feat(genapi): update faq explaining how multi-turn conversation works with llm

Author: fpagny

pages/generative-apis/troubleshooting/fixing-common-issues.mdx

@@ -122,6 +122,45 @@ Below are common issues that you may encounter when using Generative APIs, their
   - Graph across time should be empty
 ```
 
+## Previous messages are not taken into account by the model
+
+### Causes
+- Previous messages are not sent to the model
+- The content sent exceeds maximum context window for this model
+
+### Solution
+- LLM models are completely "stateless" and thus do not store previous messages or conversations. For example, when building a chatbot application, each time a new message is sent by the user, all preceding messages in the conversation needs to be sent through the API payload. Example payload for multi-turn conversation:
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    base_url="https://api.scaleway.ai/v1",
+    api_key=os.getenv("SCW_SECRET_KEY")
+)
+
+response = client.chat.completions.create(
+    model="llama-3.1-8b-instruct",
+    messages=[
+      {
+        "role": "user",
+        "content": "What is the solution to 1+1= ?"
+      },
+      {
+        "role": "assistant",
+        "content": "2"
+      },
+      {
+        "role": "user",
+        "content": "Double this number"
+      }
+    ]
+)
+
+print(response.choices[0].message.content)
+```
+This snippet will output the model response, which is `4`.
+- When exceeding maximum context window, you should receive a `400 - BadRequestError` detailing context length value you exceeded. In this case, you should reduce the size of the content you send to the API.
+
 ## Best practices for optimizing model performance
 
 ### Input size management
@@ -135,4 +174,4 @@ Below are common issues that you may encounter when using Generative APIs, their
 ### Debugging silent errors
 - For cases where no explicit error is returned:
   - Verify all fields in the API request are correctly named and formatted.
-  - Test the request with smaller and simpler inputs to isolate potential issues.
+  - Test the request with smaller and simpler inputs to isolate potential issues.