fix: fix quick start problem (#191)

* all update code

* fix a small bug

rdagent/app/benchmark/model/README.md

@@ -1,17 +1,3 @@
-
-# Preparation
-
-## Install Pytorch
-CPU CUDA will be enough for verify the implementation
-
-Please install pytorch based on your system.
-Here is an example on my system
-```bash
-pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
-pip3 install torch_geometric
-
-```
-
 # Tasks
 
 ## Task Extraction

rdagent/app/qlib_rd_loop/factor_from_report.py

@@ -103,9 +103,15 @@ def extract_hypothesis_and_exp_from_reports(report_file_path: str) -> Tuple[Qlib
 
 
 class FactorReportLoop(FactorRDLoop, metaclass=LoopMeta):
-    def __init__(self, PROP_SETTING: FACTOR_FROM_REPORT_PROP_SETTING):
-        super().__init__(PROP_SETTING=PROP_SETTING)
-        self.judge_pdf_data_items = json.load(open(PROP_SETTING.report_result_json_file_path, "r"))
+    def __init__(self, report_folder: str = None):
+        super().__init__(PROP_SETTING=FACTOR_FROM_REPORT_PROP_SETTING)
+        if report_folder is None:
+            self.judge_pdf_data_items = json.load(
+                open(FACTOR_FROM_REPORT_PROP_SETTING.report_result_json_file_path, "r")
+            )
+        else:
+            self.judge_pdf_data_items = Path(report_folder).rglob("*.pdf")
+
         self.pdf_file_index = 0
         self.valid_pdf_file_count = 0
         self.current_loop_hypothesis = None

rdagent/components/document_reader/document_reader.py

@@ -1,9 +1,11 @@
 from __future__ import annotations
 
+import io
 from pathlib import Path
 from typing import TYPE_CHECKING
 
 import fitz
+import requests
 from azure.ai.formrecognizer import DocumentAnalysisClient
 from azure.core.credentials import AzureKeyCredential
 from langchain.document_loaders import (
@@ -111,8 +113,11 @@ def load_and_process_pdfs_by_azure_document_intelligence(path: Path) -> dict[str
     return content_dict
 
 
-def extract_first_page_screenshot_from_pdf(pdf_path: Path) -> Image:
-    doc = fitz.open(pdf_path)
+def extract_first_page_screenshot_from_pdf(pdf_path: str) -> Image:
+    if not Path(pdf_path).exists():
+        doc = fitz.open(stream=io.BytesIO(requests.get(pdf_path).content), filetype="pdf")
+    else:
+        doc = fitz.open(pdf_path)
     page = doc.load_page(0)
     pix = page.get_pixmap()
     image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)

rdagent/oai/llm_utils.py

@@ -155,8 +155,6 @@ class SessionChatHistoryCache(SingletonBaseClass):
             logger.warning(f"Directory {self.session_cache_location} does not exist.")
             self.session_cache_location.mkdir(parents=True, exist_ok=True)
         json_files = [f for f in self.session_cache_location.iterdir() if f.suffix == ".json"]
-        if not json_files:
-            logger.info(f"No JSON files found in {self.session_cache_location}.")
         for file_path in json_files:
             conversation_id = file_path.stem
             with file_path.open("r") as f: