Merge pull request #679 from gventuri/release/v1.4

Release/v1.4

docs/connectors.md

@@ -89,6 +89,28 @@ df = SmartDataframe(mysql_connector)
 df.chat('What is the total amount of loans in the last year?')
 ```
 
+### Sqlite connector
+
+Similarly to the PostgreSQL and MySQL connectors, the Sqlite connector allows you to connect to a local Sqlite database file. It is designed to be easy to use, even if you are not familiar with Sqlite or with PandasAI.
+
+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.connectors import SqliteConnector
+
+connector = SqliteConnector(config={
+    "database" : "PATH_TO_DB",
+    "table" : "actor",
+    "where" :[
+        ["first_name","=","PENELOPE"]
+    ]
+})
+
+df = SmartDataframe(connector)
+df.chat('How many records are there ?')
+```
+
+
 ### Generic SQL connector
 
 The generic SQL connector allows you to connect to any SQL database that is supported by SQLAlchemy.

docs/examples.md

@@ -260,3 +260,57 @@ for question in questions:
 response = agent.explain()
 print(response)
 ```
+
+## Add Skills to the Agent
+
+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.
+
+```
+import pandas as pd
+from pandasai import Agent
+
+from pandasai.llm.openai import OpenAI
+from pandasai.skills import skill
+
+employees_data = {
+    "EmployeeID": [1, 2, 3, 4, 5],
+    "Name": ["John", "Emma", "Liam", "Olivia", "William"],
+    "Department": ["HR", "Sales", "IT", "Marketing", "Finance"],
+}
+
+salaries_data = {
+    "EmployeeID": [1, 2, 3, 4, 5],
+    "Salary": [5000, 6000, 4500, 7000, 5500],
+}
+
+employees_df = pd.DataFrame(employees_data)
+salaries_df = pd.DataFrame(salaries_data)
+
+
+@skill(
+    name="Display employee salary",
+    description="Plots the employee salaries against names",
+    usage="Displays the plot having name on x axis and salaries on y axis",
+)
+def plot_salaries(merged_df: pd.DataFrame) -> str:
+    import matplotlib.pyplot as plt
+
+    plt.bar(merged_df["Name"], merged_df["Salary"])
+    plt.xlabel("Employee Name")
+    plt.ylabel("Salary")
+    plt.title("Employee Salaries")
+    plt.xticks(rotation=45)
+    plt.savefig("temp_chart.png")
+    plt.close()
+
+
+llm = OpenAI("YOUR_API_KEY")
+agent = Agent([employees_df, salaries_df], config={"llm": llm}, memory_size=10)
+
+agent.add_skills(plot_salaries)
+
+# Chat with the agent
+response = agent.chat("Plot the employee salaries against names")
+print(response)
+
+```

docs/getting-started.md

@@ -190,6 +190,7 @@ Settings:
 - `save_charts_path`: the path where to save the charts. Defaults to `exports/charts/`. You can use this setting to override the default path.
 - `enable_cache`: whether to enable caching. Defaults to `True`. If set to `True`, PandasAI will cache the results of the LLM to improve the response time. If set to `False`, PandasAI will always call the LLM.
 - `use_error_correction_framework`: whether to use the error correction framework. Defaults to `True`. If set to `True`, PandasAI will try to correct the errors in the code generated by the LLM with further calls to the LLM. If set to `False`, PandasAI will not try to correct the errors in the code generated by the LLM.
+- `use_advanced_reasoning_framework`: whether to use the advanced reasoning framework. Defaults to `False`. If set to `True`, PandasAI will try to use advanced reasoning to improve the results of the LLM and provide an explanation for the results.
 - `max_retries`: the maximum number of retries to use when using the error correction framework. Defaults to `3`. You can use this setting to override the default number of retries.
 - `custom_prompts`: the custom prompts to use. Defaults to `{}`. You can use this setting to override the default custom prompts. You can find more information about custom prompts [here](custom-prompts.md).
 - `custom_whitelisted_dependencies`: the custom whitelisted dependencies to use. Defaults to `{}`. You can use this setting to override the default custom whitelisted dependencies. You can find more information about custom whitelisted dependencies [here](custom-whitelisted-dependencies.md).

docs/skills.md

@@ -0,0 +1,113 @@
+# Skills
+
+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.
+
+## Example Usage
+
+```python
+
+import pandas as pd
+from pandasai import Agent
+
+from pandasai.llm.openai import OpenAI
+from pandasai.skills import skill
+
+employees_data = {
+    "EmployeeID": [1, 2, 3, 4, 5],
+    "Name": ["John", "Emma", "Liam", "Olivia", "William"],
+    "Department": ["HR", "Sales", "IT", "Marketing", "Finance"],
+}
+
+salaries_data = {
+    "EmployeeID": [1, 2, 3, 4, 5],
+    "Salary": [5000, 6000, 4500, 7000, 5500],
+}
+
+employees_df = pd.DataFrame(employees_data)
+salaries_df = pd.DataFrame(salaries_data)
+
+# Function doc string to give more context to the model for use this skill
+@skill
+def plot_salaries(name: list[str], salaries: list[int]):
+    """
+    Displays the bar chart  having name on x axis and salaries on y axis
+    Args:
+        name (list[str]): Employee name
+        salaries (list[int]): Salaries
+    """
+    # plot bars
+    import matplotlib.pyplot as plt
+
+    plt.bar(name, salaries)
+    plt.xlabel("Employee Name")
+    plt.ylabel("Salary")
+    plt.title("Employee Salaries")
+    plt.xticks(rotation=45)
+
+
+
+llm = OpenAI("YOUR_API_KEY")
+agent = Agent([employees_df, salaries_df], config={"llm": llm}, memory_size=10)
+
+agent.add_skills(plot_salaries)
+
+# Chat with the agent
+response = agent.chat("Plot the employee salaries against names")
+
+
+```
+
+## Add Streamlit Skill
+
+```python
+import pandas as pd
+from pandasai import Agent
+
+from pandasai.llm.openai import OpenAI
+from pandasai.skills import skill
+import streamlit as st
+
+employees_data = {
+    "EmployeeID": [1, 2, 3, 4, 5],
+    "Name": ["John", "Emma", "Liam", "Olivia", "William"],
+    "Department": ["HR", "Sales", "IT", "Marketing", "Finance"],
+}
+
+salaries_data = {
+    "EmployeeID": [1, 2, 3, 4, 5],
+    "Salary": [5000, 6000, 4500, 7000, 5500],
+}
+
+employees_df = pd.DataFrame(employees_data)
+salaries_df = pd.DataFrame(salaries_data)
+
+# Function doc string to give more context to the model for use this skill
+@skill
+def plot_salaries(name: list[str], salary: list[int]):
+    """
+    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
+    """
+    import matplotlib.pyplot as plt
+
+    plt.bar(name, salary)
+    plt.xlabel("Employee Name")
+    plt.ylabel("Salary")
+    plt.title("Employee Salaries")
+    plt.xticks(rotation=45)
+    plt.savefig("temp_chart.png")
+    fig = plt.gcf()
+    st.pyplot(fig)
+
+
+llm = OpenAI("YOUR_API_KEY")
+agent = Agent([employees_df, salaries_df], config={"llm": llm}, memory_size=10)
+
+agent.add_skills(plot_salaries_using_streamlit)
+
+# Chat with the agent
+response = agent.chat("Plot the employee salaries against names")
+print(response)
+```

examples/from_sql.py

@@ -2,7 +2,7 @@
 
 from pandasai import SmartDatalake
 from pandasai.llm import OpenAI
-from pandasai.connectors import MySQLConnector, PostgreSQLConnector
+from pandasai.connectors import MySQLConnector, PostgreSQLConnector, SqliteConnector
 
 # With a MySQL database
 loan_connector = MySQLConnector(
@@ -38,8 +38,19 @@
     }
 )
 
+# With a Sqlite databse
+
+invoice_connector = SqliteConnector(
+    config={
+        "database": "local_path_to_db",
+        "table": "invoices",
+        "where": [["status", "=", "pending"]],
+    }
+)
 llm = OpenAI()
-df = SmartDatalake([loan_connector, payment_connector], config={"llm": llm})
+df = SmartDatalake(
+    [loan_connector, payment_connector, invoice_connector], config={"llm": llm}
+)
 response = df.chat("How many people from the United states?")
 print(response)
 # Output: 247 loans have been paid off by men.

examples/skills_example.py

@@ -0,0 +1,47 @@
+import pandas as pd
+from pandasai import Agent
+
+from pandasai.llm.openai import OpenAI
+from pandasai.skills import skill
+
+employees_data = {
+    "EmployeeID": [1, 2, 3, 4, 5],
+    "Name": ["John", "Emma", "Liam", "Olivia", "William"],
+    "Department": ["HR", "Sales", "IT", "Marketing", "Finance"],
+}
+
+salaries_data = {
+    "EmployeeID": [1, 2, 3, 4, 5],
+    "Salary": [5000, 6000, 4500, 7000, 5500],
+}
+
+employees_df = pd.DataFrame(employees_data)
+salaries_df = pd.DataFrame(salaries_data)
+
+
+# Add function docstring to give more context to model
+@skill
+def plot_salaries(name: list[str], salary: list[int]) -> str:
+    """
+    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
+    """
+    import matplotlib.pyplot as plt
+
+    plt.bar(name, salary)
+    plt.xlabel("Employee Name")
+    plt.ylabel("Salary")
+    plt.title("Employee Salaries")
+    plt.xticks(rotation=45)
+
+
+llm = OpenAI("YOUR-API-KEY")
+agent = Agent([employees_df, salaries_df], config={"llm": llm}, memory_size=10)
+
+agent.add_skills(plot_salaries)
+
+# Chat with the agent
+response = agent.chat("Plot the employee salaries against names")
+print(response)

examples/using_pandasai_log_server.py

@@ -0,0 +1,59 @@
+import os
+import pandas as pd
+from pandasai import Agent
+
+from pandasai.llm.openai import OpenAI
+
+employees_data = {
+    "EmployeeID": [1, 2, 3, 4, 5],
+    "Name": ["John", "Emma", "Liam", "Olivia", "William"],
+    "Department": ["HR", "Sales", "IT", "Marketing", "Finance"],
+}
+
+salaries_data = {
+    "EmployeeID": [1, 2, 3, 4, 5],
+    "Salary": [5000, 6000, 4500, 7000, 5500],
+}
+
+employees_df = pd.DataFrame(employees_data)
+salaries_df = pd.DataFrame(salaries_data)
+
+# Example 1: Using Environment Variables
+os.environ["LOGGING_SERVER_URL"] = "SERVER_URL"
+os.environ["LOGGING_SERVER_API_KEY"] = "YOUR_API_KEY"
+
+
+llm = OpenAI("YOUR_API_KEY")
+agent = Agent(
+    [employees_df, salaries_df],
+    config={
+        "llm": llm,
+        "enable_cache": True,
+    },
+    memory_size=10,
+)
+
+# Chat with the agent
+response = agent.chat("Plot salary against department?")
+print(response)
+
+
+# Example 2: Using Config
+llm = OpenAI("YOUR_API_KEY")
+agent = Agent(
+    [employees_df, salaries_df],
+    config={
+        "llm": llm,
+        "enable_cache": True,
+        "log_server": {
+            "server_url": "SERVER_URL",
+            "api_key": "YOUR_API_KEY",
+        },
+    },
+    memory_size=10,
+)
+
+# Chat with the agent
+response = agent.chat("Plot salary against department?")
+
+print(response)

mkdocs.yml

@@ -27,6 +27,7 @@ nav:
       - callbacks.md
       - custom-instructions.md
       - custom-prompts.md
+      - skills.md
       - custom-whitelisted-dependencies.md
   - Examples:
       - examples.md

pandasai/__init__.py

@@ -45,6 +45,7 @@
 from .schemas.df_config import Config
 from .helpers.cache import Cache
 from .agent import Agent
+from .skills import skill
 
 __version__ = importlib.metadata.version(__package__ or __name__)
 
@@ -257,4 +258,11 @@ def clear_cache(filename: str = None):
     cache.clear()
 
 
-__all__ = ["PandasAI", "SmartDataframe", "SmartDatalake", "Agent", "clear_cache"]
+__all__ = [
+    "PandasAI",
+    "SmartDataframe",
+    "SmartDatalake",
+    "Agent",
+    "clear_cache",
+    "skill",
+]