diff --git a/.gitattributes b/.gitattributes
deleted file mode 100644
index dfe0770..0000000
--- a/.gitattributes
+++ /dev/null
@@ -1,2 +0,0 @@
-# Auto detect text files and perform LF normalization
-* text=auto
diff --git a/.gitignore b/.gitignore
index 7f9a822..6769e21 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,3 +1,160 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
 
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
 .env
-test_server.py
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..09e90ca
--- /dev/null
+++ b/README.md
@@ -0,0 +1,13 @@
+# fork from JayZhou repository
+
+## app.py is the original file
+
+## app2.py is the file created by me
+
+## Key points
+
+1. To test FastAPI, go to the swagger file under http://127.0.0.1/8000/docs
+
+2. Import multiple versions of pydrantic
+
+3. Use StructuredTool to create tools for agent
diff --git a/app2.py b/app2.py
new file mode 100644
index 0000000..0714f5b
--- /dev/null
+++ b/app2.py
@@ -0,0 +1,254 @@
+import os 
+import time
+from dotenv import load_dotenv 
+import json 
+import requests 
+
+from langchain.indexes import VectorstoreIndexCreator
+from langchain_community.document_loaders.base import Document
+from langchain_community.utilities import ApifyWrapper
+
+from langchain_openai import ChatOpenAI 
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.prompts import PromptTemplate
+from langchain.chains.summarize import load_summarize_chain
+
+# import as an alias 
+from pydantic import BaseModel as BaseModelv2, Field as Fieldv2 # pydantic v2 not compatible with langchain
+from pydantic.v1 import BaseModel as BaseModelv1, Field as Fieldv1 # pydantic v1 compatible with langchain
+
+from langchain.tools import StructuredTool
+
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+
+from langchain.agents.format_scratchpad.openai_tools import (
+    format_to_openai_tool_messages
+)
+from langchain.agents.output_parsers.openai_tools import (
+    OpenAIToolsAgentOutputParser
+)
+
+from langchain.agents import AgentExecutor
+
+import streamlit as st
+
+from fastapi import FastAPI
+
+
+# 0. Load env variables 
+load_dotenv() 
+APIFY_API_TOKEN = os.getenv("APIFY_API_TOKEN")
+SERPER_API_KEY = os.getenv("SERPER_API_KEY")
+
+# 1. function for search
+def search(query) -> str:
+    """Search a query on Google for the content and the referenced URL"""
+    print(f"Googling {query}...")
+    url = "https://google.serper.dev/search"
+
+    payload = json.dumps({
+        "q": query
+    })
+
+    headers = {
+        'X-API-KEY': SERPER_API_KEY,
+        'Content-Type': 'application/json'
+    }
+
+    response = requests.request("POST", url, headers=headers, data=payload)
+
+    print("SEARCH FOUND: \n", response.text)
+
+    return response.text
+
+# 2. function for scraping the website 
+def scrape_website(objective:str, url: str) -> str: 
+
+    print(f"Scraping website [{url}]...")
+    apify = ApifyWrapper() 
+
+    loader = apify.call_actor(
+        actor_id="apify/website-content-crawler",
+        run_input={"startUrls": [{"url": url}]},
+        dataset_mapping_function=lambda item: Document(
+            page_content=item["text"] or "", metadata={"source": item["url"]}
+        ),
+    )
+
+    index = VectorstoreIndexCreator().from_loaders([loader])
+
+    result = index.query_with_sources(objective)
+
+    print("ANSWERS: \n", result["answer"])
+    print("SOURCES: \n", result["sources"])
+
+    output = result["answer"]
+    if len(output) > 10000: 
+        output = summarize(objective, output)
+
+    return output
+
+# 3. function for summarizing the website content
+def summarize(objective, content):
+    print("Summarizing...")
+
+    llm = ChatOpenAI(temperature=0, model="gpt-3.5-turbo-16k-0613")
+
+    text_splitter = RecursiveCharacterTextSplitter(
+        separators=["\n\n", "\n"], chunk_size=10000, chunk_overlap=500)
+    docs = text_splitter.create_documents([content])
+    map_prompt = """
+    Write a summary of the following text for {objective}:
+    "{text}"
+    SUMMARY:
+    """
+    map_prompt_template = PromptTemplate(
+        template=map_prompt, input_variables=["text", "objective"])
+
+    summary_chain = load_summarize_chain(
+        llm=llm,
+        chain_type='map_reduce',
+        map_prompt=map_prompt_template,
+        combine_prompt=map_prompt_template,
+        verbose=True
+    )
+
+    output = summary_chain.run(input_documents=docs, objective=objective)
+
+    print("SUMMARIZED: \n", output)
+
+    return output
+
+# 4. Tool for searching the internet 
+searchTool = StructuredTool.from_function(
+    func=search, 
+    name="Search", 
+    description="Search a query on Google for the content and the referenced URL. You should ask targeted questions"
+)
+
+# 4. Tool for scraping the website
+class ScrapeWebsiteInput(BaseModelv1):
+    """Inputs for Scraping a website on the given objective"""
+    objective: str = Fieldv1(description="The objective & task that users give to the agent")
+    url: str = Fieldv1(description="The url of the website to be scraped")
+
+scrapeWebsiteTool = StructuredTool.from_function(
+    func=scrape_website, 
+    name="scrape_website",
+    description="useful when you need to get data from a website url, passing both url and objective to the function; DO NOT make up any url, the url should only be from the search results",
+    args_schema=ScrapeWebsiteInput, 
+    return_direct=False
+)
+
+tools = [searchTool, scrapeWebsiteTool]
+
+MEMORY_KEY = "search_history"
+
+prompt = ChatPromptTemplate.from_messages([
+    (
+        "system",
+        """You are a world class researcher, who can do detailed research on any topic and produce facts based results; 
+        you do not make things up, you will try as hard as possible to gather facts & data to back up the research
+        
+        Please make sure you complete the objective above with the following rules:
+        1/ You should do enough research to gather as much information as possible about the objective
+        2/ If there are url of relevant links & articles, you will scrape it to gather more information
+        3/ After scraping & search, you should think "is there any new things i should search & scraping based on the data I collected to increase research quality?" If answer is yes, continue; But don't do this more than 3 iteratins
+        4/ You should not make things up, you should only write facts & data that you have gathered
+        5/ In the final output, You should include all reference data & links to back up your research; You should include all reference data & links to back up your research
+        6/ In the final output, You should include all reference data & links to back up your research; You should include all reference data & links to back up your research
+        """
+    ),
+    MessagesPlaceholder(variable_name=MEMORY_KEY),
+    ("user", "{input}"),
+    MessagesPlaceholder(variable_name="agent_scratchpad"),
+])
+
+llm = ChatOpenAI(model="gpt-3.5-turbo", temperature=0)
+
+llm_with_tools = llm.bind_tools(tools)
+
+agent = (
+    {
+        "input": lambda x: x["input"],
+        "agent_scratchpad": lambda x: format_to_openai_tool_messages(
+            x["intermediate_steps"]
+        ),
+        "search_history": lambda x: x["search_history"],
+    }
+    | prompt
+    | llm_with_tools
+    | OpenAIToolsAgentOutputParser()
+)
+
+agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
+
+def do_research(topic: str): 
+    search_history = []
+
+    result = agent_executor.invoke({
+        "input": topic, 
+        "search_history": search_history
+    })
+
+    print("RESULT: ", result)
+
+    return result
+
+
+def test(): 
+    topic = "Why has Meta's Thread product grown more quickly than other products?"
+
+    #search_result = search(topic)
+    #searchTool.invoke(topic)
+    #print(isinstance(ScrapeWebsiteInput, BaseModel))
+    #print(type(ScrapeWebsiteInput))
+    # scrape_website(
+    #     objective=topic, 
+    #     url="https://www.nytimes.com/2023/07/11/technology/threads-zuckerberg-meta-google-plus.html"
+    # )
+    # scrapeWebsiteTool.invoke({
+    #     "objective": topic, 
+    #     "url": "https://www.techtarget.com/whatis/feature/Meta-Threads-explained-Everything-you-need-to-know"
+    # })
+    result = do_research(topic)
+    print(result)
+
+
+def app(): 
+    st.set_page_config(page_title="AI research agent", page_icon=":bird:")
+
+    st.header("AI research agent :bird:")
+    topic = st.text_input("Research Topic:")
+
+    placeholder = st.empty()
+
+    if topic:
+        start_time = time.time()
+        placeholder.text(f"Doing research ...")
+
+        result = do_research(topic)
+
+        end_time = time.time()
+        research_time = int(end_time - start_time)
+
+        placeholder.text(f"Here is what I have found after [{research_time} seconds]:")
+
+        st.info(result["output"])
+
+# if __name__ == "__main__": 
+#     # test()  # Local Testing 
+#     app()   # Streamlit webapp 
+
+# FastAPI service 
+api = FastAPI()
+
+class Query(BaseModelv2): 
+    topic: str 
+
+@api.post("/")
+def service(query: Query): 
+    topic = query.topic
+    result = do_research(topic)
+    return result
+
diff --git a/requirements.txt b/requirements.txt
index 8a1d7ee..60ef66e 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,7 +1,7 @@
 fastapi[all]
 openai
 python-dotenv
-pydantic==1.*
+pydantic
 langchain
 bs4
 tiktoken
\ No newline at end of file
diff --git a/test-api.txt b/test-api.txt
new file mode 100644
index 0000000..3ef5f1a
--- /dev/null
+++ b/test-api.txt
@@ -0,0 +1,7 @@
+curl -X 'POST' \
+  'http://127.0.0.1:8000/' \
+  -H 'accept: application/json' \
+  -H 'Content-Type: application/json' \
+  -d '{
+  "topic": "Common ways to get rich"
+}'
\ No newline at end of file