can successfully generate reports with the pipeline

prospector/docker-compose.yml

@@ -28,14 +28,14 @@ services:
       context: .
       dockerfile: docker/worker/Dockerfile
     volumes:
-      - ./app:/app
+      - ./:/app
       # - ./pipeline/reports:/app/pipeline/reports
     depends_on:
       - redis
     environment:
       LOG_LEVEL: debug
       PIP_REQUIREMENTS: requirements.txt
-      GIT_CACHE: /tmp
+      GIT_CACHE: /tmp/gitcache
 
   db:
     image: postgres

prospector/pipeline/filter_entries.py

@@ -9,6 +9,7 @@
 import requests
 from psycopg2.extensions import parse_dsn
 from psycopg2.extras import DictCursor, DictRow, Json
+from tqdm import tqdm
 
 from backenddb.postgres import PostgresBackendDB
 from cli.console import ConsoleWriter, MessageStatus  # noqa: E402
@@ -182,8 +183,13 @@ async def process_cve_data():
         unprocessed_vulns = db.get_unprocessed_vulns()
 
         # Process each entry
+        pbar = tqdm(
+            unprocessed_vulns,
+            desc="Processing raw CVE data",
+            unit="CVE record",
+        )
         processed_vulns = []
-        for unprocessed_vuln in unprocessed_vulns:
+        for unprocessed_vuln in pbar:
             entry_id = unprocessed_vuln[0]
             raw_record = unprocessed_vuln[1]
 
@@ -224,7 +230,7 @@ async def map_entry(vuln):
                     "repo_url": data["git"],
                     "version_interval": version,
                 }
-                print(vuln["cve"]["id"])
+                # print(vuln["cve"]["id"]) # Sanity Check
                 return filtered_vuln
 
     return None

prospector/pipeline/job_creation.py

@@ -98,7 +98,7 @@ def _run_prospector(
         "backend_address": config.backend,
         "git_cache": config.git_cache,
         "limit_candidates": config.max_candidates,
-        "use_llm_repository_url": config.use_llm_repository_url,
+        "use_llm_repository_url": config.llm_service.use_llm_repository_url,
         "enabled_rules": config.enabled_rules,
     }
 
@@ -114,10 +114,11 @@ def _run_prospector(
         results, advisory_record = prospector(**params)
 
         generate_report(
-            results,
-            advisory_record,
-            "html",
-            f"{report_filepath}{cve_id}_{job_id}",
+            results=results,
+            advisory_record=advisory_record,
+            report_type=config.report.format,
+            report_filename=f"{report_filepath}{cve_id}_{job_id}",
+            prospector_params=params,
         )
         status = "finished"
         results = (f"{report_filepath}{cve_id}_{job_id}",)

prospector/pipeline/main.py

@@ -8,7 +8,7 @@
 from pipeline.job_creation import enqueue_jobs
 
 
-DAYS_AGO = 1  # Time period from DAYS_AGO to now to retrieve CVEs from NVD
+DAYS_AGO = 5  # Time period from DAYS_AGO to now to retrieve CVEs from NVD
 
 
 async def dispatch_jobs():