gventuri
commented
7 months ago Hi @vaguely_happy check out this video: https://app.gemoo.com/video/video-details/comment/621622223857717248?codeId=MlQ5yGpLeN59r
Basically, what you need to do is generating a API key from https://pandabi.ai/ and pass it, then you should be allowed to use the train method 🙂 Here's an example: import os
from pandasai import Agent
Set your PandasAI API key (you can generate one signing up at https://pandabi.ai)
os.environ["PANDASAI_API_KEY"] = "YOUR_PANDASAI_API_KEY"
agent = Agent("examples/data/Loan payments data.csv")
Example #1: train the model with docs
agent.train(docs="Only return loans information about the past 10 years")
response = agent.chat("How many loans were paid off?") print(response)
You can also see the updated docs: https://docs.pandas-ai.com/en/latest/train/#train-with-your-own-settings
Hrishikesh-Dutta0078
System Info
from pandasai import SmartDataframe from langchain_openai import AzureChatOpenAI import pandas as pd
llm = AzureChatOpenAI( openai_api_key=config.azure_openai_api_key, openai_api_version=config.azure_openai_api_version, azure_endpoint=config.azure_openai_endpoint, azure_deployment=config.model_name ) sales_by_country = pd.DataFrame({ "country": ["United States", "United Kingdom", "France", "Germany", "Italy", "Spain", "Canada", "Australia", "Japan", "China"], "sales": [5000, 3200, 2900, 4100, 2300, 2100, 2500, 2600, 4500, 7000] }) df = SmartDataframe(sales_by_country, config={"llm": llm}) response = df.chat('Which are the top 5 countries by sales?') print(response)
🐛 Describe the bug
Traceback (most recent call last): File "D:\Projects\dataCopilot-web\333.py", line 163, in
df = SmartDataframe(sales_by_country, config={"llm": llm})
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Projects\dataCopilot-web\venv\Lib\site-packages\pandasai\smart_dataframe__init.py", line 64, in init
self._agent = Agent([df], config=config)
^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Projects\dataCopilot-web\venv\Lib\site-packages\pandasai\agent\base.py", line 74, in init
config = self.get_config(config)
^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Projects\dataCopilot-web\venv\Lib\site-packages\pandasai\agent\base.py", line 147, in get_config
config = Config(**config)
^^^^^^^^^^^^^^^^
File "D:\Projects\dataCopilot-web\venv\Lib\site-packages\pydantic\v1\main.py", line 339, in init
values, fields_set, validation_error = validate_model(pydantic_self.class__, data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Projects\dataCopilot-web\venv\Lib\site-packages\pydantic\v1\main.py", line 1074, in validatemodel
v, errors = field.validate(value, values, loc=field.alias, cls=cls)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Projects\dataCopilot-web\venv\Lib\site-packages\pydantic\v1\fields.py", line 895, in validate
v, errors = self._apply_validators(v, values, loc, cls, self.post_validators)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Projects\dataCopilot-web\venv\Lib\site-packages\pydantic\v1\fields.py", line 1154, in _apply_validators
v = validator(cls, v, values, self, self.model_config)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\Projects\dataCopilot-web\venv\Lib\site-packages\pydantic\v1\class_validators.py", line 304, in
return lambda cls, v, values, field, config: validator(cls, v)
^^^^^^^^^^^^^^^^^
File "D:\Projects\dataCopilot-web\venv\Lib\site-packages\pandasai\schemas\df_config.py", line 41, in validate_llm
raise LLMNotFoundError("LLM is required")
pandasai.exceptions.LLMNotFoundError: LLM is required