feat(genapi): add examples

Author: bene2k1

menu/navigation.json

@@ -964,6 +964,10 @@
                   {
                     "label": "Adding AI to IntelliJ IDEA using Continue",
                     "slug": "adding-ai-to-intellij-using-continue"
+                  },
+                  {
+                    "label": "Integrating Generative APIs with popular AI tools",
+                    "slug": "integrating-generative-apis-with-popular-tools"
                   }
                 ],
                 "label": "Additional Content",

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

@@ -0,0 +1,178 @@
+---
+meta:
+  title: Integrating Scaleway Generative APIs with popular AI tools
+  description: Learn how to integrate Scaleway's Generative APIs with popular AI tools.
+content:
+  h1: Integrating Scaleway Generative APIs with popular AI tools
+  paragraph: Learn how to integrate Scaleway's Generative APIs with popular AI tools.
+tags: generative-apis, ai, language-models
+validation_date: 2025-02-18
+posted_date: 2025-02-18
+---
+
+Scaleway’s Generative APIs provide easy integration with various AI frameworks and tools. This guide outlines the configuration steps needed to integrate Scaleway's models into different environments.
+
+## OpenAI-Compatible libraries
+Scaleway Generative APIs follow OpenAI’s API structure, making integration straightforward.
+
+### Configuration
+Set the API key and base URL in your OpenAI-compatible client:
+
+```python
+import openai
+
+openai.api_key = "<API secret key>"
+openai.api_base = "https://api.scaleway.ai/v1"
+
+response = openai.ChatCompletion.create(
+    model="llama-3.1-8b-instruct",
+    messages=[{"role": "user", "content": "Tell me a joke about AI"}]
+)
+
+print(response["choices"][0]["message"]["content"])
+```
+
+
+## LangChain (RAG & LLM applications)
+
+LangChain supports Scaleway models for both inference and embeddings.
+
+### Configuration
+1. Install required dependencies:
+   ```bash
+   pip install langchain langchain_openai langchain_postgres psycopg2
+   ```
+2. Set up the API connection:
+   ```python
+   from langchain_openai import OpenAIEmbeddings, ChatOpenAI
+   import os
+
+   os.environ["OPENAI_API_KEY"] = "<API secret key>"
+   os.environ["OPENAI_API_BASE"] = "https://api.scaleway.ai/v1"
+
+   llm = ChatOpenAI(model="llama-3.1-8b-instruct")
+   embeddings = OpenAIEmbeddings(model="bge-multilingual-gemma2")
+   ```
+3. Use a vector store for retrieval:
+   ```python
+   from langchain_postgres import PGVector
+
+   connection_string = "postgresql+psycopg2://user:password@host:port/dbname"
+   vector_store = PGVector(connection=connection_string, embeddings=embeddings)
+   ```
+
+## LlamaIndex (document indexing & retrieval)
+
+LlamaIndex enables easy document retrieval using Scaleway’s models.
+
+### Configuration
+1. Install dependencies:
+   ```bash
+   pip install llama-index
+   ```
+2. Set up the embedding model:
+   ```python
+   from llama_index.embeddings.openai import OpenAIEmbedding
+
+   embed_model = OpenAIEmbedding(
+       api_key="<API secret key>",
+       api_base="https://api.scaleway.ai/v1",
+       model="bge-multilingual-gemma2"
+   )
+   ```
+3. Index and query documents:
+   ```python
+   from llama_index import VectorStoreIndex, SimpleDirectoryReader
+
+   documents = SimpleDirectoryReader("data").load_data()
+   index = VectorStoreIndex.from_documents(documents, embed_model=embed_model)
+   query_engine = index.as_query_engine()
+
+   response = query_engine.query("Summarize this document")
+   print(response)
+   ```
+
+## Continue Dev (AI coding assistance)
+
+Continue Dev allows configuring Scaleway models for code completion.
+
+### Configuration
+Modify `continue.json` to add Scaleway’s API:
+
+```json
+{
+  "models": [
+    {
+      "title": "Qwen2.5-Coder-32B-Instruct",
+      "provider": "scaleway",
+      "model": "qwen2.5-coder-32b-instruct",
+      "apiKey": "<API secret key>"
+    }
+  ],
+  "embeddingsProvider": {
+    "provider": "scaleway",
+    "model": "bge-multilingual-gemma2",
+    "apiKey": "<API secret key>"
+  }
+}
+```
+
+---
+
+## Transformers (Hugging Face integration)
+
+Hugging Face’s `transformers` library can send requests to Scaleway-hosted models.
+
+### Configuration
+1. Install dependencies:
+   ```bash
+   pip install transformers requests
+   ```
+2. Use a custom API endpoint:
+   ```python
+   from transformers import pipeline
+
+   generator = pipeline(
+       "text-generation",
+       model="llama-3.1-8b-instruct",
+       tokenizer="meta-llama/Llama-3-8b",
+       api_base="https://api.scaleway.ai/v1",
+       api_key="<API secret key>"
+   )
+
+   print(generator("Write a short poem about the ocean"))
+   ```
+
+---
+
+## API clients & custom integrations
+You can interact with Scaleway’s Generative APIs directly using any HTTP client.
+
+### cURL example
+```bash
+curl https://api.scaleway.ai/v1/chat/completions \
+  -H "Authorization: Bearer <API secret key>" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "llama-3.1-8b-instruct",
+    "messages": [{"role": "user", "content": "What is quantum computing?"}]
+  }'
+```
+
+### Python example
+```python
+import requestsMe
+
+headers = {
+    "Authorization": "Bearer <API secret key>",
+    "Content-Type": "application/json"
+}
+
+data = {
+    "model": "llama-3.1-8b-instruct",
+    "messages": [{"role": "user", "content": "Explain black holes"}]
+}
+
+response = requests.post("https://api.scaleway.ai/v1/chat/completions", json=data, headers=headers)
+print(response.json()["choices"][0]["message"]["content"])
+```