Added changes for cli tool package

pebblo/text_generation/text_generation.py

@@ -85,15 +85,13 @@ def _call_bedrock(
         Returns:
             Dict[str, Any]: Response from the Bedrock API.
         """
-        logger.info("In Bedrock")
         response = completion(
             model=f"{os.environ.get('MODEL_NAME')}",
             messages=message,
             temperature=0,
             custom_llm_provider="bedrock",
             aws_bedrock_client=bedrock_client,
         )
-        logger.info("Out from Bedrock")
         return response.json()
 
     def generate(

pebblo/tools/routers.py

@@ -12,10 +12,12 @@
 
 from pebblo.app.api.api import App
 from pebblo.app.api.req_models import Framework, ReqDiscover, ReqLoaderDoc, Runtime
+from pebblo.app.config.config import var_server_config_dict
 from pebblo.log import get_logger
 
 # Initialize logger
 logger = get_logger(__name__)
+config_details = var_server_config_dict.get()
 
 router = APIRouter(prefix="/tools")
 os.environ["OCR_AGENT"] = (
@@ -55,7 +57,10 @@ async def document_report(
         app_name, load_id = parse_files(saved_files)
 
         # Determine report path based on format
-        report_base = Path("/opt/.pebblo") / app_name
+        base_path = os.path.expanduser(
+            config_details.get("reports", {}).get("cacheDir", ".")
+        )
+        report_base = Path(base_path) / app_name
         if output_format == "pdf":
             return serve_report(report_base / "pebblo_report.pdf", app_name, "pdf")
         return serve_report(report_base / "report.json", app_name, "json")
@@ -77,9 +82,11 @@ def serve_report(report_path: Path, app_name: str, format_type: str):
     Returns:
         JSONResponse | Response: JSON report or downloadable PDF report.
     """
+
     if not report_path.exists():
         return JSONResponse(
-            {"error": f"{format_type.upper()} report not found"}, status_code=404
+            {"error": f"{format_type.upper()} report not found in {report_path}"},
+            status_code=404,
         )
 
     with open(report_path, "rb" if format_type == "pdf" else "r") as file:

pyproject.toml

@@ -123,7 +123,16 @@ dependencies = [
   "nltk==3.9.1",
   "boto3==1.36.24",
   "json-repair==0.39.0",
-  "litellm==1.61.11"
+  "litellm==1.61.11",
+  "python-multipart==0.0.17",
+  "opencv-python-headless==4.11.0.86",
+  "unstructured==0.16.20",
+  "python-magic==0.4.27",
+  "langchain==0.3.18",
+  "pdf2image==1.17.0",
+  "paddlepaddle==3.0.0b1",
+  "unstructured.paddleocr==2.8.1.0",
+  "unstructured[pdf]"
 ]
 
 # List additional groups of dependencies here (e.g. development

tools/pyproject.toml

@@ -0,0 +1,33 @@
+[build-system]
+requires = ["setuptools", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pebblo-cli"
+version = "0.1.2"
+description = "CLI tool for Pebblo"
+authors = [{ name = "Pebblo Authors", email = "[email protected]" }]
+dependencies = ["requests"]
+requires-python = ">=3.9"
+license = {file = "LICENSE.txt"}
+
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Topic :: Software Development :: Build Tools",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12"
+]
+
+[project.scripts]
+pebblo-report = "reporter.pebblo_report:main"
+
+[project.urls]
+Homepage = "https://github.com/daxa-ai/pebblo"
+Bug-Tracker = "https://github.com/daxa-ai/pebblo/issues"
+Funding = "https://donate.pypi.org"
+Source = "https://github.com/daxa-ai/pebblo/"

tools/reporter/pebblo-report → tools/reporter/pebblo_report.py

@@ -2,7 +2,9 @@
 
 import argparse
 import sys
-from reporter import analyze_files
+
+from reporter.reporter import analyze_files
+
 
 def main():
     parser = argparse.ArgumentParser(
@@ -13,34 +15,35 @@ def main():
     %(prog)s -f document1.pdf document2.pdf
     %(prog)s -f *.pdf -o pdf
     %(prog)s -f document.pdf -u http://localhost:8000/tools/document_report
-        """
+        """,
     )
-    
+
     parser.add_argument(
-        "-f", "--files",
-        required=True,
-        nargs="+",
-        help="One or more files to analyze"
+        "-f", "--files", required=True, nargs="+", help="One or more files to analyze"
     )
-    
+
     parser.add_argument(
-        "-o", "--output-format",
+        "-o",
+        "--output-format",
         choices=["json", "pdf"],
         default="json",
-        help="Output format for the report (default: json)"
+        help="Output format for the report (default: json)",
     )
-    
+
     parser.add_argument(
-        "-u", "--url",
+        "-u",
+        "--url",
         default="http://localhost:8000/tools/document_report",
-        help="API endpoint URL (default: http://localhost:8000/tools/document_report)"
+        help="API endpoint URL (default: http://localhost:8000/tools/document_report)",
     )
 
     args = parser.parse_args()
 
     # Validate URL
     if not args.url.startswith(("http://", "https://")):
-        print(f"Error: Invalid URL '{args.url}'. URL must start with http:// or https://")
+        print(
+            f"Error: Invalid URL '{args.url}'. URL must start with http:// or https://"
+        )
         sys.exit(1)
 
     try:
@@ -52,5 +55,6 @@ def main():
         print(f"Error: {str(e)}")
         sys.exit(1)
 
+
 if __name__ == "__main__":
-    main()
+    main()