docs: fix all docs snippets instantiations (Sinaptik-AI#825)

Most of the snippets were either outdated or didn't work at all
JamesJZhang · Dec 16, 2023 · 57e5b4b · 57e5b4b
1 parent 3e7d975
commit 57e5b4b
Show file tree

Hide file tree

Showing 10 changed files with 84 additions and 49 deletions.
diff --git a/docs/LLMs/llms.md b/docs/LLMs/llms.md
@@ -58,7 +58,7 @@ import pandas as pd
 llm = OpenAI()
 
 # conversational=False is supposed to display lower usage and cost
-df = SmartDataframe("data.csv", {"llm": llm, "conversational": False})
+df = SmartDataframe("data.csv", config={"llm": llm, "conversational": False})
 
 with get_openai_callback() as cb:
     response = df.chat("Calculate the sum of the gdp of north american countries")
@@ -175,7 +175,7 @@ from pandasai import SmartDataframe
 from langchain.llms import OpenAI
 
 langchain_llm = OpenAI(openai_api_key="my-openai-api-key")
-df = SmartDataframe("data.csv", {"llm": langchain_llm})
+df = SmartDataframe("data.csv", config={"llm": langchain_llm})
 ```
 
 PandasAI will automatically detect that you are using a LangChain LLM and will convert it to a PandasAI LLM.

diff --git a/docs/connectors.md b/docs/connectors.md
@@ -38,6 +38,7 @@ The PostgreSQL connector allows you to connect to a PostgreSQL database. It is d
 To use the PostgreSQL connector, you only need to import it into your Python code and pass it to a `SmartDataframe` or `SmartDatalake` object:
 
 ```python
+from pandasai import SmartDataframe
 from pandasai.connectors import PostgreSQLConnector
 
 postgres_connector = PostgreSQLConnector(
@@ -67,6 +68,7 @@ Similarly to the PostgreSQL connector, the MySQL connector allows you to connect
 To use the MySQL connector, you only need to import it into your Python code and pass it to a `SmartDataframe` or `SmartDatalake` object:
 
 ```python
+from pandasai import SmartDataframe
 from pandasai.connectors import MySQLConnector
 
 mysql_connector = MySQLConnector(
@@ -96,6 +98,7 @@ Similarly to the PostgreSQL and MySQL connectors, the Sqlite connector allows yo
 To use the Sqlite connector, you only need to import it into your Python code and pass it to a `SmartDataframe` or `SmartDatalake` object:
 
 ```python
+from pandasai import SmartDataframe
 from pandasai.connectors import SqliteConnector
 
 connector = SqliteConnector(config={
@@ -146,6 +149,7 @@ The Snowflake connector allows you to connect to Snowflake. It is very similar t
 To use the Snowflake connector, you only need to import it into your Python code and pass it to a `SmartDataframe` or `SmartDatalake` object:
 
 ```python
+from pandasai import SmartDataframe
 from pandasai.connectors import SnowFlakeConnector
 
 snowflake_connector = SnowFlakeConnector(
@@ -176,7 +180,7 @@ The DataBricks connector allows you to connect to DataBricks. It is very similar
 To use the DataBricks connector, you only need to import it into your Python code and pass it to a `SmartDataframe` or `SmartDatalake` object:
 
 ```python
-from pandasai.connectors import DataBricksConnector
+from pandasai.connectors import DatabricksConnector
 
 databricks_connector = DatabricksConnector(
     config={
@@ -202,6 +206,7 @@ The Yahoo Finance connector allows you to connect to Yahoo Finance, by simply pa
 To use the Yahoo Finance connector, you only need to import it into your Python code and pass it to a `SmartDataframe` or `SmartDatalake` object:
 
 ```python
+from pandasai import SmartDataframe
 from pandasai.connectors.yahoo_finance import YahooFinanceConnector
 
 yahoo_connector = YahooFinanceConnector("MSFT")

diff --git a/docs/custom-head.md b/docs/custom-head.md
@@ -13,7 +13,7 @@ head_df = pd.DataFrame({
     "happiness_index": [6.94, 7.16, 6.66, 7.07, 6.38, 6.4, 7.23, 7.22, 5.87, 5.12]
 })
 
-df = SmartDataframe("data/country_gdp.csv", {
+df = SmartDataframe("data/country_gdp.csv", config={
     "custom_head": head_df
 })
 ```

diff --git a/docs/custom-instructions.md b/docs/custom-instructions.md
@@ -9,7 +9,7 @@ With PandasAI, you can easily customize the instructions that are used by the li
 ```python
 from pandasai import SmartDataframe
 
-df = SmartDataframe("data.csv", {
+df = SmartDataframe("data.csv", config={
     "custom_instructions": "Custom instructions for the generation of Python code"
 })
 ```
diff --git a/docs/custom-prompts.md b/docs/custom-prompts.md
@@ -31,7 +31,7 @@ class MyCustomPrompt(AbstractPrompt):
         self.set_var("my_custom_value", kwargs["my_custom_value"])
 
 
-df = SmartDataframe("data.csv", {
+df = SmartDataframe("data.csv", config={
     "custom_prompts": {
         "generate_python_code": MyCustomPrompt(
             my_custom_value="my custom value")
@@ -58,7 +58,7 @@ class MyCustomFileBasedPrompt(FileBasedPrompt):
     _path_to_template = "path/to/my_prompt_template.tmpl"
 
 
-df = SmartDataframe("data.csv", {
+df = SmartDataframe("data.csv", config={
     "custom_prompts": {
         "generate_python_code": MyCustomFileBasedPrompt(
             my_custom_value="my custom value")
@@ -85,7 +85,7 @@ Here's the conversation:
 """
 
 
-df = SmartDataframe("data.csv", {
+df = SmartDataframe("data.csv", config={
     "custom_prompts": {
         "generate_python_code": MyCustomPrompt()
     }

diff --git a/docs/custom-whitelisted-dependencies.md b/docs/custom-whitelisted-dependencies.md
@@ -4,7 +4,7 @@ By default, PandasAI only allows to run code that uses some whitelisted modules.
 
 ```python
 from pandasai import SmartDataframe
-df = SmartDataframe("data.csv", {
+df = SmartDataframe("data.csv", config={
     "custom_whitelisted_dependencies": ["any_module"]
 })
 ```

diff --git a/docs/examples.md b/docs/examples.md
@@ -10,6 +10,7 @@ Example of using PandasAI with a Pandas DataFrame
 ```python
 from pandasai import SmartDataframe
 import pandas as pd
+from pandasai.llm import OpenAI
 
 # pandas dataframe
 df = pd.DataFrame({
@@ -18,10 +19,12 @@ df = pd.DataFrame({
     "happiness_index": [6.94, 7.16, 6.66, 7.07, 6.38, 6.4, 7.23, 7.22, 5.87, 5.12]
 })
 
+llm = OpenAI(api_token="YOUR_API_TOKEN")
+
 # convert to SmartDataframe
-df = SmartDataframe(df)
+df = SmartDataframe(df, config={"llm": llm})
 
-df.chat('Calculate the sum of the gdp of north american countries')
+response = df.chat('Calculate the sum of the gdp of north american countries')
 print(response)
 # Output: 20901884461056
 ```
@@ -32,11 +35,14 @@ Example of using PandasAI with a CSV file
 
 ```python
 from pandasai import SmartDataframe
+from pandasai.llm import OpenAI
+
+llm = OpenAI(api_token="YOUR_API_TOKEN")
 
 # You can instantiate a SmartDataframe with a path to a CSV file
-df = Smartdataframe("data/Loan payments data.csv")
+df = SmartDataframe("data/Loan payments data.csv", config={"llm": llm})
 
-df.chat("How many loans are from men and have been paid off?")
+response = df.chat("How many loans are from men and have been paid off?")
 print(response)
 # Output: 247 loans have been paid off by men.
 ```
@@ -53,11 +59,14 @@ Then, you can use PandasAI with an Excel file as follows:
 
 ```python
 from pandasai import SmartDataframe
+from pandasai.llm import OpenAI
+
+llm = OpenAI(api_token="YOUR_API_TOKEN")
 
 # You can instantiate a SmartDataframe with a path to an Excel file
-df = Smartdataframe("data/Loan payments data.xlsx")
+df = SmartDataframe("data/Loan payments data.xlsx", config={"llm": llm})
 
-df.chat("How many loans are from men and have been paid off?")
+response = df.chat("How many loans are from men and have been paid off?")
 print(response)
 # Output: 247 loans have been paid off by men.
 ```
@@ -74,10 +83,13 @@ Then, you can use PandasAI with a Google Sheet as follows:
 
 ```python
 from pandasai import SmartDataframe
+from pandasai.llm import OpenAI
+
+llm = OpenAI(api_token="YOUR_API_TOKEN")
 
 # You can instantiate a SmartDataframe with a path to a Google Sheet
-df = Smartdataframe("https://docs.google.com/spreadsheets/d/fake/edit#gid=0")
-df.chat("How many loans are from men and have been paid off?")
+df = SmartDataframe("https://docs.google.com/spreadsheets/d/fake/edit#gid=0", config={"llm": llm})
+response = df.chat("How many loans are from men and have been paid off?")
 print(response)
 # Output: 247 loans have been paid off by men.
 ```
@@ -97,15 +109,21 @@ Then, you can use PandasAI with a Polars DataFrame as follows:
 ```python
 from pandasai import SmartDataframe
 import polars as pl
+from pandasai.llm import OpenAI
+
+llm = OpenAI(api_token="YOUR_API_TOKEN")
+
 
 # You can instantiate a SmartDataframe with a Polars DataFrame
 
-df = pd.DataFrame([
+df = pl.DataFrame({
     "country": ["United States", "United Kingdom", "France", "Germany", "Italy", "Spain", "Canada", "Australia", "Japan", "China"],
     "gdp": [19294482071552, 2891615567872, 2411255037952, 3435817336832, 1745433788416, 1181205135360, 1607402389504, 1490967855104, 4380756541440, 14631844184064],
     "happiness_index": [6.94, 7.16, 6.66, 7.07, 6.38, 6.4, 7.23, 7.22, 5.87, 5.12]
-])
-df.chat("How many loans are from men and have been paid off?")
+})
+
+df = SmartDataframe(df, config={"llm": llm})
+response = df.chat("How many loans are from men and have been paid off?")
 print(response)
 # Output: 247 loans have been paid off by men.
 ```
@@ -116,10 +134,13 @@ Example of using PandasAI to generate a chart from a Pandas DataFrame
 
 ```python
 from pandasai import SmartDataframe
+from pandasai.llm import OpenAI
 
-df = SmartDataframe("data/Countries.csv")
+llm = OpenAI(api_token="YOUR_API_TOKEN")
+
+df = SmartDataframe("data/Countries.csv", config={"llm": llm})
 response = df.chat(
-    "Plot the histogram of countries showing for each the gpd, using different colors for each bar"
+    "Plot the histogram of countries showing for each the gpd, using different colors for each bar",
 )
 print(response)
 # Output: check out images/histogram-chart.png
@@ -131,12 +152,17 @@ You can pass a custom path to save the charts. The path must be a valid global p
 Below is the example to Save Charts with user defined location.
 
 ```python
+import os
 from pandasai import SmartDataframe
+from pandasai.llm import OpenAI
 
 user_defined_path = os.getcwd()
-df = SmartDataframe("data/Countries.csv", {
+llm = OpenAI(api_token="YOUR_API_TOKEN")
+
+df = SmartDataframe("data/Countries.csv", config={
     "save_charts": True,
     "save_charts_path": user_defined_path,
+    "llm": llm
 })
 response = df.chat(
     "Plot the histogram of countries showing for each the gpd,"
@@ -153,6 +179,7 @@ Example of using PandasAI with multiple dataframes. In order to use multiple dat
 ```python
 from pandasai import SmartDatalake
 import pandas as pd
+from pandasai.llm import OpenAI
 
 employees_data = {
     'EmployeeID': [1, 2, 3, 4, 5],
@@ -168,7 +195,9 @@ salaries_data = {
 employees_df = pd.DataFrame(employees_data)
 salaries_df = pd.DataFrame(salaries_data)
 
-df = SmartDatalake([employees_df, salaries_df])
+llm = OpenAI(api_token="YOUR_API_TOKEN")
+
+df = SmartDatalake([employees_df, salaries_df], config={"llm": llm})
 response = df.chat("Who gets paid the most?")
 print(response)
 # Output: Olivia gets paid the most.
@@ -181,8 +210,10 @@ dataframe by gender and then by loans that have been paid off.
 
 ```python
 from pandasai import SmartDataframe
+from pandasai.llm import OpenAI
 
-df = SmartDataframe("data/Loan payments data.csv")
+llm = OpenAI(api_token="YOUR_API_TOKEN")
+df = SmartDataframe("data/Loan payments data.csv", config={"llm": llm})
 
 # We filter by males only
 from_males_df = df.chat("Filter the dataframe by women")
@@ -222,7 +253,7 @@ With the chat agent, you can engage in dynamic conversations where the agent ret
 
 Feel free to initiate conversations, seek clarifications, and explore explanations to enhance your interactions with the chat agent!
 
-```
+```python
 import pandas as pd
 from pandasai import Agent
 
@@ -265,7 +296,7 @@ print(response)
 
 You can add customs functions for the agent to use, allowing the agent to expand its capabilities. These custom functions can be seamlessly integrated with the agent's skills, enabling a wide range of user-defined operations.
 
-```
+```python
 import pandas as pd
 from pandasai import Agent
 
@@ -288,12 +319,9 @@ salaries_df = pd.DataFrame(salaries_data)
 
 
 @skill
-def plot_salaries(merged_df: pd.DataFrame) -> str:
+def plot_salaries(merged_df: pd.DataFrame):
     """
-    Displays the bar chart having name on x axis and salaries on y axis using streamlit
-    Args:
-        name (list[str]): Employee name
-        salaries (list[int]): Salaries
+    Displays the bar chart having name on x-axis and salaries on y-axis using streamlit
     """
     import matplotlib.pyplot as plt
 

diff --git a/docs/getting-started.md b/docs/getting-started.md
@@ -44,6 +44,8 @@ Below is simple example to get started with `pandasai`.
 ```python
 import pandas as pd
 from pandasai import SmartDataframe
+from pandasai.llm import OpenAI
+
 
 # Sample DataFrame
 df = pd.DataFrame({
@@ -53,7 +55,6 @@ df = pd.DataFrame({
 })
 
 # Instantiate a LLM
-from pandasai.llm import OpenAI
 llm = OpenAI(api_token="YOUR_API_TOKEN")
 
 df = SmartDataframe(df, config={"llm": llm})
@@ -124,6 +125,8 @@ PandasAI also supports agents. While a `SmartDataframe` or a `SmartDatalake` can
 ```python
 from pandasai import Agent
 import pandas as pd
+from pandasai.llm import OpenAI
+
 
 # Sample DataFrames
 df1 = pd.DataFrame({
@@ -132,7 +135,9 @@ df1 = pd.DataFrame({
     "happiness_index": [6.94, 7.16, 6.66, 7.07, 6.38, 6.4, 7.23, 7.22, 5.87, 5.12]
 })
 
-agent = Agent([df1])
+llm = OpenAI(api_token="YOUR_API_TOKEN")
+
+agent = Agent([df1], config={"llm": llm})
 ```
 
 Then, you can use the agent as follows:
@@ -214,6 +219,3 @@ Try out PandasAI in your browser:
 
 You can find some examples [here](examples.md).
 
-```
-
-```