add missing config

Author: ArslanSaleem

docs/v3/migration-guide.mdx

@@ -4,7 +4,10 @@ description: "Step-by-step guide to migrate from PandasAI v2 to v3"
 ---
 
 <Note title="Migration Notice">
-  PandasAI 3.0 introduces significant architectural changes. This guide covers breaking changes and migration steps. See [Backwards Compatibility](/v3/migration-backwards-compatibility) for v2 classes that still work.
+  PandasAI 3.0 introduces significant architectural changes. This guide covers
+  breaking changes and migration steps. See [Backwards
+  Compatibility](/v3/migration-backwards-compatibility) for v2 classes that
+  still work.
 </Note>
 
 ## Breaking Changes
@@ -13,9 +16,10 @@ description: "Step-by-step guide to migrate from PandasAI v2 to v3"
 
 Configuration is now global using `pai.config.set()` instead of per-dataframe. Several options have been removed:
 
-**Removed:** `save_charts`, `enable_cache`, `security`, `custom_whitelisted_dependencies`, `save_charts_path`
+**Removed:** `save_charts`, `enable_cache`, `security`, `custom_whitelisted_dependencies`, `save_charts_path`, `custom_head`
 
 **v2:**
+
 ```python
 from pandasai import SmartDataframe
 
@@ -29,6 +33,7 @@ df = SmartDataframe(data, config=config)
 ```
 
 **v3:**
+
 ```python
 import pandasai as pai
 
@@ -42,6 +47,7 @@ df = pai.DataFrame(data)
 ```
 
 **Key Changes:**
+
 - Global configuration applies to all dataframes
 - Charts returned as `ChartResponse` objects for manual handling
 - Security handled through sandbox environment
@@ -54,6 +60,7 @@ df = pai.DataFrame(data)
 LLMs are now extension-based. Install `pandasai-litellm` separately for unified access to 100+ models.
 
 **v2:**
+
 ```python
 from pandasai.llm import OpenAI
 from pandasai import SmartDataframe
@@ -63,6 +70,7 @@ df = SmartDataframe(data, config={"llm": llm})
 ```
 
 **v3:**
+
 ```bash
 pip install pandasai-litellm
 ```
@@ -77,6 +85,7 @@ df = pai.DataFrame(data)
 ```
 
 **Key Changes:**
+
 - LLMs are now extension-based, not built-in
 - Install `pandasai-litellm` for unified LLM interface
 - LiteLLM supports 100+ models (GPT-4, Claude, Gemini, etc.)
@@ -90,6 +99,7 @@ df = pai.DataFrame(data)
 Connectors are now separate extensions. Install only what you need. Cloud connectors require [enterprise license](/v3/enterprise-features).
 
 **v2:**
+
 ```python
 from pandasai.connectors import PostgreSQLConnector
 from pandasai import SmartDataframe
@@ -103,6 +113,7 @@ df = SmartDataframe(connector)
 ```
 
 **v3:**
+
 ```bash
 pip install pandasai-sql[postgres]
 ```
@@ -127,6 +138,7 @@ df = pai.create(
 ```
 
 **Key Changes:**
+
 - Install specific extensions: `pandasai-sql[postgres]`, `pandasai-sql[mysql]`
 - Use `pai.create()` with semantic layer
 - Environment variables supported: `${DB_USER}`
@@ -136,12 +148,14 @@ df = pai.create(
 ### Skills
 
 <Note title="Enterprise Feature">
-  Skills require a valid enterprise license for production use. See [Enterprise Features](/v3/enterprise-features) for more details.
+  Skills require a valid enterprise license for production use. See [Enterprise
+  Features](/v3/enterprise-features) for more details.
 </Note>
 
 Skills use `@pai.skill` decorator and are automatically registered globally.
 
 **v2:**
+
 ```python
 from pandasai.skills import skill
 from pandasai import Agent
@@ -158,6 +172,7 @@ agent.add_skills(calculate_bonus)
 ```
 
 **v3:**
+
 ```python
 import pandasai as pai
 from pandasai import Agent
@@ -174,6 +189,7 @@ agent = Agent([df])
 ```
 
 **Key Changes:**
+
 - Use `@pai.skill` instead of `@skill`
 - Automatic global registration
 - No need for `agent.add_skills()`
@@ -184,12 +200,14 @@ agent = Agent([df])
 ### Training
 
 <Note title="Enterprise Feature">
-  Training with vector stores requires a valid enterprise license for production use. See [Enterprise Features](/v3/enterprise-features) for more details.
+  Training with vector stores requires a valid enterprise license for production
+  use. See [Enterprise Features](/v3/enterprise-features) for more details.
 </Note>
 
 Training is now available through local vector stores (ChromaDB, Qdrant, Pinecone, LanceDB) for few-shot learning. The `train()` method is still available but requires a vector store.
 
 **v2:**
+
 ```python
 from pandasai import Agent
 
@@ -198,6 +216,7 @@ agent.train(queries=["query"], codes=["code"])
 ```
 
 **v3:**
+
 ```python
 from pandasai import Agent
 from pandasai.ee.vectorstores import ChromaDB
@@ -211,6 +230,7 @@ agent.train(queries=["query"], codes=["code"])
 ```
 
 **Key Changes:**
+
 - Training requires a vector store (ChromaDB, Qdrant, Pinecone, LanceDB)
 - Vector stores enable few-shot learning
 - Better scalability and performance
@@ -265,9 +285,10 @@ pai.config.set({
 ### Step 4: Migrate DataFrames (optional)
 
 Check the [Backwards Compatibility](/v3/migration-backwards-compatibility) section for details on the difference between SmartDataframe, SmartDatalakes, and the new Semantic DataFrames (pai dataframes).
-In this way you can decide if migrating or not. 
+In this way you can decide if migrating or not.
 
 **Option A: Keep SmartDataframe (backward compatible)**
+
 ```python
 from pandasai import SmartDataframe
 
@@ -276,6 +297,7 @@ response = df.chat("Your question")
 ```
 
 **Option B: Use pai.DataFrame (recommended)**
+
 ```python
 import pandasai as pai
 
@@ -297,6 +319,7 @@ response = df.chat("Your question")
 ```
 
 **Multiple DataFrames:**
+
 ```python
 # v2 style (still works)
 from pandasai import SmartDatalake
@@ -338,7 +361,8 @@ df = pai.create(
 ### Step 6: Update Skills (if applicable)
 
 <Note title="Enterprise Feature">
-  Skills require a valid enterprise license for production use. See [Enterprise Features](/v3/enterprise-features) for more details.
+  Skills require a valid enterprise license for production use. See [Enterprise
+  Features](/v3/enterprise-features) for more details.
 </Note>
 
 ```python
@@ -362,7 +386,7 @@ def calculate_metric(value: float) -> float:
 ### Step 7: Remove Deprecated Configuration
 
 ```python
-# Remove: save_charts, enable_cache, security, 
+# Remove: save_charts, enable_cache, security,
 # custom_whitelisted_dependencies, save_charts_path
 
 # v3 (keep only these)
@@ -415,7 +439,7 @@ print(response)
 ---
 
 <Note>
-  **Next Steps:**
-  - Review [Backwards Compatibility](/v3/migration-backwards-compatibility) for v2 classes
-  - Check [Migration Troubleshooting](/v3/migration-troubleshooting) for common issues
+  **Next Steps:** - Review [Backwards
+  Compatibility](/v3/migration-backwards-compatibility) for v2 classes - Check
+  [Migration Troubleshooting](/v3/migration-troubleshooting) for common issues
 </Note>