docs: update v3 documentation, readme and examples

README.md

@@ -25,12 +25,16 @@ 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")
+
 df = pai.read_csv("./filepath.csv")
-df.push()
 
-df.save(path="your-organization/dataset-name",
+df = pai.create(path="your-organization/dataset-name",
+    df=df,
     name="dataset-name",
     description="dataset-description")
+
+df.push()
 ```
 Your team can now access and query this data using natural language through the platform.
 

docs/v3/data-ingestion.mdx

@@ -24,8 +24,10 @@ import pandasai as pai
 df = pai.read_csv("data.csv")
 
 # Use the semantic layer on CSV
-df.save(
+df = pai.create(
+    path="company/sales-data",
     name="sales_data",
+    df = df,
     description="Sales data from our retail stores",
     columns={
         "transaction_id": {"type": "string", "description": "Unique identifier for each sale"},

docs/v3/getting-started.mdx

@@ -19,7 +19,7 @@ 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://app.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 [app.pandabi.ai](https://app.pandabi.ai), which allows you to both use the data platform and get BambooLLM credits.
 
 ```python
 import pandasai as pai
@@ -49,7 +49,7 @@ Depending on your question, it can return different objects:
 
 Find it more about output data formats [here](/v3/output-formats)
 
-### Save and load dataframes
+### Create and load dataframes
 
 To work faster with your data, you can save dataframes.
 This allows you to avoid reading the data every time.
@@ -60,20 +60,18 @@ import pandasai as pai
 # read csv - replace "filepath" with your file path
 df = pai.read_csv("filepath")
 
-df.save(path="organization/dataset-name",
+df = pai.create(path="organization/dataset-name",
     name="dataset-name",
+    df = df,
     description="describe your dataset")
 ```
 
-The saved dataframe can then be loaded using the `load` method.
+The created dataframe can then be loaded using the `load` method.
 
 ```python
 import pandasai as pai
 
-# read csv - replace "filepath" with your file path
-df = pai.read_csv("filepath")
-
-df.load("organization/dataset-name")
+df = pai.load("organization/dataset-name")
 ```
 
 ## Share with your team

docs/v3/semantic-layer.mdx

@@ -14,18 +14,19 @@ The semantic layer allows you to turn raw data into [dataframes](/v3/dataframes)
 
 There are two ways to use the semantic layer:
 
-### For CSV files: using the save method
+### For CSV files: using the create method
 
-The simplest way to create a semantic layer for CSV files is using the `save` method:
+The simplest way to create a semantic layer for CSV files is using the `create` method:
 
 ```python
 import pandasai as pai
 
 df = pai.read_csv("data.csv")
 
-df.save(
+df = pai.create(
     path="company/sales-data",         # Format: "organization/dataset"
     name="sales-data",                 # Human-readable name
+    df = df,                           # Input Dataframe
     description="Sales data from our retail stores",  # Optional description
     columns=[
         {
@@ -44,10 +45,12 @@ df.save(
 
 #### name
 
-The name field identifies your dataset in the save method.
+The name field identifies your dataset in the create method.
 
 ```python
-df.save(
+df = pai.read_csv("data.csv")
+
+pai.create(
     path="company/sales-data",
     name="sales-data",  # Unique, descriptive name
     ...
@@ -59,13 +62,55 @@ df.save(
 - Unique within your project
 - Examples: "sales-data", "customer-profiles"
 
+#### path
+
+The path uniquely identifies your dataset in the PandaAI ecosystem using the format "organization/dataset".
+
+```python
+df = pai.read_csv("data.csv")
+
+pai.create(
+    path="acme-corp/sales-data",  # Format: "organization/dataset"
+    ...
+)
+```
+
+**Type**: `str`
+- Must follow the format: "organization-identifier/dataset-identifier"
+- Organization identifier should be unique to your organization
+- Dataset identifier should be unique within your organization
+- Can be used both locally and with the PandaAI Data Platform
+- Examples: "acme-corp/sales-data", "my-org/customer-profiles"
+
+#### df
+
+The input dataframe that contains your data, typically created using `pai.read_csv()`.
+
+```python
+df = pai.read_csv("data.csv")  # Create the input dataframe
+
+pai.create(
+    path="acme-corp/sales-data",
+    df=df,  # Pass your dataframe here
+    ...
+)
+```
+
+**Type**: `DataFrame`
+- Must be a pandas DataFrame created with `pai.read_csv()`
+- Contains the raw data you want to enhance with semantic information
+- Required parameter for creating a semantic layer
+
 #### description
 A clear text description that helps others understand the dataset's contents and purpose.
 
 ```python
-df.save(
+df = pai.read_csv("data.csv")
+
+pai.create(
     path="company/sales-data",
     name="sales-data",
+    df = df,
     description="Daily sales transactions from all retail stores, including transaction IDs, dates, and amounts",
     ...
 )
@@ -77,14 +122,19 @@ df.save(
 - Any relevant context about data collection or usage
 - Optional but recommended for better data understanding
 
-
 #### columns
 Define the structure and metadata of your dataset's columns to help PandaAI understand your data better.
 
+**Note**: If the `columns` parameter is not provided, all columns from the input dataframe will be included in the semantic layer. 
+When specified, only the declared columns will be included, allowing you to select specific columns for your semantic layer.
+
 ```python
-df.save(
+df = pai.read_csv("data.csv")
+
+pai.create(
     path="company/sales-data",
     name="sales-data",
+    df = df,
     description="Daily sales transactions from all retail stores",
     columns=[
         {

examples/data_platform_guide.ipynb

@@ -60,9 +60,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## 1. Save Dataframes\n",
+    "## 1. Create Dataframes\n",
     "\n",
-    "The `save()` method allows you to save your dataframes with metadata and column descriptions. This enriches your data with semantic meaning."
+    "The `create()` method allows you to save your dataframes with metadata and column descriptions. This enriches your data with semantic meaning."
    ]
   },
   {
@@ -71,10 +71,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Save heart disease dataset with semantic information\n",
-    "heart_df.save(\n",
+    "# Create heart disease dataset with semantic information\n",
+    "heart = pai.create(\n",
     "    path=\"my-team/heart\",\n",
     "    name=\"Heart Disease Data\",\n",
+    "    df = heart_df,\n",
     "    description=\"Dataset containing heart disease patient information\",\n",
     "    columns=[\n",
     "        {\"name\": \"Age\", \"type\": \"integer\", \"description\": \"Age of the patient in years\"},\n",
@@ -90,9 +91,10 @@
     ")\n",
     "\n",
     "# Save loans dataset\n",
-    "loans_df.save(\n",
+    "loans = pai.create(\n",
     "    path=\"my-team/loans\",\n",
     "    name=\"Loan Payments Data\",\n",
+    "    df = loans_df,\n",
     "    description=\"Dataset containing loan payment information\",\n",
     "    columns=[\n",
     "        {\"name\": \"loan_id\", \"type\": \"integer\", \"description\": \"Unique identifier for each loan\"},\n",
@@ -120,8 +122,8 @@
    "outputs": [],
    "source": [
     "# Push datasets to platform\n",
-    "heart_df.push('my-team-slug/heart')\n",
-    "loans_df.push('my-team-slug/loans')"
+    "heart.push('my-team-slug/heart')\n",
+    "loans.push('my-team-slug/loans')"
    ]
   },
   {
@@ -160,7 +162,7 @@
    "outputs": [],
    "source": [
     "# Pull latest versions\n",
-    "latest_heart = pai.pull('my-team--slug/heart')\n",
+    "latest_heart = pai.pull('my-team-slug/heart')\n",
     "latest_loans = pai.pull('my-team-slug/loans')"
    ]
   },

examples/quickstart.ipynb

@@ -9,6 +9,11 @@
     "This notebook demonstrates how to get started with PandaAI and how to use it to analyze data through natural language."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": []
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -52,11 +57,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Save DataFrame\n",
+    "## Chat with Your Data\n",
     "\n",
-    "To use PandaAI in combination with our Data Platform, you need to save your dataframes.  \n",
-    "The path must be in format 'organization/dataset'. \n",
-    "You can create organizations directly within the data platform ([pandabi.ai](https://pandabi.ai))"
+    "You can ask questions about your data using natural language"
    ]
   },
   {
@@ -65,18 +68,19 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df.save(path=\"your-organization/heart\",\n",
-    "    name=\"Heart\",\n",
-    "    description=\"Heart Disease Dataset\")"
+    "response = df.chat(\"What is the correlation between age and cholesterol?\")\n",
+    "print(response)"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Chat with Your Data\n",
+    "## Create Dataset\n",
     "\n",
-    "Now you can ask questions about your data using natural language"
+    "To use PandaAI in combination with our Data Platform, you need to save your dataframes.  \n",
+    "The path must be in format 'organization/dataset'. \n",
+    "You can create organizations directly within the data platform ([pandabi.ai](https://pandabi.ai))"
    ]
   },
   {
@@ -85,15 +89,17 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "response = df.chat(\"What is the correlation between age and cholesterol?\")\n",
-    "print(response)"
+    "dataset = pai.create(path=\"your-organization/heart\",\n",
+    "    name=\"Heart\",\n",
+    "    df = df,\n",
+    "    description=\"Heart Disease Dataset\")"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Turn the dataframe into a chatbot\n",
+    "## Turn the dataframe into a shareble link with a built-in chatbot\n",
     "\n",
     "Push the dataframe to the data platform for collaboration.\n",
     "This will turn the dataframe into a chatbot and allow non technical users to interact with your data using natural language."
@@ -105,8 +111,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "df = pai.load(\"your-organization/heart\")\n",
-    "df.push()"
+    "dataset = pai.load(\"your-organization/heart\")\n",
+    "\n",
+    "dataset.push()"
    ]
   }
  ],

examples/semantic_layer_csv.ipynb

@@ -62,6 +62,7 @@
     "Requirements for the semantic layer:\n",
     "- `path`: Must be in format 'organization/dataset'\n",
     "- `name`: A descriptive name for the dataset\n",
+    "-  `df`: A dataframe\n",
     "- `description`: Brief overview of the dataset\n",
     "- `columns`: List of dictionaries with format:\n",
     "  ```python\n",
@@ -82,6 +83,7 @@
     "df.save(path=\"organization/heart\",\n",
     "    name=\"Heart\",\n",
     "    description=\"Heart Disease Dataset\",\n",
+    "    df = df,\n",
     "    columns=[\n",
     "        {\n",
     "            \"name\": \"Age\",\n",