Sinaptik-AI · gventuri · Jan 15, 2025 · Jan 14, 2025 · Jan 14, 2025 · Jan 14, 2025
diff --git a/README.md b/README.md
@@ -4,18 +4,12 @@
 [![CI](https://github.com/sinaptik-ai/pandas-ai/actions/workflows/ci.yml/badge.svg)](https://github.com/sinaptik-ai/pandas-ai/actions/workflows/ci.yml/badge.svg)
 [![CD](https://github.com/sinaptik-ai/pandas-ai/actions/workflows/cd.yml/badge.svg)](https://github.com/sinaptik-ai/pandas-ai/actions/workflows/cd.yml/badge.svg)
 [![Coverage](https://codecov.io/gh/sinaptik-ai/pandas-ai/branch/main/graph/badge.svg)](https://codecov.io/gh/sinaptik-ai/pandas-ai)
-[![Discord](https://dcbadge.vercel.app/api/server/kF7FqH2FwS?style=flat&compact=true)](https://discord.gg/kF7FqH2FwS)
+[![Discord](https://dcbadge.vercel.app/api/server/kF7FqH2FwS?style=flat&compact=true)](https://discord.gg/KYKj9F2FRH)
 [![Downloads](https://static.pepy.tech/badge/pandasai)](https://pepy.tech/project/pandasai) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
 [![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1ZnO-njhL7TBOYPZaqvMvGtsjckZKrv2E?usp=sharing)
 
 PandaAI is a Python platform that makes it easy to ask questions to your data in natural language. It helps non-technical users to interact with their data in a more natural way, and it helps technical users to save time, and effort when working with data.
 
-# 🚀 Deploying PandaAI
-
-PandaAI can be used in a variety of ways. You can easily use it in your Jupyter notebooks or Streamlit apps, or you can deploy it as a REST API such as with FastAPI or Flask.
-
-If you are interested in the managed PandaAI Cloud or our self-hosted Enterprise Offering, [contact us](https://forms.gle/JEUqkwuTqFZjhP7h8).
-
 # 🔧 Getting started
 
 You can find the full documentation for PandaAI [here](https://pandas-ai.readthedocs.io/en/latest/).
@@ -24,30 +18,30 @@ You can either decide to use PandaAI in your Jupyter notebooks, Streamlit apps,
 
 ## ☁️ Using the platform
 
-[![PandaAI platform](assets/demo.gif?raw=true)](https://www.youtube.com/watch?v=kh61wEy9GYM)
-
-### 📦 Installation
+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. 
 
-PandaAI platform is uses a dockerized client-server architecture. You will need to have Docker installed in your machine.
+Load your data, save them as a dataframe, and push them to the platform
 
-```bash
-git clone https://github.com/sinaptik-ai/pandas-ai/
-cd pandas-ai
-docker-compose build
-```
-
-### 🚀 Running the platform
+```python
+import pandasai as pai
 
-Once you have built the platform, you can run it with:
+df = pai.read_csv("./filepath.csv")
+df.push()
 
-```bash
-docker-compose up
+df.save(path="your-organization/dataset-name",
+    name="dataset-name",
+    description="dataset-description")
 ```
+Your team can now access and query this data using natural language through the platform.
 
-This will start the client and server, and you can access the client at `http://localhost:3000`.
+![PandaAI](assets/demo.gif) 
 
 ## 📚 Using the library
 
+### Python Requirements
+
+Python version `3.8+ <3.12`
+
 ### 📦 Installation
 
 You can install the PandaAI library using pip or poetry.
@@ -64,18 +58,11 @@ With poetry:
 poetry add pandasai
 ```
 
-### 🔍 Demo
-
-Try out the PandaAI library yourself in your browser:
-
-[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1ZnO-njhL7TBOYPZaqvMvGtsjckZKrv2E?usp=sharing)
-
 ### 💻 Usage
 
 #### Ask questions
 
 ```python
-import os
 import pandasai as pai
 
 # Sample DataFrame
@@ -85,8 +72,8 @@ df = pai.DataFrame({
 })
 
 # By default, unless you choose a different LLM, it will use BambooLLM.
-# You can get your free API key signing up at https://pandabi.ai (you can also configure it in your .env file)
-os.environ["PANDABI_API_KEY"] = "YOUR_PANDABI_API_KEY"
+# 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?')
 ```
@@ -126,8 +113,6 @@ df.chat(
 You can also pass in multiple dataframes to PandaAI and ask questions relating them.
 
 ```python
-import os
-import pandas as pd
 from pandasai import Agent
 
 employees_data = {
@@ -141,12 +126,12 @@ salaries_data = {
     'Salary': [5000, 6000, 4500, 7000, 5500]
 }
 
-employees_df = pd.DataFrame(employees_data)
-salaries_df = pd.DataFrame(salaries_data)
+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://pandabi.ai (you can also configure it in your .env file)
-os.environ["PANDABI_API_KEY"] = "YOUR_PANDABI_API_KEY"
+# 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")
 
 agent = Agent([employees_df, salaries_df])
 agent.chat("Who gets paid the most?")
@@ -168,7 +153,7 @@ If you are interested in managed PandaAI Cloud or self-hosted Enterprise Offerin
 
 - [Docs](https://pandas-ai.readthedocs.io/en/latest/) for comprehensive documentation
 - [Examples](examples) for example notebooks
-- [Discord](https://discord.gg/kF7FqH2FwS) for discussion with the community and PandaAI team
+- [Discord](https://discord.gg/KYKj9F2FRH) for discussion with the community and PandaAI team
 
 ## 🤝 Contributing
 

diff --git a/assets/demo.gif b/assets/demo.gif
diff --git a/docs/assets/demo.gif b/docs/assets/demo.gif
diff --git a/docs/assets/permissions.png b/docs/assets/permissions.png
diff --git a/docs/mint.json b/docs/mint.json
@@ -54,7 +54,7 @@
     "navigation": [
       {
         "group": "Overview",
-        "pages": ["v3/introduction", "v3/getting-started", "v3/output-formats"],
+        "pages": ["v3/introduction", "v3/getting-started"],
         "version": "v3"
       },
       {
@@ -64,7 +64,7 @@
       },
       {
         "group": "Natural Language",
-        "pages": ["v3/overview-nl", "v3/large-language-models", "v3/chat-and-cache", "v3/privacy-and-security"],
+        "pages": ["v3/overview-nl", "v3/large-language-models", "v3/chat-and-cache", "v3/output-formats"],
         "version": "v3"
       },
       {

diff --git a/docs/v3/agent.mdx b/docs/v3/agent.mdx
@@ -8,7 +8,7 @@ You can train PandaAI to understand your data better and to improve its performa
 
 ## Prerequisites
 
-Before you start training PandaAI, you need to set your PandaAI API key. You can generate your API key by signing up at [https://pandabi.ai](https://pandabi.ai).
+Before you start training PandaAI, you need to set your PandaAI API key. You can generate your API key by signing up at [https://app.pandabi.ai](https://app.pandabi.ai).
 
 Then you can set your API key as an environment variable:
 
@@ -35,7 +35,7 @@ As an alternative, if you want to use a local vector store (enterprise only for
 ```python
 from pandasai import Agent
 
-# Set your PandasAI API key (you can generate one signing up at https://pandabi.ai)
+# Set your PandasAI API key (you can generate one signing up at https://app.pandabi.ai)
 os.environ["PANDABI_API_KEY"] = "YOUR_PANDABI_API_KEY"
 
 agent = Agent("data.csv")

diff --git a/docs/v3/ai-dashboards.mdx b/docs/v3/ai-dashboards.mdx
@@ -3,17 +3,20 @@ title: 'AI Dashboards'
 description: 'Turn your dataframes into collaborative AI dashboards'
 ---
 
-PandaAI provides a data platform that maximizes the power of your [semantic dataframes](/v3/dataframes). 
+PandaAI provides a [data platform](https://app.pandabi.ai) that maximizes the power of your [semantic dataframes](/v3/dataframes). 
 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/customers")
+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.
+[![PandaAI](../assets/demo.gif)](https://app.pandabi.ai)
+
 ## Auto-generated Dashboards
 
 For each materialized dataframe, the platform automatically:
@@ -49,4 +52,5 @@ Your dashboards and conversational agent stay continuously synchronized with you
 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).
 
 ## How to get the Data Platform?
-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. 
diff --git a/docs/v3/getting-started.mdx b/docs/v3/getting-started.mdx
@@ -19,12 +19,12 @@ pip install pandasai
 ## Chat with your data
 
 In order to use PandaAI, 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 [pandabi.ai](https://pandabi.ai), which allows you to both use the data platform and get BambooLLM credits.
+You can get your free API key signing up at [pandabi.ai](https://app.pandabi.ai), which allows you to both use the data platform and get BambooLLM credits.
 
 ```python
 import pandasai as pai
 
-# replace "YOUR_PANDABI_API_KEY" with your API key from https://pandabi.ai
+# get the api key from https://app.pandabi.ai
 pai.api_key.set("YOUR_PANDABI_API_KEY")
 ```
 
@@ -38,9 +38,17 @@ df = pai.read_csv("filepath")
 
 # ask questions
 df.chat('Which are the top 5 countries by sales?')
-# replace "Which are the top 5 countries by sales?" with your question
 ```
 
+When you ask a question, PandaAI will use the LLM to generate the answer and output a response.
+Depending on your question, it can return different objects:
+- string
+- dataframe
+- chart
+- number
+
+Find it more about output data formats [here](/v3/output-formats)
+
 ### Save and load dataframes
 
 To work faster with your data, you can save dataframes.
@@ -68,6 +76,27 @@ df = pai.read_csv("filepath")
 df.load("organization/dataset-name")
 ```
 
+## Share with your team
+
+Dataframes can be shared with your team using the [data platform](/v3/ai-dashboards).
+
+```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.
+[![PandaAI](../assets/demo.gif)](https://app.pandabi.ai)
+
+
+## Advanced features
+
+- Explore the [Semantic Layer](/v3/semantic-layer) to learn how to configure, save and dataframes
+- Learn more about the [Natural Language Layer](/v3/overview-nl)
+
 
 ### Chat with multiple dataframes
 
@@ -81,11 +110,4 @@ df_orders = pai.load("company/orders")
 df_products = pai.load("company/products")
 
 response = pai.chat('Who are our top 5 customers and what products do they buy most frequently?', df_customers, df_orders, df_products)
-```
-
-## Share with your team
-
-## Advances features
-
-- Explore the [Semantic Layer](/v3/semantic-layer) to learn how to configure, save and dataframes
-- Learn more about the [Natural Language Layer](/v3/overview-nl)
+```
diff --git a/docs/v3/large-language-models.mdx b/docs/v3/large-language-models.mdx
@@ -11,13 +11,13 @@ Then, every time you use the `.chat()` method, it will use the configured LLM.
 ## BambooLLM
 
 BambooLLM is the default LLM for PandaAI, fine-tuned for data analysis.
-You can get your free API key by signing up at [pandabi.ai](https://pandabi.ai).
+You can get your free API key by signing up at [pandabi.ai](https://app.pandabi.ai).
 
 ```python
 import pandasai as pai
 
 # set up BambooLLM
-# replace "YOUR_PANDABI_API_KEY" with your API key from https://pandabi.ai
+# replace "YOUR_PANDABI_API_KEY" with your API key from https://app.pandabi.ai
 os.environ["PANDABI_API_KEY"] = "YOUR_PANDABI_API_KEY"
 ```
 

diff --git a/docs/v3/output-formats.mdx b/docs/v3/output-formats.mdx
@@ -1,10 +1,8 @@
 ---
-title: 'Output Formats'
+title: 'Output formats'
 description: 'Understanding the different output formats supported by PandaAI'
 ---
 
-# Output Formats
-
 PandaAI supports multiple output formats for responses, each designed to handle different types of data and analysis results effectively. This document outlines the available output formats and their use cases.
 
 ## Available Output Formats

diff --git a/docs/v3/overview-nl.mdx b/docs/v3/overview-nl.mdx
@@ -8,6 +8,7 @@ description: 'Understanding the AI and natural language processing capabilities
 The Natural Language Layer uses generative AI to transform natural language queries into production-ready code generated by LLMs.
 When you use the `.chat` method on a [semantic dataframe](/v3/dataframes), PandaAI passes to the LLM the question, the table headers, and 5-10 rows of the Dataframe.
 It then instructs the LLM to generate the most relevant code, whether Python or SQL. The code is then executed locally.
+There are different output formats supported by PandaAI, which can be found [here](/v3/output-formats).
 
 The NL Layer is also one of the core components of our [Data Platform](/v3/ai-dashboards), which allows you to turn raw data into collaborative AI dashboards with in-built conversational agents with a single line of code.
 ```python

diff --git a/docs/v3/permission-management.mdx b/docs/v3/permission-management.mdx
@@ -10,34 +10,18 @@ You can choose between four levels of access:
 - Password-protected: for controlled sharing
 - Organization: for team collaboration
 
+![Permission Management](../assets/permissions.png)
+
 Each access level determines who can view and interact with your dataframes, and who consumes query quota when asking questions to the AI agent.
 
 ## Private Dataframes
 Private dataframes are accessible only by their owner. When asking questions to the agent, the owner consumes their own query quota.
 
-```python
-import pandasai as pai
-
-df = pai.load("sales_data.csv")
-df.push(access="private")
-```
-
 ## Public Dataframes
 Public dataframes are accessible by anyone with a PandaAI account. They are indexed on the web for discovery. When users ask questions, they consume their own query quota.
 
-```python
-df.push(access="public")
-```
-
 ## Password-Protected Dataframes
 Password-protected dataframes are accessible only by users with the correct password. When users ask questions, the dataframe owner consumes their query quota.
 
-```python
-df.push(
-    access="password_protected",
-    password="secure_password"
-)
-```
-
 ## Organization Dataframes
 Organization dataframes are accessible by team members based on their permissions. Members can have read-only or write access. Permissions are handled in-platform by the organization owner and admins.
diff --git a/docs/v3/share-dataframes.mdx b/docs/v3/share-dataframes.mdx
@@ -3,22 +3,27 @@ title: 'Share Dataframes'
 description: 'Learn how to push and pull dataframes to/from the PandaAI Data Platform'
 ---
 
+## Pushing Dataframes
 Once you have turned raw data into dataframes using the [semantic layer](/v3/semantic-layer), you can push them to our data platform with one line of code.
-In a similar way, you can pull dataframes your team-mates have pushed to the platform.
 
-## Pushing Dataframes
 
 ```python
 import pandasai as pai
 
-df_customers = pai.load("company/customers")
+df_customers = pai.load("company/heart-data")
 
 df.push()
 ```
+When you push a dataframe to the platform, business users and team mates can chat with your data using natural language.
+![PandaAI](../assets/demo.gif) 
 
 ## Pulling Dataframes
 
+You can pull dataframes your team-mates have pushed to the platform by combining the load and pull methods.
+
+
 ```python
 
-df_customers = pai.pull("company/customers")
+df_customers = pai.load("company/heart-data")
+df_customers = pai.pull()
 ```