UPDATE users
|
SET role = %s, updated_at = CURRENT_TIMESTAMP
|
||||||
SET role = %s, updated_at = CURRENT_TIMESTAMP
|
WHERE id = %s
|
||||||
WHERE id = %s
|
RETURNING id, email, role, created_at
|
||||||
RETURNING id, email, role, created_at
|
""",
|
||||||
""",
|
(role, user_id),
|
||||||
(role, user_id),
|
)
|
||||||
)
|
user = cursor.fetchone()
|
||||||
user = cursor.fetchone()
|
conn.commit()
|
||||||
self.conn.commit()
|
|
||||||
return dict(user) if user else None
|
return dict(user) if user else None
|
||||||
|
|
||||||
def delete_user(self, user_id: int) -> bool:
|
def delete_user(self, user_id: int) -> bool:
|
||||||
@@ -797,12 +786,11 @@ class DatabaseClient:
|
|||||||
Returns:
|
Returns:
|
||||||
True if deleted
|
True if deleted
|
||||||
"""
|
"""
|
||||||
self.connect()
|
with self.get_conn() as conn:
|
||||||
|
with conn.cursor() as cursor:
|
||||||
with self.conn.cursor() as cursor:
|
cursor.execute("DELETE FROM users WHERE id = %s", (user_id,))
|
||||||
cursor.execute("DELETE FROM users WHERE id = %s", (user_id,))
|
deleted = cursor.rowcount > 0
|
||||||
deleted = cursor.rowcount > 0
|
conn.commit()
|
||||||
self.conn.commit()
|
|
||||||
return deleted
|
return deleted
|
||||||
|
|
||||||
def get_user_count(self) -> int:
|
def get_user_count(self) -> int:
|
||||||
@@ -811,8 +799,7 @@ class DatabaseClient:
|
|||||||
Returns:
|
Returns:
|
||||||
Number of users
|
Number of users
|
||||||
"""
|
"""
|
||||||
self.connect()
|
with self.get_conn() as conn:
|
||||||
|
with conn.cursor() as cursor:
|
||||||
with self.conn.cursor() as cursor:
|
cursor.execute("SELECT COUNT(*) FROM users")
|
||||||
cursor.execute("SELECT COUNT(*) FROM users")
|
return cursor.fetchone()[0]
|
||||||
return cursor.fetchone()[0]
|
|
||||||
|
|||||||
+6
-7
@@ -1,5 +1,6 @@
|
|||||||
"""LLM integration for patent analysis using OpenRouter."""
|
"""LLM integration for patent analysis using OpenRouter."""
|
||||||
|
|
||||||
|
import logging
|
||||||
from typing import Dict
|
from typing import Dict
|
||||||
|
|
||||||
from openai import OpenAI
|
from openai import OpenAI
|
||||||
@@ -7,6 +8,8 @@ from openai import OpenAI
|
|||||||
from SPARC import config
|
from SPARC import config
|
||||||
from SPARC.database import DatabaseClient
|
from SPARC.database import DatabaseClient
|
||||||
|
|
||||||
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
|
||||||
class LLMAnalyzer:
|
class LLMAnalyzer:
|
||||||
"""Handles LLM-based analysis of patent content."""
|
"""Handles LLM-based analysis of patent content."""
|
||||||
@@ -22,7 +25,7 @@ class LLMAnalyzer:
|
|||||||
"""
|
"""
|
||||||
self.test_mode = test_mode
|
self.test_mode = test_mode
|
||||||
self.use_cache = use_cache if use_cache is not None else config.use_cache
|
self.use_cache = use_cache if use_cache is not None else config.use_cache
|
||||||
self.model = "anthropic/claude-3.5-sonnet"
|
self.model = config.model
|
||||||
|
|
||||||
# Always initialize database client for storage and caching
|
# Always initialize database client for storage and caching
|
||||||
self.db_client = DatabaseClient(config.database_url)
|
self.db_client = DatabaseClient(config.database_url)
|
||||||
@@ -61,11 +64,7 @@ Patent Content:
|
|||||||
Provide a concise analysis (2-3 paragraphs) focusing on what this patent reveals about the company's technical direction and competitive advantage."""
|
Provide a concise analysis (2-3 paragraphs) focusing on what this patent reveals about the company's technical direction and competitive advantage."""
|
||||||
|
|
||||||
if self.test_mode:
|
if self.test_mode:
|
||||||
print("=" * 80)
|
logger.debug("TEST MODE - Prompt that would be sent to LLM:\n%s", prompt)
|
||||||
print("TEST MODE - Prompt that would be sent to LLM:")
|
|
||||||
print("=" * 80)
|
|
||||||
print(prompt)
|
|
||||||
print("=" * 80)
|
|
||||||
return "[TEST MODE - No API call made]"
|
return "[TEST MODE - No API call made]"
|
||||||
|
|
||||||
# Check cache first
|
# Check cache first
|
||||||
@@ -167,7 +166,7 @@ Patent Portfolio:
|
|||||||
Provide a comprehensive analysis (4-5 paragraphs) with a final verdict on the company's innovation strength and performance outlook."""
|
Provide a comprehensive analysis (4-5 paragraphs) with a final verdict on the company's innovation strength and performance outlook."""
|
||||||
|
|
||||||
if self.test_mode:
|
if self.test_mode:
|
||||||
print(prompt)
|
logger.debug("TEST MODE - Portfolio prompt:\n%s", prompt)
|
||||||
return "[TEST MODE]"
|
return "[TEST MODE]"
|
||||||
|
|
||||||
metadata = {
|
metadata = {
|
||||||
|
|||||||
+1
-1
@@ -4,7 +4,7 @@ from datetime import datetime
|
|||||||
|
|
||||||
@dataclass
|
@dataclass
|
||||||
class Patent:
|
class Patent:
|
||||||
patent_id: int
|
patent_id: str
|
||||||
pdf_link: str
|
pdf_link: str
|
||||||
pdf_path: str | None = None
|
pdf_path: str | None = None
|
||||||
summary: dict | None = None
|
summary: dict | None = None
|
||||||
|
|||||||
@@ -0,0 +1,139 @@
|
|||||||
|
"""Webhook notifications for job completion and alert events.
|
||||||
|
|
||||||
|
Sends JSON payloads to configured webhook URLs with retry logic.
|
||||||
|
Supports generic HTTP POST and Slack-compatible text payloads.
|
||||||
|
"""
|
||||||
|
|
||||||
|
import logging
|
||||||
|
import os
|
||||||
|
import time
|
||||||
|
from datetime import datetime
|
||||||
|
from typing import Any
|
||||||
|
|
||||||
|
import requests
|
||||||
|
|
||||||
|
logger = logging.getLogger(__name__)
|
||||||
|
|
||||||
|
# Comma-separated list of webhook URLs (env var based config)
|
||||||
|
_WEBHOOK_URLS_RAW = os.getenv("WEBHOOK_URLS", "")
|
||||||
|
WEBHOOK_URLS: list[str] = [
|
||||||
|
url.strip() for url in _WEBHOOK_URLS_RAW.split(",") if url.strip()
|
||||||
|
]
|
||||||
|
|
||||||
|
MAX_RETRIES = 3
|
||||||
|
BACKOFF_BASE = 2 # seconds
|
||||||
|
|
||||||
|
|
||||||
|
def _is_slack_url(url: str) -> bool:
|
||||||
|
"""Check if a URL looks like a Slack incoming webhook."""
|
||||||
|
return "hooks.slack.com" in url or "discord.com/api/webhooks" in url
|
||||||
|
|
||||||
|
|
||||||
|
def _build_payload(event_type: str, data: dict[str, Any], slack: bool = False) -> dict:
|
||||||
|
"""Build the webhook payload.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
event_type: Type of event (e.g., "job_completed", "alert")
|
||||||
|
data: Event-specific data
|
||||||
|
slack: If True, wrap in Slack-compatible ``text`` format
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
JSON-serializable payload dict
|
||||||
|
"""
|
||||||
|
payload = {
|
||||||
|
"event": event_type,
|
||||||
|
"timestamp": datetime.utcnow().isoformat() + "Z",
|
||||||
|
**data,
|
||||||
|
}
|
||||||
|
|
||||||
|
if slack:
|
||||||
|
# Build a human-readable summary for Slack/Discord
|
||||||
|
lines = [f"*[SPARC] {event_type}*"]
|
||||||
|
for key, value in data.items():
|
||||||
|
lines.append(f" {key}: {value}")
|
||||||
|
return {"text": "\n".join(lines)}
|
||||||
|
|
||||||
|
return payload
|
||||||
|
|
||||||
|
|
||||||
|
def _send_with_retry(url: str, payload: dict) -> bool:
|
||||||
|
"""Send a POST request with exponential backoff retry.
|
||||||
|
|
||||||
|
Args:
|
||||||
|
url: Webhook URL
|
||||||
|
payload: JSON payload to send
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
True if delivered successfully, False after all retries exhausted
|
||||||
|
"""
|
||||||
|
for attempt in range(1, MAX_RETRIES + 1):
|
||||||
|
try:
|
||||||
|
response = requests.post(url, json=payload, timeout=10)
|
||||||
|
if response.status_code < 300:
|
||||||
|
logger.debug("Webhook delivered to %s (attempt %d)", url, attempt)
|
||||||
|
return True
|
||||||
|
logger.warning(
|
||||||
|
"Webhook %s returned %d (attempt %d/%d)",
|
||||||
|
url, response.status_code, attempt, MAX_RETRIES,
|
||||||
|
)
|
||||||
|
except requests.RequestException as e:
|
||||||
|
logger.warning(
|
||||||
|
"Webhook delivery failed for %s (attempt %d/%d): %s",
|
||||||
|
url, attempt, MAX_RETRIES, e,
|
||||||
|
)
|
||||||
|
|
||||||
|
if attempt < MAX_RETRIES:
|
||||||
|
wait = BACKOFF_BASE ** attempt
|
||||||
|
time.sleep(wait)
|
||||||
|
|
||||||
|
logger.error("Webhook permanently failed for %s after %d attempts", url, MAX_RETRIES)
|
||||||
|
return False
|
||||||
|
|
||||||
|
|
||||||
|
def notify(event_type: str, data: dict[str, Any]) -> None:
|
||||||
|
"""Fire all configured webhooks for an event.
|
||||||
|
|
||||||
|
Safe to call even when no webhooks are configured (returns immediately).
|
||||||
|
|
||||||
|
Args:
|
||||||
|
event_type: Event identifier (e.g., "job_completed", "patent_alert")
|
||||||
|
data: Event data to include in the payload
|
||||||
|
"""
|
||||||
|
if not WEBHOOK_URLS:
|
||||||
|
return
|
||||||
|
|
||||||
|
for url in WEBHOOK_URLS:
|
||||||
|
slack = _is_slack_url(url)
|
||||||
|
payload = _build_payload(event_type, data, slack=slack)
|
||||||
|
_send_with_retry(url, payload)
|
||||||
|
|
||||||
|
|
||||||
|
def notify_job_completed(
|
||||||
|
job_id: str,
|
||||||
|
status: str,
|
||||||
|
total_companies: int,
|
||||||
|
successful: int,
|
||||||
|
failed: int,
|
||||||
|
) -> None:
|
||||||
|
"""Send notification when a batch job completes."""
|
||||||
|
notify("job_completed", {
|
||||||
|
"job_id": job_id,
|
||||||
|
"status": status,
|
||||||
|
"total_companies": total_companies,
|
||||||
|
"successful": successful,
|
||||||
|
"failed": failed,
|
||||||
|
"summary": f"Batch job {job_id}: {successful}/{total_companies} succeeded",
|
||||||
|
})
|
||||||
|
|
||||||
|
|
||||||
|
def notify_alert(
|
||||||
|
company_name: str,
|
||||||
|
alert_type: str,
|
||||||
|
message: str,
|
||||||
|
) -> None:
|
||||||
|
"""Send notification for a tracked company alert."""
|
||||||
|
notify("patent_alert", {
|
||||||
|
"company_name": company_name,
|
||||||
|
"alert_type": alert_type,
|
||||||
|
"message": message,
|
||||||
|
})
|
||||||
Reference in New Issue
Block a user