Merge branch 'main' into template_improvements

# Conflicts:
#	poetry.lock

Author: matteocacciola

README.md

@@ -16,31 +16,6 @@ You can find the full documentation for PandasAI [here](https://pandas-ai.readth
 
 You can either decide to use PandasAI in your Jupyter notebooks, Streamlit apps, or use the client and server architecture from the repo.
 
-## ☁️ Using the platform
-
-The library can be used alongside our powerful data platform, making end-to-end conversational data analytics possible with as little as a few lines of code.
-
-Load your data, save them as a dataframe, and push them to the platform
-
-```python
-import pandasai as pai
-
-pai.api_key.set("your-pai-api-key")
-
-file = pai.read_csv("./filepath.csv")
-
-dataset = pai.create(path="your-organization/dataset-name",
-    df=file,
-    name="dataset-name",
-    description="dataset-description")
-
-dataset.push()
-```
-
-Your team can now access and query this data using natural language through the platform.
-
-![PandasAI](assets/demo.gif)
-
 ## 📚 Using the library
 
 ### Python Requirements
@@ -69,17 +44,20 @@ poetry add "pandasai>=3.0.0b2"
 
 ```python
 import pandasai as pai
+from pandasai_openai.openai import OpenAI
+
+llm = OpenAI("OPEN_AI_API_KEY")
+
+pai.config.set({
+    "llm": llm
+})
 
 # Sample DataFrame
 df = pai.DataFrame({
     "country": ["United States", "United Kingdom", "France", "Germany", "Italy", "Spain", "Canada", "Australia", "Japan", "China"],
     "revenue": [5000, 3200, 2900, 4100, 2300, 2100, 2500, 2600, 4500, 7000]
 })
 
-# By default, unless you choose a different LLM, it will use BambooLLM.
-# You can get your free API key signing up at https://app.pandabi.ai (you can also configure it in your .env file)
-pai.api_key.set("your-pai-api-key")
-
 df.chat('Which are the top 5 countries by sales?')
 ```
 
@@ -119,6 +97,7 @@ You can also pass in multiple dataframes to PandasAI and ask questions relating
 
 ```python
 import pandasai as pai
+from pandasai_openai.openai import OpenAI
 
 employees_data = {
     'EmployeeID': [1, 2, 3, 4, 5],
@@ -131,12 +110,15 @@ salaries_data = {
     'Salary': [5000, 6000, 4500, 7000, 5500]
 }
 
+llm = OpenAI("OPEN_AI_API_KEY")
+
+pai.config.set({
+    "llm": llm
+})
+
 employees_df = pai.DataFrame(employees_data)
 salaries_df = pai.DataFrame(salaries_data)
 
-# By default, unless you choose a different LLM, it will use BambooLLM.
-# You can get your free API key signing up at https://app.pandabi.ai (you can also configure it in your .env file)
-pai.api_key.set("your-pai-api-key")
 
 pai.chat("Who gets paid the most?", employees_df, salaries_df)
 ```
@@ -160,6 +142,7 @@ pip install "pandasai-docker"
 ```python
 import pandasai as pai
 from pandasai_docker import DockerSandbox
+from pandasai_openai.openai import OpenAI
 
 # Initialize the sandbox
 sandbox = DockerSandbox()
@@ -176,13 +159,15 @@ salaries_data = {
     'Salary': [5000, 6000, 4500, 7000, 5500]
 }
 
+llm = OpenAI("OPEN_AI_API_KEY")
+
+pai.config.set({
+    "llm": llm
+})
+
 employees_df = pai.DataFrame(employees_data)
 salaries_df = pai.DataFrame(salaries_data)
 
-# By default, unless you choose a different LLM, it will use BambooLLM.
-# You can get your free API key signing up at https://app.pandabi.ai (you can also configure it in your .env file)
-pai.api_key.set("your-pai-api-key")
-
 pai.chat("Who gets paid the most?", employees_df, salaries_df, sandbox=sandbox)
 
 # Don't forget to stop the sandbox when done

docs/mint.json

@@ -54,7 +54,7 @@
     "navigation": [
       {
         "group": "Overview",
-        "pages": ["v3/introduction", "v3/getting-started", "v3/cli", "v3/privacy-security"],
+        "pages": ["v3/introduction", "v3/getting-started", "v3/privacy-security"],
         "version": "v3"
       },
       {

docs/v3/ai-dashboards.mdx

@@ -1,60 +1,63 @@
 ---
-title: 'AI Dashboards'
-description: 'Turn your dataframes into collaborative AI dashboards'
+title: "AI Dashboards"
+description: "Turn your dataframes into interactive AI dashboards"
 ---
 
 <Note title="Beta Notice">
-Release v3 is currently in beta. This documentation reflects the features and functionality in progress and may change before the final release.
+  Release v3 is currently in beta. This documentation reflects the features and
+  functionality in progress and may change before the final release.
 </Note>
 
-PandasAI provides a [data platform](https://app.pandabi.ai) that maximizes the power of your [semantic dataframes](/v3/semantic-layer). 
+PandasAI provides a [data platform](https://app.pandabi.ai) that maximizes the power of your [semantic dataframes](/v3/semantic-layer).
 With a single line of code, you can turn your dataframes into auto-updating AI dashboards - no UI development needed.
 Each dashboard comes with a pre-generated set of insights and a conversational agent that helps you and your team explore the data through natural language.
 
 ```python
 import pandasai as pai
 
 df = pai.load("company/heart-data")
-df.push()
 ```
 
-The pushed datasets can then be accessed by your team-mates that can use natural language to ask questions about the data.
-[![PandasAI](../assets/demo.gif)](https://app.pandabi.ai)
-
 ## Auto-generated Dashboards
 
 For each materialized dataframe, the platform automatically:
+
 - Generates relevant questions about your data
 - Creates insightful charts and visualizations
 - Provides a pre-built dashboard with key insights
 - Includes a conversational agent for dynamic analysis
 
 ## Conversational Data Analysis
 
-The platform provides a powerful chat interface where your team can interact with your data using natural language. 
+The platform provides a powerful chat interface where your team can interact with your data using natural language.
 The conversational agent uses your [semantic layer](/v3/semantic-layer) definitions to understand business context and maintain consistency across analyses.
 
 When you ask questions, PandasAI:
+
 1. Uses AI to generate precise code snippets for your analysis
 2. Executes the code securely within the platform
 3. Returns visualizations and insights from the results
 
 Your data never leaves the platform - the AI only generates code, while all data processing happens in your secure environment.
 
 Ask any question about your data and:
+
 - Get instant answers with explanatory visualizations
 - Save insights as new dashboard cards
 
 ## Dynamic Analysis
 
 Your dashboards and conversational agent stay continuously synchronized with your data sources through code execution:
+
 - Each insight is powered by auto-generated code snippets
 - Code runs on live data, ensuring results are always current
 - Inherits all data cleaning and transformations defined in your [semantic layer](/v3/semantic-layer)
 
 ## Who should use the Data Platform?
-Whether you're a data scientist sharing analysis with stakeholders, a business analyst creating reports, or a team leader fostering data-driven decisions, the platform makes it easy to collaborate on data analysis through our [sharing capabilities](/v3/share-dataframes).
+
+Whether you're a data scientist creating analysis for stakeholders, a business analyst creating reports, or a team leader fostering data-driven decisions, the platform makes it easy to work with data analysis.
 
 ## How to get the Data Platform?
-Visit [app.pandabi.ai](https://app.pandabi.ai) to get started. 
-The data platform is available as a Cloud SaaS or as an enterprise solution that can be deployed on your own cloud infrastructure with full privacy and security controls. 
+
+Visit [app.pandabi.ai](https://app.pandabi.ai) to get started.
+The data platform is available as a Cloud SaaS or as an enterprise solution that can be deployed on your own cloud infrastructure with full privacy and security controls.

docs/v3/cli.mdx

@@ -1,10 +1,11 @@
 ---
-title: 'Quickstart'
-description: 'Start building your data preparation layer with PandasAI and chat with your data'
+title: "Quickstart"
+description: "Start building your data preparation layer with PandasAI and chat with your data"
 ---
 
 <Note title="Beta Notice">
-PandasAI 3.0 is currently in beta. This documentation reflects the latest features and functionality, which may evolve before the final release.
+  PandasAI 3.0 is currently in beta. This documentation reflects the latest
+  features and functionality, which may evolve before the final release.
 </Note>
 
 <iframe
@@ -31,23 +32,42 @@ pip install "pandasai>=3.0.0b2"
 
 ## Quick setup
 
-In order to use PandasAI, you need a large language model (LLM). While you can use any LLM, for the purpose of this guide, we are using BambooLLM. 
-You can get your free API key signing up at [app.pandabi.ai](https://app.pandabi.ai), which allows you to both use the data platform and get BambooLLM credits.
+In order to use PandasAI, you need a large language model (LLM). You can use any LLM, but for this guide we'll use OpenAI through the LiteLLM extension.
 
-First, import PandasAI and set up your API key:
+First, install the required extension:
+
+```bash
+pip install pandasai-litellm
+```
+
+Then, import PandasAI and configure the LLM:
 
 ```python
 import pandasai as pai
+from pandasai_litellm.litellm import LiteLLM
 
-# Get your API key from https://app.pandabi.ai
-pai.api_key.set("YOUR_PANDABI_API_KEY")
-```
+# Initialize LiteLLM with your OpenAI model
+llm = LiteLLM(model="gpt-4.1-mini", api_key="YOUR_OPENAI_API_KEY")
 
+# Configure PandasAI to use this LLM
+pai.config.set({
+    "llm": llm
+})
+```
 
 ## Chat with your data
 
 ```python
 import pandasai as pai
+from pandasai_litellm.litellm import LiteLLM
+
+# Initialize LiteLLM with your OpenAI model
+llm = LiteLLM(model="gpt-4.1-mini", api_key="YOUR_OPENAI_API_KEY")
+
+# Configure PandasAI to use this LLM
+pai.config.set({
+    "llm": llm
+})
 
 # Load your data
 df = pai.read_csv("data/companies.csv")
@@ -58,14 +78,14 @@ print(response)
 
 When you ask a question, PandasAI will use the LLM to generate the answer and output a response.
 Depending on your question, it can return different kind of responses:
+
 - string
 - dataframe
 - chart
 - number
 
 Find it more about output data formats [here](/v3/chat-and-output#available-output-formats).
 
-
 ## Creating your first data layer
 
 ### 1. Define a data source
@@ -142,29 +162,13 @@ companies = pai.load("organization/companies")
 response = stocks.chat("What is the volatility of the Coca Cola stock?")
 response = companies.chat("What is the average revenue by region?")
 
-# Query using multiple datasets 
+# Query using multiple datasets
 result = pai.chat("Compare the revenue between Coca Cola and Apple", stocks, companies)
 ```
 
-## Sharing and collaboration
-
-Share your data layers with your team:
-
-```python
-# Push datasets to the platform
-stocks.push()
-companies.push()
-```
-
-Team members can then access and query the shared datasets through:
-- The web interface at [app.pandabi.ai](https://app.pandabi.ai)
-- Their own PandasAI code using `pai.load("organization/dataset-name")`
-
-Of course, they will only be able to see the datasets they have access to. You can control access using the [permission management](/v3/permission-management) features.
-
 ## Next Steps
 
 - Learn more about [Semantic Layer](/v3/semantic-layer)
 - Join our [Discord Community](https://discord.gg/KYKj9F2FRH) for support
-{/* - Explore [Advanced Views and Joins](/v3/views) */}
-{/*- Check out our [Example Projects](/v3/examples) */}
+  {/* - Explore [Advanced Views and Joins](/v3/views) */}
+  {/* - Check out our [Example Projects](/v3/examples) */}