rickyloynd-microsoft
commented
9 months ago How many conversational turns until the failure? Can you attach a complete copy of your terminal window input & output?
Closed PriyaBrataSen closed 9 months ago
rickyloynd-microsoft
commented
9 months ago How many conversational turns until the failure? Can you attach a complete copy of your terminal window input & output?
PriyaBrataSen
commented
9 months ago @rickyloynd-microsoft Thank your Sir for looking into this matter. Sure, below is my terminal. I copied the demo.py file in working directory inside the docker file. It has the first example.
PS C:\Users\PSen\OneDrive - Ashley Furniture Industries, Inc\autogen> activate PS C:\Users\PSen\OneDrive - Ashley Furniture Industries, Inc\autogen> conda activate C:\Users\PSen\AppData\Local\anaconda3 PS C:\Users\PSen\OneDrive - Ashley Furniture Industries, Inc\autogen> docker run -it autogen2 autogen-dev@43ce554b3892:~/autogen$ python demo.py user_proxy (to assistant):
What date is today? Compare the year-to-date gain for META and TESLA.
assistant (to user_proxy):
First, let's get the current date. Then, we will fetch the stock prices for META (Facebook) and TESLA and calculate the year-to-date gain for both.
Step 1: Get the current date
from datetime import datetime
today = datetime.now()
print("Today's date:", today.strftime("%Y-%m-%d"))Step 2: Fetch stock prices and calculate year-to-date gain
To fetch stock prices, we will use the yfinance library. Please install it by running the following command:
pip install yfinanceAfter installing the library, execute the following code to fetch the stock prices and calculate the year-to-date gain:
import yfinance as yf
from datetime import datetime, timedelta
today = datetime.now()
start_of_year = datetime(today.year, 1, 1)
meta = yf.Ticker("FB")
tesla = yf.Ticker("TSLA")
meta_history = meta.history(start=start_of_year, end=today)
tesla_history = tesla.history(start=start_of_year, end=today)
meta_start_price = meta_history.iloc[0]['Close']
meta_end_price = meta_history.iloc[-1]['Close']
meta_ytd_gain = (meta_end_price - meta_start_price) / meta_start_price * 100
tesla_start_price = tesla_history.iloc[0]['Close']
tesla_end_price = tesla_history.iloc[-1]['Close']
tesla_ytd_gain = (tesla_end_price - tesla_start_price) / tesla_start_price * 100
print(f"Year-to-date gain for META (Facebook): {meta_ytd_gain:.2f}%")
print(f"Year-to-date gain for TESLA: {tesla_ytd_gain:.2f}%")This code will print the current date and the year-to-date gain for both META (Facebook) and TESLA.
EXECUTING CODE BLOCK 0 (inferred language is python)...
EXECUTING CODE BLOCK 1 (inferred language is sh)...
EXECUTING CODE BLOCK 2 (inferred language is python)... user_proxy (to assistant):
exitcode: 1 (execution failed) Code output: Today's date: 2023-12-07
Defaulting to user installation because normal site-packages is not writeable Collecting yfinance Downloading yfinance-0.2.33-py2.py3-none-any.whl (69 kB) āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā 69.0/69.0 kB 1.4 MB/s eta 0:00:00 Collecting lxml>=4.9.1 Downloading lxml-4.9.3-cp310-cp310-manylinux_2_28_x86_64.whl (7.9 MB) āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā 7.9/7.9 MB 8.7 MB/s eta 0:00:00 Requirement already satisfied: requests>=2.31 in /usr/local/lib/python3.10/site-packages (from yfinance) (2.31.0) Collecting appdirs>=1.4.4 Downloading appdirs-1.4.4-py2.py3-none-any.whl (9.6 kB) Collecting peewee>=3.16.2 Downloading peewee-3.17.0.tar.gz (2.9 MB) āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā 2.9/2.9 MB 7.3 MB/s eta 0:00:00 Installing build dependencies: started Installing build dependencies: finished with status 'done' Getting requirements to build wheel: started Getting requirements to build wheel: finished with status 'done' Preparing metadata (pyproject.toml): started Preparing metadata (pyproject.toml): finished with status 'done' Requirement already satisfied: numpy>=1.16.5 in /usr/local/lib/python3.10/site-packages (from yfinance) (1.26.2) Collecting multitasking>=0.0.7 Downloading multitasking-0.0.11-py3-none-any.whl (8.5 kB) Collecting pytz>=2022.5 Downloading pytz-2023.3.post1-py2.py3-none-any.whl (502 kB) āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā 502.5/502.5 kB 10.0 MB/s eta 0:00:00 Collecting frozendict>=2.3.4 Downloading frozendict-2.3.10-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (115 kB) āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā 115.9/115.9 kB 5.4 MB/s eta 0:00:00 Collecting html5lib>=1.1 Downloading html5lib-1.1-py2.py3-none-any.whl (112 kB) āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā 112.2/112.2 kB 14.2 MB/s eta 0:00:00 Collecting pandas>=1.3.0 Downloading pandas-2.1.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.3 MB) āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā 12.3/12.3 MB 11.3 MB/s eta 0:00:00 Requirement already satisfied: beautifulsoup4>=4.11.1 in /usr/local/lib/python3.10/site-packages (from yfinance) (4.12.2) Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.10/site-packages (from beautifulsoup4>=4.11.1->yfinance) (2.5) Requirement already satisfied: webencodings in /usr/local/lib/python3.10/site-packages (from html5lib>=1.1->yfinance) (0.5.1) Requirement already satisfied: six>=1.9 in /usr/local/lib/python3.10/site-packages (from html5lib>=1.1->yfinance) (1.16.0) Collecting tzdata>=2022.1 Downloading tzdata-2023.3-py2.py3-none-any.whl (341 kB) āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā 341.8/341.8 kB 7.6 MB/s eta 0:00:00 Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/site-packages (from pandas>=1.3.0->yfinance) (2.8.2) Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/site-packages (from requests>=2.31->yfinance) (3.6) Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/site-packages (from requests>=2.31->yfinance) (3.3.2) Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/site-packages (from requests>=2.31->yfinance) (2.1.0) Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/site-packages (from requests>=2.31->yfinance) (2023.11.17) Building wheels for collected packages: peewee Building wheel for peewee (pyproject.toml): started Building wheel for peewee (pyproject.toml): finished with status 'done' Created wheel for peewee: filename=peewee-3.17.0-cp310-cp310-linux_x86_64.whl size=848717 sha256=8e366956e5851a3fcc9c7818a72ccb9f38042516929902151b9269e744eb2006 Stored in directory: /home/autogen-dev/.cache/pip/wheels/c7/70/ad/212867e96e7004265a69c4aa5dcff00a95f547a67ba26e7e76 Successfully built peewee Installing collected packages: pytz, peewee, multitasking, appdirs, tzdata, lxml, html5lib, frozendict, pandas, yfinance Successfully installed appdirs-1.4.4 frozendict-2.3.10 html5lib-1.1 lxml-4.9.3 multitasking-0.0.11 pandas-2.1.3 peewee-3.17.0 pytz-2023.3.post1 tzdata-2023.3 yfinance-0.2.33
Failed to get ticker 'FB' reason: HTTPSConnectionPool(host='fc.yahoo.com', port=443): Max retries exceeded with url: / (Caused by SSLError(SSLError(1, '[SSL: UNSAFE_LEGACY_RENEGOTIATION_DISABLED] unsafe legacy renegotiation disabled (_ssl.c:1007)')))
FB: No timezone found, symbol may be delisted
Failed to get ticker 'TSLA' reason: HTTPSConnectionPool(host='fc.yahoo.com', port=443): Max retries exceeded with url: / (Caused by SSLError(SSLError(1, '[SSL: UNSAFE_LEGACY_RENEGOTIATION_DISABLED] unsafe legacy renegotiation disabled (_ssl.c:1007)')))
TSLA: No timezone found, symbol may be delisted
Traceback (most recent call last):
File "", line 13, in
assistant (to user_proxy):
I apologize for the error. It seems there is an issue with fetching the stock data using the yfinance library. Let's try an alternative approach using the alpha_vantage library to fetch the stock prices.
First, you need to obtain an API key from Alpha Vantage. Please follow these steps:
Next, install the alpha_vantage library by running the following command:
pip install alpha_vantageAfter installing the library and obtaining your API key, execute the following code to fetch the stock prices and calculate the year-to-date gain:
Replace YOUR_API_KEY with the API key you obtained from Alpha Vantage.
from alpha_vantage.timeseries import TimeSeries
from datetime import datetime, timedelta
api_key = "YOUR_API_KEY"
today = datetime.now()
start_of_year = datetime(today.year, 1, 1)
ts = TimeSeries(key=api_key, output_format='pandas')
meta_data, meta_history = ts.get_daily_adjusted(symbol='FB', outputsize='full')
tesla_data, tesla_history = ts.get_daily_adjusted(symbol='TSLA', outputsize='full')
meta_history = meta_history.loc[start_of_year.strftime("%Y-%m-%d"):today.strftime("%Y-%m-%d")]
tesla_history = tesla_history.loc[start_of_year.strftime("%Y-%m-%d"):today.strftime("%Y-%m-%d")]
meta_start_price = meta_history.iloc[0]['5. adjusted close']
meta_end_price = meta_history.iloc[-1]['5. adjusted close']
meta_ytd_gain = (meta_end_price - meta_start_price) / meta_start_price * 100
tesla_start_price = tesla_history.iloc[0]['5. adjusted close']
tesla_end_price = tesla_history.iloc[-1]['5. adjusted close']
tesla_ytd_gain = (tesla_end_price - tesla_start_price) / tesla_start_price * 100
print("Today's date:", today.strftime("%Y-%m-%d"))
print(f"Year-to-date gain for META (Facebook): {meta_ytd_gain:.2f}%")
print(f"Year-to-date gain for TESLA: {tesla_ytd_gain:.2f}%")This code will print the current date and the year-to-date gain for both META (Facebook) and TESLA.
EXECUTING CODE BLOCK 0 (inferred language is sh)...
EXECUTING CODE BLOCK 1 (inferred language is python)... user_proxy (to assistant):
exitcode: 1 (execution failed) Code output: Defaulting to user installation because normal site-packages is not writeable Collecting alpha_vantage Downloading alpha_vantage-2.3.1-py3-none-any.whl (31 kB) Collecting aiohttp Downloading aiohttp-3.9.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB) āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā 1.2/1.2 MB 6.9 MB/s eta 0:00:00 Requirement already satisfied: requests in /usr/local/lib/python3.10/site-packages (from alpha_vantage) (2.31.0) Collecting frozenlist>=1.1.1 Downloading frozenlist-1.4.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (225 kB) āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā 225.7/225.7 kB 4.6 MB/s eta 0:00:00 Collecting aiosignal>=1.1.2 Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB) Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/site-packages (from aiohttp->alpha_vantage) (23.1.0) Collecting multidict<7.0,>=4.5 Downloading multidict-6.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (114 kB) āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā 114.5/114.5 kB 4.9 MB/s eta 0:00:00 Collecting yarl<2.0,>=1.0 Downloading yarl-1.9.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (301 kB) āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā 301.6/301.6 kB 8.4 MB/s eta 0:00:00 Collecting async-timeout<5.0,>=4.0 Downloading async_timeout-4.0.3-py3-none-any.whl (5.7 kB) Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/site-packages (from requests->alpha_vantage) (2.1.0) Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/site-packages (from requests->alpha_vantage) (3.3.2) Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/site-packages (from requests->alpha_vantage) (3.6) Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/site-packages (from requests->alpha_vantage) (2023.11.17) Installing collected packages: multidict, frozenlist, async-timeout, yarl, aiosignal, aiohttp, alpha_vantage Successfully installed aiohttp-3.9.1 aiosignal-1.3.1 alpha_vantage-2.3.1 async-timeout-4.0.3 frozenlist-1.4.0 multidict-6.0.4 yarl-1.9.4
Traceback (most recent call last):
File "", line 11, in
assistant (to user_proxy):
I apologize for the inconvenience. It seems that the Alpha Vantage API requires a premium subscription to access the daily adjusted stock prices. In this case, I recommend using the FRED (Federal Reserve Economic Data) API to fetch the stock prices. However, FRED API does not provide stock prices for individual companies like META and TESLA.
As an alternative, you can manually check the year-to-date gain for META and TESLA using financial websites like Yahoo Finance or Google Finance:
On these websites, you can find the year-to-date gain percentage under the "Performance Outlook" section.
I apologize for not being able to provide a code-based solution for this task. If you have any other questions or need assistance with a different task, please feel free to ask.
user_proxy (to assistant):
assistant (to user_proxy):
TERMINATE
autogen-dev@43ce554b3892:~/autogen$
rickyloynd-microsoft
commented
9 months ago Are you using GPT-4 or some other LLM?
PriyaBrataSen
commented
9 months ago @rickyloynd-microsoft yeah,i am using 'model': 'gpt-4-8k'
rickyloynd-microsoft
commented
9 months ago Have you tried running on your computer without docker? That would tell us whether the SSL error is because of your docker configuration or some firewall.
PriyaBrataSen
commented
9 months ago let me run it. Should i use "use_docker":False in the code_execution_config?
PriyaBrataSen
commented
9 months ago @rickyloynd-microsoft Hello Sir, I have run it from my computer. Below are my demo.py file (removed the api key for security purpose). After that, i showed the terminal results. I am getting the same issues in my system.
Input: import autogen
config_list = [ { 'model': 'gpt-4-8k', 'api_key': '', 'base_url': '', 'api_type': 'azure', 'api_version': '', } ]
assistant = autogen.AssistantAgent( name="assistant", llm_config={ "cache_seed": 42, # seed for caching and reproducibility "config_list": config_list, # a list of OpenAI API configurations "temperature": 0, # temperature for sampling }, # configuration for autogen's enhanced inference API which is compatible with OpenAI API )
user_proxy = autogen.UserProxyAgent( name="user_proxy", human_input_mode="NEVER", max_consecutive_auto_reply=15, is_termination_msg=lambda x: x.get("content", "").rstrip().endswith("TERMINATE"), code_execution_config={ "work_dir": "coding", "use_docker":False, # set to True or image name like "python:3" to use docker }, )
math_problem_to_solve = """ What date is today? Compare the year-to-date gain for META and TESLA. """
user_proxy.initiate_chat( assistant, message=math_problem_to_solve, )
Output:
C:\Users\PSen\OneDrive - Ashley Furniture Industries, Inc\autogen_test>python demo.py
Tried to attach usage logger pyspark.databricks.pandas.usage_logger, but an exception was raised: JVM wasn't initialised. Did you call it on executor side?
user_proxy (to assistant):
What date is today? Compare the year-to-date gain for META and TESLA.
assistant (to user_proxy):
First, let's get the current date. Then, we will fetch the stock prices for META (Facebook) and TESLA and calculate the year-to-date gain for both.
Step 1: Get the current date
import datetime
today = datetime.date.today()
print(today)Step 2: Fetch stock prices for META and TESLA and calculate the year-to-date gain
import yfinance as yf
def get_stock_data(ticker, start_date, end_date):
stock = yf.Ticker(ticker)
return stock.history(start=start_date, end=end_date)
def calculate_ytd_gain(stock_data):
start_price = stock_data.iloc[0]['Close']
end_price = stock_data.iloc[-1]['Close']
return (end_price - start_price) / start_price * 100
start_date = datetime.date(today.year, 1, 1)
end_date = today + datetime.timedelta(days=1)
meta_data = get_stock_data("FB", start_date, end_date)
tesla_data = get_stock_data("TSLA", start_date, end_date)
meta_ytd_gain = calculate_ytd_gain(meta_data)
tesla_ytd_gain = calculate_ytd_gain(tesla_data)
print(f"META year-to-date gain: {meta_ytd_gain:.2f}%")
print(f"TESLA year-to-date gain: {tesla_ytd_gain:.2f}%")Please execute the above code blocks one by one. The first code block will print the current date, and the second code block will print the year-to-date gain for META and TESLA.
EXECUTING CODE BLOCK 0 (inferred language is python)... SIGALRM is not supported on Windows. No timeout will be enforced.
EXECUTING CODE BLOCK 1 (inferred language is python)... SIGALRM is not supported on Windows. No timeout will be enforced. user_proxy (to assistant):
exitcode: 1 (execution failed) Code output: 2023-12-07
Traceback (most recent call last):
File "", line 12, in
assistant (to user_proxy):
Apologies for the error. I made a mistake in the second code block. I should have imported the datetime module. Here's the corrected code:
import datetime
import yfinance as yf
def get_stock_data(ticker, start_date, end_date):
stock = yf.Ticker(ticker)
return stock.history(start=start_date, end=end_date)
def calculate_ytd_gain(stock_data):
start_price = stock_data.iloc[0]['Close']
end_price = stock_data.iloc[-1]['Close']
return (end_price - start_price) / start_price * 100
today = datetime.date.today()
start_date = datetime.date(today.year, 1, 1)
end_date = today + datetime.timedelta(days=1)
meta_data = get_stock_data("FB", start_date, end_date)
tesla_data = get_stock_data("TSLA", start_date, end_date)
meta_ytd_gain = calculate_ytd_gain(meta_data)
tesla_ytd_gain = calculate_ytd_gain(tesla_data)
print(f"META year-to-date gain: {meta_ytd_gain:.2f}%")
print(f"TESLA year-to-date gain: {tesla_ytd_gain:.2f}%")Please execute the above code block. It will print the year-to-date gain for META and TESLA.
EXECUTING CODE BLOCK 0 (inferred language is python)... SIGALRM is not supported on Windows. No timeout will be enforced. user_proxy (to assistant):
exitcode: 1 (execution failed)
Code output:
Failed to get ticker 'FB' reason: HTTPSConnectionPool(host='fc.yahoo.com', port=443): Max retries exceeded with url: / (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self signed certificate in certificate chain (_ssl.c:1002)')))
FB: No timezone found, symbol may be delisted
Failed to get ticker 'TSLA' reason: HTTPSConnectionPool(host='fc.yahoo.com', port=443): Max retries exceeded with url: / (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self signed certificate in certificate chain (_ssl.c:1002)')))
TSLA: No timezone found, symbol may be delisted
Traceback (most recent call last):
File "", line 20, in
File "C:\Users\PSen\AppData\Local\anaconda3\Lib\site-packages\pandas\core\indexing.py", line 1073, in __getitem__
return self._getitem_axis(maybe_callable, axis=axis)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\PSen\AppData\Local\anaconda3\Lib\site-packages\pandas\core\indexing.py", line 1625, in _getitem_axis
self._validate_integer(key, axis)
File "C:\Users\PSen\AppData\Local\anaconda3\Lib\site-packages\pandas\core\indexing.py", line 1557, in _validate_integer
raise IndexError("single positional indexer is out-of-bounds")
IndexError: single positional indexer is out-of-bounds
--------------------------------------------------------------------------------
assistant (to user_proxy):
I apologize for the inconvenience. It seems there is an issue with the SSL certificate verification when fetching the stock data using the yfinance library. Let's try an alternative approach using the `requests` library and the Alpha Vantage API to fetch the stock data.
First, you need to obtain an API key from Alpha Vantage. You can get a free API key by signing up at https://www.alphavantage.co/support/#api-key.
Once you have the API key, replace `<YOUR_API_KEY>` in the code below with your actual API key:
```python
import datetime
import requests
import pandas as pd
API_KEY = "<YOUR_API_KEY>"
def get_stock_data(ticker, start_date, end_date):
url = f"https://www.alphavantage.co/query?function=TIME_SERIES_DAILY_ADJUSTED&symbol={ticker}&outputsize=full&apikey={API_KEY}"
response = requests.get(url)
data = response.json()
df = pd.DataFrame(data["Time Series (Daily)"]).T
df.index = pd.to_datetime(df.index)
df = df.loc[start_date:end_date]
df["Close"] = df["4. close"].astype(float)
return df
def calculate_ytd_gain(stock_data):
start_price = stock_data.iloc[0]['Close']
end_price = stock_data.iloc[-1]['Close']
return (end_price - start_price) / start_price * 100
today = datetime.date.today()
start_date = datetime.date(today.year, 1, 1)
end_date = today
meta_data = get_stock_data("FB", start_date, end_date)
tesla_data = get_stock_data("TSLA", start_date, end_date)
meta_ytd_gain = calculate_ytd_gain(meta_data)
tesla_ytd_gain = calculate_ytd_gain(tesla_data)
print(f"META year-to-date gain: {meta_ytd_gain:.2f}%")
print(f"TESLA year-to-date gain: {tesla_ytd_gain:.2f}%")
```
Please execute the above code block after replacing `<YOUR_API_KEY>` with your actual API key. It will print the year-to-date gain for META and TESLA.
--------------------------------------------------------------------------------
>>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...
SIGALRM is not supported on Windows. No timeout will be enforced.
user_proxy (to assistant):
exitcode: 1 (execution failed)
Code output:
Traceback (most recent call last):
File "", line 26, in <module>
meta_data = get_stock_data("FB", start_date, end_date)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "", line 11, in get_stock_data
df = pd.DataFrame(data["Time Series (Daily)"]).T
~~~~^^^^^^^^^^^^^^^^^^^^^^^
KeyError: 'Time Series (Daily)'
--------------------------------------------------------------------------------
assistant (to user_proxy):
I apologize for the error. It seems that the Alpha Vantage API has a limit on the number of requests per minute. The error might have occurred due to exceeding this limit. Let's add a delay between the requests to avoid this issue.
Please try the following code:
```python
import datetime
import requests
import pandas as pd
import time
API_KEY = "<YOUR_API_KEY>"
def get_stock_data(ticker, start_date, end_date):
url = f"https://www.alphavantage.co/query?function=TIME_SERIES_DAILY_ADJUSTED&symbol={ticker}&outputsize=full&apikey={API_KEY}"
response = requests.get(url)
data = response.json()
if "Time Series (Daily)" not in data:
print(f"Error fetching data for {ticker}: {data}")
return None
df = pd.DataFrame(data["Time Series (Daily)"]).T
df.index = pd.to_datetime(df.index)
df = df.loc[start_date:end_date]
df["Close"] = df["4. close"].astype(float)
return df
def calculate_ytd_gain(stock_data):
start_price = stock_data.iloc[0]['Close']
end_price = stock_data.iloc[-1]['Close']
return (end_price - start_price) / start_price * 100
today = datetime.date.today()
start_date = datetime.date(today.year, 1, 1)
end_date = today
meta_data = get_stock_data("FB", start_date, end_date)
time.sleep(15) # Add a delay between requests
tesla_data = get_stock_data("TSLA", start_date, end_date)
if meta_data is not None and tesla_data is not None:
meta_ytd_gain = calculate_ytd_gain(meta_data)
tesla_ytd_gain = calculate_ytd_gain(tesla_data)
print(f"META year-to-date gain: {meta_ytd_gain:.2f}%")
print(f"TESLA year-to-date gain: {tesla_ytd_gain:.2f}%")
else:
print("Error fetching stock data. Please try again later.")
```
Please execute the above code block after replacing `<YOUR_API_KEY>` with your actual API key. It will print the year-to-date gain for META and TESLA.
--------------------------------------------------------------------------------
>>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...
SIGALRM is not supported on Windows. No timeout will be enforced.
user_proxy (to assistant):
exitcode: 0 (execution succeeded)
Code output:
Error fetching data for FB: {'Information': 'Thank you for using Alpha Vantage! This is a premium endpoint. You may subscribe to any of the premium plans at https://www.alphavantage.co/premium/ to instantly unlock all premium endpoints'}
Error fetching data for TSLA: {'Information': 'Thank you for using Alpha Vantage! This is a premium endpoint. You may subscribe to any of the premium plans at https://www.alphavantage.co/premium/ to instantly unlock all premium endpoints'}
Error fetching stock data. Please try again later.
--------------------------------------------------------------------------------
assistant (to user_proxy):
I apologize for the inconvenience. It seems that the Alpha Vantage API has restricted access to the daily adjusted time series data for free users. In this case, I recommend using the FRED (Federal Reserve Economic Data) API to fetch the stock data. The FRED API provides stock data for a limited number of companies, including Facebook (META) and Tesla.
First, you need to obtain an API key from FRED. You can get a free API key by signing up at https://research.stlouisfed.org/docs/api/api_key.html.
Once you have the API key, replace `<YOUR_API_KEY>` in the code below with your actual API key:
```python
import datetime
import requests
import pandas as pd
FRED_API_KEY = "<YOUR_API_KEY>"
def get_stock_data(ticker, start_date, end_date):
url = f"https://fred.stlouisfed.org/graph/fredgraph.csv?bgcolor=%23e1e9f0&chart_type=line&drp=0&fo=open%20sans&graph_bgcolor=%23ffffff&height=450&mode=fred&recession_bars=on&txtcolor=%23444444&ts=12&tts=12&width=1168&nt=0&thu=0&trc=0&show_legend=yes&show_axis_titles=yes&show_tooltip=yes&id={ticker}&scale=left&cosd={start_date}&coed={end_date}&line_color=%234572a7&link_values=false&line_style=solid&mark_type=none&mw=3&lw=2&ost=-99999&oet=99999&mma=0&fml=a&fq=Daily&fam=avg&fgst=lin&fgsnd=2020-02-01&line_index=1&transformation=lin&vintage_date={end_date}&revision_date={end_date}&nd={start_date}"
response = requests.get(url)
data = response.text.splitlines()
df = pd.read_csv(pd.StringIO("\n".join(data[1:])), header=None, names=["Date", "Close"], index_col=0, parse_dates=True)
return df.loc[start_date:end_date]
def calculate_ytd_gain(stock_data):
start_price = stock_data.iloc[0]['Close']
end_price = stock_data.iloc[-1]['Close']
return (end_price - start_price) / start_price * 100
today = datetime.date.today()
start_date = datetime.date(today.year, 1, 1)
end_date = today
meta_data = get_stock_data("WILL5000INDFC", start_date, end_date) # Facebook (META) stock data
tesla_data = get_stock_data("WILL5000INDFT", start_date, end_date) # Tesla stock data
meta_ytd_gain = calculate_ytd_gain(meta_data)
tesla_ytd_gain = calculate_ytd_gain(tesla_data)
print(f"META year-to-date gain: {meta_ytd_gain:.2f}%")
print(f"TESLA year-to-date gain: {tesla_ytd_gain:.2f}%")
```
Please execute the above code block after replacing `<YOUR_API_KEY>` with your actual API key. It will print the year-to-date gain for META and TESLA.
--------------------------------------------------------------------------------
>>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...
SIGALRM is not supported on Windows. No timeout will be enforced.
user_proxy (to assistant):
exitcode: 1 (execution failed)
Code output:
Traceback (most recent call last):
File "", line 23, in <module>
meta_data = get_stock_data("WILL5000INDFC", start_date, end_date) # Facebook (META) stock data
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "", line 11, in get_stock_data
df = pd.read_csv(pd.StringIO("\n".join(data[1:])), header=None, names=["Date", "Close"], index_col=0, parse_dates=True)
^^^^^^^^^^^
File "C:\Users\PSen\AppData\Local\anaconda3\Lib\site-packages\pandas\__init__.py", line 264, in __getattr__
raise AttributeError(f"module 'pandas' has no attribute '{name}'")
AttributeError: module 'pandas' has no attribute 'StringIO'
--------------------------------------------------------------------------------Then this SSL error must be caused by something external to docker and autogen. Which python version are you using? I see several comments on the web about what might cause this error. Search for "SSL: UNSAFE_LEGACY_RENEGOTIATION_DISABLED".
PriyaBrataSen
commented
9 months ago thank you Sir, I used the Dockerfile microsoft gave in the repo. That had Python 3:10. I am using the following commands to create my own docker image where i am using python:3.11-alpine. Sure, i will do some research. The interesting part is that everything runs fine inside google colab notbooks given by microsoft.
FROM python:3.11-alpine
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY . .
CMD [ "python","demo.py"]
sonichi
commented
9 months ago "alpine" can't install new packages. Try "python:3".
PriyaBrataSen
commented
9 months ago I prompted the agent to use 'verify'=False in the get request, so that it bypass the SSL certification issue. It works now. Thanks for your help. @rickyloynd-microsoft @sonichi
OlivierBDA
commented
2 months ago Hello, I have the same issue with SSL verification issue. How did you resolve it ? Your previous message is not enough explicit to know where to indicate the Agents to use 'verify'=False. Can you provide your llm_config list ? ie: config_list = [{"model":"xxxx", "api_key":"mykey", "base_url":"myurl"}] ? or in another part of the code ? AssistantAgent(name="MyAssistant", system_message="You are an assistant...", llm_config={"config_list" : config_list, "cache_seed":None}) Thanks Olivier
thrivedhG
commented
1 month ago @PriyaBrataSen
I prompted the agent to use 'verify'=False in the get request, so that it bypass the SSL certification issue. It works now. Hi, could you please elaborate on this comment on where we need to set verify = false condition, facing similar issue. Thanks
Hello, When i run the first example code to get Meta and Tesla ytd gain%, it runs fine in the goggle colab. However, when i run it in my computer using docker, i always get this error. Once this error happens, Autogen stop using yfinance and starts moving to some paid library. Ultimately, it fails. It seems like the SSLError. Any idea why it is happening? Any help will be highly appreciated
Downloading soupsieve-2.5-py3-none-any.whl (36 kB) Building wheels for collected packages: peewee Building wheel for peewee (pyproject.toml): started Building wheel for peewee (pyproject.toml): finished with status 'done' Created wheel for peewee: filename=peewee-3.17.0-py3-none-any.whl size=135721 sha256=b884edfe675a286ba1622af63dad5b64eefd93fd434291a32a2b49b3bae75dce Stored in directory: /root/.cache/pip/wheels/02/20/23/74a10d0cd31f5d41c19b92ddf4c138ceff01b9f4675f19dbf5 Successfully built peewee Installing collected packages: webencodings, pytz, peewee, multitasking, appdirs, tzdata, soupsieve, six, lxml, frozendict, python-dateutil, html5lib, beautifulsoup4, pandas, yfinance Successfully installed appdirs-1.4.4 beautifulsoup4-4.12.2 frozendict-2.3.10 html5lib-1.1 lxml-4.9.3 multitasking-0.0.11 pandas-2.1.3 peewee-3.17.0 python-dateutil-2.8.2 pytz-2023.3.post1 six-1.16.0 soupsieve-2.5 tzdata-2023.3 webencodings-0.5.1 yfinance-0.2.33
Failed to get ticker 'FB' reason: HTTPSConnectionPool(host='fc.yahoo.com', port=443): Max retries exceeded with url: / (Caused by SSLError(SSLError(1, '[SSL: UNSAFE_LEGACY_RENEGOTIATION_DISABLED] unsafe legacy renegotiation disabled (_ssl.c:1006)'))) FB: No price data found, symbol may be delisted (period=ytd) Traceback (most recent call last): File "", line 11, in
meta_ytd_gain = get_ytd_gain("FB")
^^^^^^^^^^^^^^^^^^
File "", line 6, in get_ytd_gain
start_price = hist.iloc[0]["Close"]