reporeformat V2 (#23)

* reformat factor implement process

* move some code to more reasonable place

* fix the bug

* add test function in factor_extract_and_implement.py

* change select factor number to ratio , add some factor implement setting and fix some bug while using knowledgebase

* change evoagent

* add abstract class EvoAgent

* add benchmark workflow

* fix some bug in llm_utils

* run wenjun's code

* fix the knowledgebase instance check

---------

Co-authored-by: xuyang1 <xuyang1@microsoft.com>

rdagent/document_process/document_analysis.py

@@ -10,7 +10,7 @@ import numpy as np
 import pandas as pd
 import tiktoken
 from jinja2 import Template
-from rdagent.core.conf import FincoSettings as Config
+from rdagent.core.conf import RDAgentSettings as Config
 from rdagent.core.log import FinCoLog
 from rdagent.core.prompts import Prompts
 from rdagent.oai.llm_utils import APIBackend, create_embedding_with_multiprocessing

rdagent/document_process/document_reader.py

@@ -9,7 +9,7 @@ from langchain.document_loaders import PyPDFDirectoryLoader, PyPDFLoader
 
 if TYPE_CHECKING:
     from langchain_core.documents import Document
-from rdagent.core.conf import FincoSettings as Config
+from rdagent.core.conf import RDAgentSettings as Config
 
 
 def load_documents_by_langchain(path: Path) -> list: