Tutorial polish

README.md

@@ -30,7 +30,7 @@ Small models with the right adapters consistently outperform much larger general
 </p>
 
 <p align="center"><em>aLoRA completes 20 of 32 RAG queries while standard LoRA is still waiting — same model, same hardware, different adapter technology.</em><br>
-<a href="https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/05_alora_vs_lora_race.ipynb">Reproduce it yourself on Colab →</a></p>
+<a href="https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/alora_vs_lora_race.ipynb">Reproduce it yourself on Colab →</a></p>
 
 ## Quick Start
 
@@ -114,9 +114,9 @@ New here? Start with a 5-minute notebook and work your way up:
 
 | Notebook | What you'll build | Time | |
 |---|---|---|---|
-| [Hello Mellea](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/01_hello_mellea.ipynb) | Call adapters through a clean Python API | 5 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/01_hello_mellea.ipynb) |
-| [RAG Pipeline](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/03_01_govt_rag_pipeline_simple.ipynb) | Query rewrite + answerability + citations in one model | 30 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/03_01_govt_rag_pipeline_simple.ipynb) |
-| [Compose Your Own](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/04_compose_granite_switch.ipynb) | Build a custom checkpoint from adapter libraries | 15 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/04_compose_granite_switch.ipynb) |
+| [Hello Mellea](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/hello_mellea.ipynb) | Call adapters through a clean Python API | 5 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/hello_mellea.ipynb) |
+| [RAG Pipeline](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/rag_full_pipeline.ipynb) | Query rewrite + answerability + citations in one model | 30 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/rag_full_pipeline.ipynb) |
+| [Compose Your Own](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/compose_granite_switch.ipynb) | Build a custom checkpoint from adapter libraries | 15 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/compose_granite_switch.ipynb) |
 
 All notebooks run on Colab. See [tutorials/README.md](tutorials/README.md) for the full list and guided learning paths.
 

tutorials/README.md

@@ -1,28 +1,28 @@
 # Granite Switch Tutorials
 
-Granite Switch facilitates a modular architecture by consolidating multiple LoRA adapters into a single, unified checkpoint. The following tutorials explore the underlying mechanics and usability, detailing adapter invocation, multi-step pipelines with guardrails, and checkpoint composition.
+Granite Switch facilitates a modular architecture by consolidating multiple LoRA adapters into a single, unified checkpoint. The following tutorials explore the underlying mechanics and usability, detailing adapter function invocation, multi-step pipelines with guardrails, and checkpoint composition.
 
 ## Notebooks
 
-Step-by-step walkthroughs covering adapter invocation, pipeline construction, and model composition.
+Step-by-step walkthroughs covering adapter function invocation, pipeline construction, and model composition.
 
 | Notebook | Topics | Duration | Colab |
 |----------|--------|----------|-------|
-| [hello_mellea.ipynb](notebooks/hello_mellea.ipynb) | Mellea adapters intro with vLLM | 5 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/hello_mellea.ipynb) |
+| [hello_mellea.ipynb](notebooks/hello_mellea.ipynb) | Mellea adapter functions intro with vLLM | 5 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/hello_mellea.ipynb) |
 | [rag_101.ipynb](notebooks/rag_101.ipynb) | RAG 101: build a vector corpus and run a basic answerability check | 15 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/rag_101.ipynb) |
-| [rag_full_pipeline.ipynb](notebooks/rag_full_pipeline.ipynb) | Full RAG pipeline with guardian checks (harm + scope) | 30 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/rag_full_pipeline.ipynb) |
+| [rag_full_flow.ipynb](notebooks/rag_full_flow.ipynb) | Full RAG pipeline with guardian checks (harm + scope) | 30 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/rag_full_flow.ipynb) |
 | [compose_granite_switch.ipynb](notebooks/compose_granite_switch.ipynb) | Compose a checkpoint from adapter libraries | 15 min |  |
 | [alora_vs_lora_race.ipynb](notebooks/alora_vs_lora_race.ipynb) | ALORA vs LoRA race: side-by-side throughput comparison on a multi-step RAG pipeline | 20 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/alora_vs_lora_race.ipynb) |
-| [hello_adapter.ipynb](notebooks/hello_adapter.ipynb) | Minimal adapter invocation with HuggingFace | 5 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/hello_adapter.ipynb) |
-| [granite_switch_with_hf.ipynb](notebooks/granite_switch_with_hf.ipynb) | Compose + HuggingFace backend, `adapter_name=` invocation, Core + Guardian adapters in a multi-turn conversation | 10 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/granite_switch_with_hf.ipynb) |
+| [hello_adapter.ipynb](notebooks/hello_adapter.ipynb) | Minimal adapter function invocation with HuggingFace | 5 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/hello_adapter.ipynb) |
+| [granite_switch_with_hf.ipynb](notebooks/granite_switch_with_hf.ipynb) | Compose + HuggingFace backend, `adapter_name=` invocation, Core + Guardian adapter functions in a multi-turn conversation | 10 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/granite_switch_with_hf.ipynb) |
 | [granite_speech_demo.ipynb](notebooks/granite_speech_demo.ipynb) | Real-time voice assistant: Granite Speech STT + Granite Switch LLM + Granite Libraries validation, orchestrated by Mellea over WebRTC | 10 min | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/granite_speech_demo.ipynb) |
 
 ## Guides
 
 | Guide | Description |
 |-------|-------------|
 | [Using Mellea with Granite Switch](guides/mellea_with_granite_switch.md) | Connect Mellea to a Granite Switch model |
-| [Bring Your Own Adapter](guides/bring_your_own_adapter.md) | Train, compose, and use custom adapters |
+| [Bring Your Own Adapter](guides/build_your_own_adapter.md) | Train, compose, and use custom adapters |
 | [Compare Inference Throughput](guides/compare_inference_throughput.md) | Compare LoRA vs aLoRA based models in an inference race setup |
 
 
@@ -48,29 +48,29 @@ support coming soon.
 
 ### Path 2: Real-World Pipelines (Usability)
 
-Best for: Seeing how adapters compose into multi-step applications
+Best for: Seeing how adapter functions compose into multi-step applications
 
 1. [RAG 101](notebooks/rag_101.ipynb) - corpus build + answerability check, the smallest end-to-end RAG demo [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/rag_101.ipynb)
-2. [Full RAG Pipeline with Guardians](notebooks/rag_full_pipeline.ipynb) - rewrite, answerability, citations, harm + scope checks [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/rag_full_pipeline.ipynb)
+2. [Full RAG Pipeline with Guardians](notebooks/rag_full_flow.ipynb) - rewrite, answerability, citations, harm + scope checks [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/rag_full_flow.ipynb)
 
 
 
 
 
 ### Path 3: Bring Your Own Adapter
 
-Best for: Custom adapter development
+Best for: Custom adapter function development
 
-1. [Bring Your Own Adapter Guide](guides/bring_your_own_adapter.md)
-2. [Configure Your Own Adapter Guide](guides/mellea_bring_your_own_adapter.md)
+1. [Bring Your Own Adapter Guide](guides/build_your_own_adapter.md)
+2. [Configure Your Own Adapter Guide](guides/mellea_build_your_own_adapter.md)
 3. [Compose Your Checkpoint](notebooks/compose_granite_switch.ipynb) 
 
 
 ### Path 4: Low-Level Understanding (HuggingFace)
 
 Best for: Understanding how Granite Switch works at the control-token level
 
-HuggingFace inference examples demonstrate how adapters are activated via control tokens, providing insight into the underlying mechanics. For most applications, we recommend running inference with Mellea (Part 2).
+HuggingFace inference examples demonstrate how adapter functions are activated via control tokens, providing insight into the underlying mechanics. For most applications, we recommend running inference with Mellea (Part 2).
 1. [Prerequisites](PREREQUISITES.md#huggingface-backend)
 2. [Hello Adapter](notebooks/hello_adapter.ipynb) — see control tokens in action [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/hello_adapter.ipynb)
 3. [Granite Switch with HuggingFace](notebooks/granite_switch_with_hf.ipynb) — detailed walkthrough [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/generative-computing/granite-switch/blob/main/tutorials/notebooks/granite_switch_with_hf.ipynb)
@@ -83,8 +83,8 @@ Runnable scripts in [`scripts/`](scripts/) for common tasks:
 
 | Script | Description |
 |--------|-------------|
-| [run_adapter_generation_direct.py](scripts/reference/run_adapter_generation_direct.py) | Direct adapter invocation via control tokens |
-| [run_adapter_generation_mellea.py](scripts/reference/run_adapter_generation_mellea.py) | Adapter invocation through Mellea |
+| [run_adapter_generation_direct.py](scripts/reference/run_adapter_generation_direct.py) | Direct adapter function invocation via control tokens |
+| [run_adapter_generation_mellea.py](scripts/reference/run_adapter_generation_mellea.py) | Adapter function invocation through Mellea |
 
 
 ## Adapter Libraries
@@ -93,9 +93,9 @@ Granite Switch checkpoints embed adapters drawn from IBM's granitelib libraries.
 
 | Adapter | Purpose | Where used in tutorials | HF repo |
 |---------|---------|-------------------------|---------|
-| Core | Foundational post-generation adapters: certainty scoring, requirement checking, and response attribution. | [granite_switch_with_hf](notebooks/granite_switch_with_hf.ipynb), [compose_granite_switch](notebooks/compose_granite_switch.ipynb) | [ibm-granite/granitelib-core-r1.0](https://huggingface.co/ibm-granite/granitelib-core-r1.0) |
-| RAG | Retrieval-augmented generation adapters: query rewrite, answerability, hallucination detection, and citation generation. | [hello_mellea](notebooks/hello_mellea.ipynb), [rag_101](notebooks/rag_101.ipynb), [rag_full_pipeline](notebooks/rag_full_pipeline.ipynb), [compose_granite_switch](notebooks/compose_granite_switch.ipynb) | [ibm-granite/granitelib-rag-r1.0](https://huggingface.co/ibm-granite/granitelib-rag-r1.0) |
-| Guardian | Safety and risk detection: harm, social bias, jailbreaking, factuality, and policy compliance checks. | [hello_adapter](notebooks/hello_adapter.ipynb), [hello_mellea](notebooks/hello_mellea.ipynb), [granite_switch_with_hf](notebooks/granite_switch_with_hf.ipynb), [rag_full_pipeline](notebooks/rag_full_pipeline.ipynb), [compose_granite_switch](notebooks/compose_granite_switch.ipynb) | [ibm-granite/granitelib-guardian-r1.0](https://huggingface.co/ibm-granite/granitelib-guardian-r1.0) |
+| Core | Foundational post-generation adapter functions: certainty scoring, requirement checking, and response attribution. | [granite_switch_with_hf](notebooks/granite_switch_with_hf.ipynb), [compose_granite_switch](notebooks/compose_granite_switch.ipynb) | [ibm-granite/granitelib-core-r1.0](https://huggingface.co/ibm-granite/granitelib-core-r1.0) |
+| RAG | Retrieval-augmented generation adapter functions: query rewrite, answerability, hallucination detection, and citation generation. | [hello_mellea](notebooks/hello_mellea.ipynb), [rag_101](notebooks/rag_101.ipynb), [rag_full_flow](notebooks/rag_full_flow.ipynb), [compose_granite_switch](notebooks/compose_granite_switch.ipynb) | [ibm-granite/granitelib-rag-r1.0](https://huggingface.co/ibm-granite/granitelib-rag-r1.0) |
+| Guardian | Safety and risk detection: harm, social bias, jailbreaking, factuality, and policy compliance checks. | [hello_adapter](notebooks/hello_adapter.ipynb), [hello_mellea](notebooks/hello_mellea.ipynb), [granite_switch_with_hf](notebooks/granite_switch_with_hf.ipynb), [rag_full_flow](notebooks/rag_full_flow.ipynb), [compose_granite_switch](notebooks/compose_granite_switch.ipynb) | [ibm-granite/granitelib-guardian-r1.0](https://huggingface.co/ibm-granite/granitelib-guardian-r1.0) |
 
 ## External Resources
 

tutorials/guides/compare_inference_throughput.md

@@ -87,4 +87,4 @@ raced simultaneously.
 
 - **[Hello Adapter](../notebooks/hello_adapter.ipynb)** - minimal embedded-adapter invocation via the HuggingFace backend
 - **[Using Mellea with Granite Switch](mellea_with_granite_switch.md)** - deeper Mellea integration details
-- **[Bring Your Own Adapter](bring_your_own_adapter.md)** - train a custom adapter and compose it in
+- **[Bring Your Own Adapter](build_your_own_adapter.md)** - train a custom adapter and compose it in

tutorials/guides/mellea_bring_your_own_adapter.md → tutorials/guides/mellea_build_your_own_adapter.md

@@ -6,7 +6,7 @@ This guide explains how to configure your own adapter with Mellea to be used by
 
 Together, Mellea + Granite Switch + vLLM provide a production-ready inference stack for adapter-based AI applications that can utilize custom adapters.
 - See [Mellea With Granite Switch](mellea_with_granite_switch.md) for a detailed explanation of how granite-switch and Mellea work together.
-- See [Bring Your Own Adapter](bring_your_own_adapter.md) for info on how to train your own adapter.
+- See [Bring Your Own Adapter](build_your_own_adapter.md) for info on how to train your own adapter.
 - See Mellea's [Lora and aLoRA adapters](https://docs.mellea.ai/advanced/lora-and-alora-adapters) for info on how to train your own custom adapters using Mellea.
 
 ## Prerequisites

tutorials/guides/mellea_with_granite_switch.md

@@ -247,7 +247,7 @@ print(f"Citations: {citations}")
 ## Next Steps
 
 - **[Hello Adapter](../notebooks/hello_adapter.ipynb)** - Minimal embedded-adapter invocation via the HuggingFace backend
-- **[Bring Your Own Adapter](bring_your_own_adapter.md)** - Train a custom adapter and compose it in
+- **[Bring Your Own Adapter](build_your_own_adapter.md)** - Train a custom adapter and compose it in
 - **[Compare Inference Throughput](compare_inference_throughput.md)** - Benchmark ALORA vs LoRA on a 6-step RAG pipeline
 - **[Mellea Repository](https://github.com/generative-computing/mellea)** - Full documentation
 - **[Granite Models](https://huggingface.co/ibm-granite)**

tutorials/notebooks/compose_granite_switch.ipynb

@@ -257,7 +257,7 @@
    "cell_type": "markdown",
    "id": "generate-md",
    "metadata": {},
-   "source": "## 6 * Generate against the composed model\n\nConnect Mellea to the running vLLM server, register the embedded adapters, and call the `rewrite_question` adapter. If it prints a cleaned-up version of the messy query, your composed checkpoint is wired up correctly."
+   "source": "## 6 * Generate against the composed model\n\nConnect Mellea to the running vLLM server, register the embedded adapters, and call the `rewrite_question` adapter function. If it prints a cleaned-up version of the messy query, your composed checkpoint is wired up correctly."
   },
   {
    "cell_type": "code",
@@ -304,4 +304,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}