docs: Mistral docs v2 (#1674)

* add weave.op

* rafactor in shawn style

* add images to folder

* remove table of contents

* highlight weave dec

---------

Co-authored-by: Jason Zhao <[email protected]>

docs/docs/guides/ecosystem/mistral.md

@@ -1,52 +1,68 @@
 ---
 sidebar_position: 1
-hide_table_of_contents: false
+hide_table_of_contents: true
 ---
 
 # MistralAI
 
-Weave automatically tracks and logs LLM calls made via the [MistralAI Python library](https://github.com/mistralai/client-python), after `weave.init()` is called.
+Weave automatically tracks and logs LLM calls made via the [MistralAI Python library](https://github.com/mistralai/client-python).
 
-## Setup
+## Traces
 
-1. Install the MistralAI Python library:
-   ```bash
-   pip install mistralai weave
-   ```
+It’s important to store traces of LLM applications in a central database, both during development and in production. You’ll use these traces for debugging, and as a dataset that will help you improve your application.
 
-2. Initialize Weave in your Python script:
-   ```python
-   import weave
-   weave.init("cheese_recommender")
-   ```
-   :::note
-   We patch the mistral `chat_completion` method for you to keep track of your LLM calls.
-   :::
+Weave will automatically capture traces for [mistralai](https://github.com/mistralai/client-python). You can use the library as usual, start by calling `weave.init()`:
 
-3. Use the MistralAI library as usual:
+```python
+import weave
+weave.init("cheese_recommender")
 
-    ```python
-    import os
-    from mistralai.client import MistralClient
-    from mistralai.models.chat_completion import ChatMessage
+# then use mistralai library as usual
+import os
+from mistralai.client import MistralClient
+from mistralai.models.chat_completion import ChatMessage
 
-    api_key = os.environ["MISTRAL_API_KEY"]
-    model = "mistral-large-latest"
+api_key = os.environ["MISTRAL_API_KEY"]
+model = "mistral-large-latest"
 
-    client = MistralClient(api_key=api_key)
+client = MistralClient(api_key=api_key)
 
-    messages = [
-        ChatMessage(role="user", content="What is the best French cheese?")
-    ]
+messages = [
+    ChatMessage(role="user", content="What is the best French cheese?")
+]
+
+chat_response = client.chat(
+    model=model,
+    messages=messages,
+)
+```
+
+Weave will now track and log all LLM calls made through the MistralAI library. You can view the traces in the Weave web interface.
+
+[![mistral_trace.png](imgs/mistral_trace.png)](https://wandb.ai/capecape/mistralai_project/weave/calls)
+
+## Wrapping with your own ops
+
+Weave ops make results *reproducible* by automatically versioning code as you experiment, and they capture their inputs and outputs. Simply create a function decorated with [`@weave.op()`](https://wandb.github.io/weave/guides/tracking/ops) that calls into [`mistralai.client.MistralClient.chat()`](https://docs.mistral.ai/capabilities/completion/) and Weave will track the inputs and outputs for you. Let's see how we can do this for our cheese recommender:
+
+```python
+# highlight-next-line
+@weave.op()
+def cheese_recommender(region:str, model:str) -> str:
+    "Recommend the best cheese in a given region"
+
+    messages = [ChatMessage(role="user", content=f"What is the best cheese in {region}?")]
 
     chat_response = client.chat(
         model=model,
         messages=messages,
     )
+    return chat_response.choices[0].message.content
 
-    print(chat_response.choices[0].message.content)
-    ```
+cheese_recommender(region="France", model="mistral-large-latest")
+cheese_recommender(region="Spain", model="mistral-large-latest")
+cheese_recommender(region="Netherlands", model="mistral-large-latest")
+```
 
-Weave will now track and log all LLM calls made through the MistralAI library. You can view the logs and insights in the Weave web interface.
+[![mistral_ops.png](imgs/mistral_ops.png)](https://wandb.ai/capecape/mistralai_project/weave/calls)
 
-[![mistral_trace.png](mistral_trace.png)](https://wandb.ai/capecape/mistralai_project/weave/calls)