feat(gen-apis): add llamaindex

pages/generative-apis/reference-content/integrating-generative-apis-with-popular-tools.mdx

@@ -20,8 +20,8 @@ The following table compares AI tools and libraries supported by Scaleway's Gene
 | Tool/Library | Description | Use cases | Integration effort |
 | --- | --- | --- | --- |
 | [OpenAI client](#openai-client-libraries) | Popular AI library for natural language processing | Text generation, language translation, text summarization | Low |
-| [LangChain](#langchain-rag-and-llm-applications) | Library for building AI applications | Inference, embeddings, document indexing and retrieval | Medium |
-| [LlamaIndex](#llamaindex-data-framework) | Framework for building powerful LLM (Large Language Model) applications | Knowledge graph building, document retrieval, data indexing | Medium |
+| [LangChain](#langchain-rag-and-llm-applications) | Library for building AI applications leveraging RAG | Inference, embeddings, document indexing and retrieval | Medium |
+| [LlamaIndex](#llamaIndex-advanced-rag-applications) | Library for building advanced AI RAG applications | Knowledge graph building, document retrieval, data indexing | Medium |
 | [Continue Dev](#continue-dev-ai-coding-assistance) | Library for AI-powered coding assistance | Code completion, code review | Low |
 | [cURL/Python](#custom-http-integrations) | Direct HTTP API calls for custom integrations | Custom applications, data processing | High |
 
@@ -72,46 +72,47 @@ LangChain is a popular library for building AI applications. Scaleway's Generati
   - [Implementing Retrieval-Augmented Generation (RAG) with LangChain and Scaleway Generative APIs](/tutorials/how-to-implement-rag-generativeapis/)
 </Message>
 
-## LlamaIndex data framework
-
-LlamaIndex is an open source is a data framework for building Large Language Models (LLMs) based application. To get started, you'll need to install the LlamaIndex and set up your API key.
-
-### Configuration
+## LlamaIndex (advanced RAG applications)
 
+LlamaIndex is an open source framework for building Large Language Models (LLMs) based application, especially optimizing RAG (Retrieval Augmented Generation) pipelines. 
 To use the LlamaIndex framework with Scaleway's Generative APIs, first install the required dependencies:
-
 ```bash
-    pip install llama-index-llms-openai-like
+pip install llama-index-llms-openai-like
 ```
 
-Then set the API key and base URL in your OpenAILike-compatible client:
-
+Then, create a file `main.py` and add the following code to it to configure `OpenAILike` client and secret key:
 ```python
 from llama_index.llms.openai_like import OpenAILike
+from llama_index.core.llms import ChatMessage
 
 llm = OpenAILike(
-model="pixtral-12b-2409",
-api_key="<API secret key>",
-api_base="https://api.scaleway.ai/v1",
-max_tokens=512,
-temperature=0.7,
-top_p=1,
-presence_penalty=0,
+  model="llama-3.1-8b-instruct",
+  api_key="<API secret key>",
+  api_base="https://api.scaleway.ai/v1",
+  max_tokens=512,
+  temperature=0.7,
+  top_p=1,
+  presence_penalty=0,
 )
 ```
 <Message type="tip">
     Make sure to replace `<API secret key>` with your actual API key.
 </Message>
 
-### Using LlamaIndex client to chat with the LLM
-
-Once the configuration is set up, you can interact with the LLM by sending messages to the model. The following code demonstrates how to chat with the model using LlamaIndex:
-
+You can then interact with the LLM by sending messages to the model with the following code:
 ```python
-    response = llm.chat([ChatMessage("could you tell about Scaleway please")])
-    print(response)
+response = llm.chat([ChatMessage("Could you tell me about Scaleway please ?")])
+print(response)
 ```
 
+Finally, run `main.py`:
+```python
+python main.py
+```
+The LLM response should display an answer:
+```bash
+Generally, Scaleway is a reliable and secure cloud provider that offers a range of services for businesses and developers.
+```
 
 ## Continue Dev (AI coding assistance)
 
@@ -166,4 +167,4 @@ print(response.json()["choices"][0]["message"]["content"])
 ```
 <Message type="tip">
   Make sure to replace `<API secret key>` with your actual API key.
-</Message>
+</Message>