Refactor model examples

docs/GEMMA3.md

@@ -12,7 +12,7 @@ The Python and HTTP APIs support sending images as:
 The Rust API takes an image from the [image](https://docs.rs/image/latest/image/index.html) crate.
 
 ## HTTP server
-You can find this example [here](../examples/server/gemma3.py).
+You can find this example [here](../examples/server/vision_chat.py).
 
 We support an OpenAI compatible HTTP API for vision models. This example demonstrates sending a chat completion request with an image.
 
@@ -97,7 +97,7 @@ print(resp)
 ---
 
 ## Rust
-You can find this example [here](../mistralrs/examples/gemma3/main.rs).
+You can find this example [here](../mistralrs/examples/vision_chat/main.rs).
 
 This is a minimal example of running the Gemma 3 model with a dummy image.
 
@@ -142,7 +142,7 @@ async fn main() -> Result<()> {
 ```
 
 ## Python
-You can find this example [here](../examples/python/gemma3.py).
+You can find this example [here](../examples/python/vision_chat.py).
 
 This example demonstrates loading and sending a chat completion request with an image.
 

docs/IDEFICS2.md

@@ -137,7 +137,7 @@ async fn main() -> Result<()> {
 ```
 
 ## Python
-You can find this example [here](../examples/python/phi3v.py).
+You can find this example [here](../examples/python/vision_chat.py).
 
 This example demonstrates loading and sending a chat completion request with an image.
 

docs/LLAMA4.md

@@ -24,7 +24,7 @@ The Python and HTTP APIs support sending images as:
 The Rust API takes an image from the [image](https://docs.rs/image/latest/image/index.html) crate.
 
 ## HTTP server
-You can find this example [here](../examples/server/llama4.py).
+You can find this example [here](../examples/server/vision_chat.py).
 
 We support an OpenAI compatible HTTP API for vision models. This example demonstrates sending a chat completion request with an image.
 
@@ -116,7 +116,7 @@ print(resp)
 ---
 
 ## Rust
-You can find this example [here](../mistralrs/examples/llama4/main.rs).
+You can find this example [here](../mistralrs/examples/vision_chat/main.rs).
 
 This is a minimal example of running the Llama 4 model with a dummy image.
 
@@ -162,7 +162,7 @@ async fn main() -> Result<()> {
 ```
 
 ## Python
-You can find this example [here](../examples/python/llama4.py).
+You can find this example [here](../examples/python/vision_chat.py).
 
 This example demonstrates loading and sending a chat completion request with an image.
 

docs/LLaVA.md

@@ -24,7 +24,7 @@ The Rust API takes an image from the [image](https://docs.rs/image/latest/image/
 > It should be added to messages manually, and is of the format `<image>`.
 
 ## HTTP server
-You can find this example [here](../examples/server/llava_next.py).
+You can find this example [here](../examples/server/vision_chat.py).
 
 We support an OpenAI compatible HTTP API for vision models. This example demonstrates sending a chat completion request with an image.
 
@@ -101,7 +101,7 @@ print(resp)
 ---
 
 ## Rust
-You can find this example [here](../mistralrs/examples/llava_next/main.rs).
+You can find this example [here](../mistralrs/examples/vision_chat/main.rs).
 
 This is a minimal example of running the LLaVA and LLaVANext model with a dummy image.
 
@@ -146,7 +146,7 @@ async fn main() -> Result<()> {
 ```
 
 ## Python
-You can find this example [here](../examples/python/llava_next.py).
+You can find this example [here](../examples/python/vision_chat.py).
 
 This example demonstrates loading and sending a chat completion request with an image.
 

docs/MISTRAL3.md

@@ -22,7 +22,7 @@ tool calling with Mistral Small 3.1, and you can use it by specifying the `jinja
 
 
 ## HTTP server
-You can find this example [here](../examples/server/mistral3.py).
+You can find this example [here](../examples/server/vision_chat.py).
 
 We support an OpenAI compatible HTTP API for vision models. This example demonstrates sending a chat completion request with an image.
 
@@ -107,7 +107,7 @@ print(resp)
 ---
 
 ## Rust
-You can find this example [here](../mistralrs/examples/mistral3/main.rs).
+You can find this example [here](../mistralrs/examples/vision_chat/main.rs).
 
 This is a minimal example of running the Mistral 3 model with a dummy image.
 
@@ -152,7 +152,7 @@ async fn main() -> Result<()> {
 ```
 
 ## Python
-You can find this example [here](../examples/python/mistral3.py).
+You can find this example [here](../examples/python/vision_chat.py).
 
 This example demonstrates loading and sending a chat completion request with an image.
 

docs/PHI3V.md

@@ -19,7 +19,7 @@ The Rust API takes an image from the [image](https://docs.rs/image/latest/image/
 > They should be added to messages manually, and are of the format `<|image_{N}|>` where N starts from 1.
 
 ## HTTP server
-You can find this example [here](../examples/server/phi3v.py).
+You can find this example [here](../examples/server/vision_chat.py).
 
 We support an OpenAI compatible HTTP API for vision models. This example demonstrates sending a chat completion request with an image.
 
@@ -96,7 +96,7 @@ print(resp)
 ---
 
 ## Rust
-You can find this example [here](../mistralrs/examples/phi3v/main.rs).
+You can find this example [here](../mistralrs/examples/vision_chat/main.rs).
 
 This is a minimal example of running the Phi 3 Vision model with a dummy image.
 
@@ -140,7 +140,7 @@ async fn main() -> Result<()> {
 ```
 
 ## Python
-You can find this example [here](../examples/python/phi3v.py).
+You can find this example [here](../examples/python/vision_chat.py).
 
 This example demonstrates loading and sending a chat completion request with an image.
 

docs/PHI4MM.md

@@ -19,7 +19,7 @@ The Rust API takes an image from the [image](https://docs.rs/image/latest/image/
 > They should be added to messages manually, and are of the format `<|image_{N}|>` where N starts from 1.
 
 ## HTTP server
-You can find this example [here](../examples/server/phi3v.py).
+You can find this example [here](../examples/server/vision_chat.py).
 
 We support an OpenAI compatible HTTP API for vision models. This example demonstrates sending a chat completion request with an image.
 
@@ -94,7 +94,7 @@ print(resp)
 ---
 
 ## Rust
-You can find this example [here](../mistralrs/examples/phi3v/main.rs).
+You can find this example [here](../mistralrs/examples/vision_chat/main.rs).
 
 This is a minimal example of running the Phi 4 Multimodal model with a dummy image.
 
@@ -139,7 +139,7 @@ async fn main() -> Result<()> {
 ```
 
 ## Python
-You can find this example [here](../examples/python/phi3v.py).
+You can find this example [here](../examples/python/vision_chat.py).
 
 This example demonstrates loading and sending a chat completion request with an image.
 

docs/QWEN2VL.md

@@ -58,7 +58,7 @@ camellias are also known for their resilience and ability to thrive in a variety
 ```
 
 ## HTTP server
-You can find this example [here](../examples/server/qwen2vl.py).
+You can find this example [here](../examples/server/vision_chat.py).
 
 We support an OpenAI compatible HTTP API for vision models. This example demonstrates sending a chat completion request with an image.
 
@@ -137,7 +137,7 @@ print(resp)
 ---
 
 ## Rust
-You can find this example [here](../mistralrs/examples/qwen2vl/main.rs).
+You can find this example [here](../mistralrs/examples/vision_chat/main.rs).
 
 ```rust
 use anyhow::Result;
@@ -184,7 +184,7 @@ async fn main() -> Result<()> {
 ---
 
 ## Python
-You can find this example [here](../examples/python/qwen2vl.py).
+You can find this example [here](../examples/python/vision_chat.py).
 
 This example demonstrates loading and sending a chat completion request with an image.
 

docs/VISION_MODELS.md

@@ -13,4 +13,4 @@ Please see docs for the following model types:
 - Phi 4 Multimodal: [PHI4MM.md](PHI4MM.md)
 
 > Note for the Python and HTTP APIs:
-> We follow the OpenAI specification for structuring the image messages and allow both base64 encoded images as well as a URL/path to the image. There are many examples of this, see [this Python example](../examples/python/phi3v.py).
+> We follow the OpenAI specification for structuring the image messages and allow both base64 encoded images as well as a URL/path to the image. There are many examples of this, see [this Python example](../examples/python/vision_chat.py).

docs/VLLAMA.md

@@ -65,7 +65,7 @@ The image appears to be of Mount Washington, which is the highest peak in the No
 ```
 
 ## HTTP server
-You can find this example [here](../examples/server/llama_vision.py).
+You can find this example [here](../examples/server/vision_chat.py).
 
 We support an OpenAI compatible HTTP API for vision models. This example demonstrates sending a chat completion request with an image.
 
@@ -152,7 +152,7 @@ print(resp)
 ---
 
 ## Rust
-You can find this example [here](../mistralrs/examples/llama_vision/main.rs).
+You can find this example [here](../mistralrs/examples/vision_chat/main.rs).
 
 ```rust
 use anyhow::Result;
@@ -198,7 +198,7 @@ async fn main() -> Result<()> {
 ---
 
 ## Python
-You can find this example [here](../examples/python/llama_vision.py).
+You can find this example [here](../examples/python/vision_chat.py).
 
 This example demonstrates loading and sending a chat completion request with an image.