doc: Fix headings (#706)

Only one H1 heading with the title is allowed.  The rest must be H2 and
deeper, so adjust them accordingly.

Signed-off-by: David B. Kinder <david.b.kinder@intel.com>

comps/embeddings/predictionguard/README.md

@@ -6,9 +6,9 @@ This embedding microservice is designed to efficiently convert text into vectori
 
 **Note** - The BridgeTower model implemented in Prediction Guard can actually embed text, images, or text + images (jointly). For now this service only embeds text, but a follow on contribution will enable the multimodal functionality.
 
-# 🚀 Start Microservice with Docker
+## 🚀 Start Microservice with Docker
 
-## Setup Environment Variables
+### Setup Environment Variables
 
 Setup the following environment variables first
 
@@ -16,20 +16,20 @@ Setup the following environment variables first
 export PREDICTIONGUARD_API_KEY=${your_predictionguard_api_key}
 ```
 
-## Build Docker Images
+### Build Docker Images
 
 ```bash
 cd ../../..
 docker build -t opea/embedding-predictionguard:latest -f comps/embeddings/predictionguard/Dockerfile .
 ```
 
-## Start Service
+### Start Service
 
 ```bash
 docker run -d --name="embedding-predictionguard" -p 6000:6000 -e PREDICTIONGUARD_API_KEY=$PREDICTIONGUARD_API_KEY opea/embedding-predictionguard:latest
 ```
 
-# 🚀 Consume Embeddings Service
+## 🚀 Consume Embeddings Service
 
 ```bash
 curl localhost:6000/v1/embeddings \

comps/llms/text-generation/predictionguard/README.md

@@ -1,27 +1,27 @@
-# Introduction
+# Prediction Guard Introduction
 
 [Prediction Guard](https://docs.predictionguard.com) allows you to utilize hosted open access LLMs, LVMs, and embedding functionality with seamlessly integrated safeguards. In addition to providing a scalable access to open models, Prediction Guard allows you to configure factual consistency checks, toxicity filters, PII filters, and prompt injection blocking. Join the [Prediction Guard Discord channel](https://discord.gg/TFHgnhAFKd) and request an API key to get started.
 
-# Get Started
+## Get Started
 
-## Build Docker Image
+### Build Docker Image
 
 ```bash
 cd ../../..
 docker build -t opea/llm-textgen-predictionguard:latest -f comps/llms/text-generation/predictionguard/Dockerfile .
 ```
 
-## Run the Predictionguard Microservice
+### Run the Predictionguard Microservice
 
 ```bash
 docker run -d -p 9000:9000 -e PREDICTIONGUARD_API_KEY=$PREDICTIONGUARD_API_KEY  --name llm-textgen-predictionguard opea/llm-textgen-predictionguard:latest
 ```
 
-# Consume the Prediction Guard Microservice
+## Consume the Prediction Guard Microservice
 
 See the [Prediction Guard docs](https://docs.predictionguard.com/) for available model options.
 
-## Without streaming
+### Without streaming
 
 ```bash
 curl -X POST http://localhost:9000/v1/chat/completions \
@@ -37,7 +37,7 @@ curl -X POST http://localhost:9000/v1/chat/completions \
     }'
 ```
 
-## With streaming
+### With streaming
 
 ```bash
 curl -N -X POST http://localhost:9000/v1/chat/completions \

comps/lvms/predictionguard/README.md

@@ -4,23 +4,23 @@
 
 Visual Question and Answering is one of the multimodal tasks empowered by LVMs (Large Visual Models). This microservice supports visual Q&A by using a LLaVA model available via the Prediction Guard API. It accepts two inputs: a prompt and an image. It outputs the answer to the prompt about the image.
 
-# 🚀1. Start Microservice with Python
+## 🚀1. Start Microservice with Python
 
-## 1.1 Install Requirements
+### 1.1 Install Requirements
 
 ```bash
 pip install -r requirements.txt
 ```
 
-## 1.2 Start LVM Service
+### 1.2 Start LVM Service
 
 ```bash
 python lvm.py
 ```
 
-# 🚀2. Start Microservice with Docker (Option 2)
+## 🚀2. Start Microservice with Docker (Option 2)
 
-## 2.1 Setup Environment Variables
+### 2.1 Setup Environment Variables
 
 Setup the following environment variables first
 
@@ -28,20 +28,20 @@ Setup the following environment variables first
 export PREDICTIONGUARD_API_KEY=${your_predictionguard_api_key}
 ```
 
-## 2.1 Build Docker Images
+### 2.1 Build Docker Images
 
 ```bash
 cd ../../..
 docker build -t opea/lvm-predictionguard:latest -f comps/lvms/predictionguard/Dockerfile .
 ```
 
-## 2.2 Start Service
+### 2.2 Start Service
 
 ```bash
 docker run -d --name="lvm-predictionguard" -p 9399:9399 -e PREDICTIONGUARD_API_KEY=$PREDICTIONGUARD_API_KEY opea/lvm-predictionguard:latest
 ```
 
-# 🚀3. Consume LVM Service
+## 🚀3. Consume LVM Service
 
 ```bash
 curl -X POST http://localhost:9399/v1/lvm \