Merge pull request #98 from ovh/update-models-on-tutos

scraly · web-flow · commit 9a43f57ee7fe · 2025-04-09T11:55:05.000+02:00
fix: 🐛 made the models choices more generic
diff --git a/ai/ai-endpoints/java-langchain4j-chatbot/pom.xml b/ai/ai-endpoints/java-langchain4j-chatbot/pom.xml
@@ -18,7 +18,7 @@
     <maven.compiler.source>21</maven.compiler.source>
     <maven.compiler.target>21</maven.compiler.target>
     <maven.compiler.release>21</maven.compiler.release>
-    <langchain4j.version>0.33.0</langchain4j.version>
+    <langchain4j.version>0.36.2</langchain4j.version>
   </properties>
 
   <dependencies>
diff --git a/ai/ai-endpoints/java-langchain4j-chatbot/src/main/java/com/ovhcloud/examples/aiendpoints/BlockingChatbot.java b/ai/ai-endpoints/java-langchain4j-chatbot/src/main/java/com/ovhcloud/examples/aiendpoints/BlockingChatbot.java
@@ -6,16 +6,17 @@
 
 public class BlockingChatbot {
   private static final Logger _LOG = LoggerFactory.getLogger(BlockingChatbot.class);
-  private static final String OVHCLOUD_API_KEY = System.getenv("OVHCLOUD_API_KEY");
-
+  private static final String OVH_AI_ENDPOINTS_ACCESS_TOKEN = System.getenv("OVH_AI_ENDPOINTS_ACCESS_TOKEN");
+  private static final String OVH_AI_ENDPOINTS_MODEL_NAME = System.getenv("OVH_AI_ENDPOINTS_MODEL_NAME");
+  private static final String OVH_AI_ENDPOINTS_MODEL_URL = System.getenv("OVH_AI_ENDPOINTS_MODEL_URL");
 
   public static void main(String[] args) {
 
 
     MistralAiChatModel aiChatModel = MistralAiChatModel.builder()
-      .apiKey(OVHCLOUD_API_KEY)
-      .modelName("Mixtral-8x22B-Instruct-v0.1")
-      .baseUrl("https://mixtral-8x22b-instruct-v01.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/")
+      .apiKey(OVH_AI_ENDPOINTS_ACCESS_TOKEN)
+      .modelName(OVH_AI_ENDPOINTS_MODEL_NAME)
+      .baseUrl(OVH_AI_ENDPOINTS_MODEL_URL)
       .maxTokens(1500)
       .build();
 
diff --git a/ai/ai-endpoints/java-langchain4j-chatbot/src/main/java/com/ovhcloud/examples/aiendpoints/MemoryStreamingChatbot.java b/ai/ai-endpoints/java-langchain4j-chatbot/src/main/java/com/ovhcloud/examples/aiendpoints/MemoryStreamingChatbot.java
@@ -11,18 +11,21 @@
 public class MemoryStreamingChatbot {
 
   private static final Logger _LOG = LoggerFactory.getLogger(MemoryStreamingChatbot.class);
-  private static final String OVHCLOUD_API_KEY = System.getenv("OVHCLOUD_API_KEY");
+  private static final String OVH_AI_ENDPOINTS_ACCESS_TOKEN = System.getenv("OVH_AI_ENDPOINTS_ACCESS_TOKEN");
+  private static final String OVH_AI_ENDPOINTS_MODEL_NAME = System.getenv("OVH_AI_ENDPOINTS_MODEL_NAME");
+  private static final String OVH_AI_ENDPOINTS_MODEL_URL = System.getenv("OVH_AI_ENDPOINTS_MODEL_URL");
+  
 
   interface Assistant {
     TokenStream chat(String message);
   }
 
   public static void main(String[] args) {
     MistralAiStreamingChatModel streamingChatModel = MistralAiStreamingChatModel.builder()
-        .apiKey(OVHCLOUD_API_KEY)
-        .modelName("Mixtral-8x22B-Instruct-v0.1")
+        .apiKey(OVH_AI_ENDPOINTS_ACCESS_TOKEN)
+        .modelName(OVH_AI_ENDPOINTS_MODEL_NAME)
         .baseUrl(
-            "https://mixtral-8x22b-instruct-v01.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/")
+          OVH_AI_ENDPOINTS_MODEL_URL)
         .maxTokens(1500)
         .build();
 
diff --git a/ai/ai-endpoints/java-langchain4j-chatbot/src/main/java/com/ovhcloud/examples/aiendpoints/RAGStreamingChatbot.java b/ai/ai-endpoints/java-langchain4j-chatbot/src/main/java/com/ovhcloud/examples/aiendpoints/RAGStreamingChatbot.java
@@ -25,10 +25,14 @@
 
 public class RAGStreamingChatbot {
   private static final Logger _LOG = LoggerFactory.getLogger(RAGStreamingChatbot.class);
-  private static final String OVHCLOUD_API_KEY = System.getenv("OVHCLOUD_API_KEY");
   private static final String DATABASE_HOST = System.getenv("DATABASE_HOST");
   private static final String DATABASE_USER = System.getenv("DATABASE_USER");
   private static final String DATABASE_PASSWORD = System.getenv("DATABASE_PASSWORD");
+  private static final String OVH_AI_ENDPOINTS_ACCESS_TOKEN = System.getenv("OVH_AI_ENDPOINTS_ACCESS_TOKEN");
+  private static final String OVH_AI_ENDPOINTS_MODEL_NAME = System.getenv("OVH_AI_ENDPOINTS_MODEL_NAME");
+  private static final String OVH_AI_ENDPOINTS_MODEL_URL = System.getenv("OVH_AI_ENDPOINTS_MODEL_URL"); 
+  private static final String OVH_AI_ENDPOINTS_EMBEDDING_MODEL_URL = System.getenv("OVH_AI_ENDPOINTS_EMBEDDING_MODEL_URL"); 
+
 
   interface Assistant {
     TokenStream chat(String userMessage);
@@ -47,7 +51,10 @@ public static void main(String[] args) throws Exception {
     List<TextSegment> segments = splitter.split(document);
 
     // Do the embeddings and store them in an embedding store
-    EmbeddingModel embeddingModel = OvhAiEmbeddingModel.withApiKey(OVHCLOUD_API_KEY);
+    EmbeddingModel embeddingModel = OvhAiEmbeddingModel.builder()
+        .apiKey(OVH_AI_ENDPOINTS_ACCESS_TOKEN)
+        .baseUrl(OVH_AI_ENDPOINTS_EMBEDDING_MODEL_URL)
+        .build();
     List<Embedding> embeddings = embeddingModel.embedAll(segments).content();
 
     EmbeddingStore<TextSegment> embeddingStore = PgVectorEmbeddingStore.builder()
@@ -72,10 +79,10 @@ public static void main(String[] args) throws Exception {
         .build();
 
     MistralAiStreamingChatModel streamingChatModel = MistralAiStreamingChatModel.builder()
-        .apiKey(OVHCLOUD_API_KEY)
-        .modelName("Mistral-7B-Instruct-v0.2")
+        .apiKey(OVH_AI_ENDPOINTS_ACCESS_TOKEN)
+        .modelName(OVH_AI_ENDPOINTS_MODEL_NAME)
         .baseUrl(
-            "https://mistral-7b-instruct-v02.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1")
+            OVH_AI_ENDPOINTS_MODEL_URL)
         .maxTokens(512)
         .build();
 
diff --git a/ai/ai-endpoints/java-langchain4j-chatbot/src/main/java/com/ovhcloud/examples/aiendpoints/StreamingChatbot.java b/ai/ai-endpoints/java-langchain4j-chatbot/src/main/java/com/ovhcloud/examples/aiendpoints/StreamingChatbot.java
@@ -11,14 +11,18 @@
 public class StreamingChatbot {
 
   private static final Logger _LOG = LoggerFactory.getLogger(StreamingChatbot.class);
-  private static final String OVHCLOUD_API_KEY = System.getenv("OVHCLOUD_API_KEY");
+  private static final String OVH_AI_ENDPOINTS_ACCESS_TOKEN = System.getenv("OVH_AI_ENDPOINTS_ACCESS_TOKEN");
+  private static final String OVH_AI_ENDPOINTS_MODEL_NAME = System.getenv("OVH_AI_ENDPOINTS_MODEL_NAME");
+  private static final String OVH_AI_ENDPOINTS_MODEL_URL = System.getenv("OVH_AI_ENDPOINTS_MODEL_URL");
+
 
   public static void main(String[] args) {
     MistralAiStreamingChatModel streamingChatModel = MistralAiStreamingChatModel.builder()
-        .apiKey(OVHCLOUD_API_KEY).modelName("Mixtral-8x22B-Instruct-v0.1")
-        .baseUrl(
-            "https://mixtral-8x22b-instruct-v01.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1/")
-        .maxTokens(1500).build();
+        .apiKey(OVH_AI_ENDPOINTS_ACCESS_TOKEN)
+        .modelName(OVH_AI_ENDPOINTS_MODEL_NAME)
+        .baseUrl(OVH_AI_ENDPOINTS_MODEL_URL)
+        .maxTokens(1500)
+    .build();
 
     _LOG.info("🤖: ");
 
diff --git a/ai/ai-endpoints/js-langchain-chatbot/chatbot-streaming.js b/ai/ai-endpoints/js-langchain-chatbot/chatbot-streaming.js
@@ -15,10 +15,10 @@ async function chatCompletion(question) {
 
   // Use Mixtral-8x22B as LLM
   const model = new ChatMistralAI({
-    modelName: "Mixtral-8x22B-Instruct-v0.1",
-    model: "Mixtral-8x22B-Instruct-v0.1",
-    apiKey: "None",
-    endpoint: "https://mixtral-8x22b-instruct-v01.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/",
+    modelName: process.env.OVH_AI_ENDPOINTS_MODEL_NAME,
+    model: process.env.OVH_AI_ENDPOINTS_MODEL_NAME,
+    apiKey: process.env.OVH_AI_ENDPOINTS_ACCESS_TOKEN,
+    endpoint: process.env.OVH_AI_ENDPOINTS_MODEL_URL,
     maxTokens: 1500,
     streaming: true,
     verbose: false,
diff --git a/ai/ai-endpoints/js-langchain-chatbot/chatbot.js b/ai/ai-endpoints/js-langchain-chatbot/chatbot.js
@@ -14,10 +14,10 @@ async function chatCompletion(question) {
 
   // Use Mixtral-8x22B as LLM
   const model = new ChatMistralAI({
-    modelName: "Mixtral-8x22B-Instruct-v0.1",
-    model: "Mixtral-8x22B-Instruct-v0.1",
-    apiKey: "None",
-    endpoint: "https://mixtral-8x22b-instruct-v01.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/",
+    modelName: process.env.OVH_AI_ENDPOINTS_MODEL_NAME,
+    model: process.env.OVH_AI_ENDPOINTS_MODEL_NAME,
+    apiKey: process.env.OVH_AI_ENDPOINTS_ACCESS_TOKEN,
+    endpoint: process.env.OVH_AI_ENDPOINTS_MODEL_URL,
     maxTokens: 1500,
     streaming: false,
     verbose: false,
diff --git a/ai/ai-endpoints/python-langchain-chatbot/chat-bot-streaming-rag.py b/ai/ai-endpoints/python-langchain-chatbot/chat-bot-streaming-rag.py
@@ -14,8 +14,12 @@
 from langchain_core.output_parsers import StrOutputParser
 from langchain_core.runnables import RunnablePassthrough
 
-## Set the OVHcloud AI Endpoints token to use models
-_OVH_AI_ENDPOINTS_ACCESS_TOKEN = os.environ.get('OVH_AI_ENDPOINTS_TOKEN') 
+## Set the OVHcloud AI Endpoints configurations
+_OVH_AI_ENDPOINTS_ACCESS_TOKEN = os.environ.get('OVH_AI_ENDPOINTS_ACCESS_TOKEN') 
+_OVH_AI_ENDPOINTS_MODEL_NAME = os.environ.get('OVH_AI_ENDPOINTS_MODEL_NAME') 
+_OVH_AI_ENDPOINTS_MODEL_URL = os.environ.get('OVH_AI_ENDPOINTS_MODEL_URL') 
+_OVH_AI_ENDPOINTS_EMBEDDING_MODEL_NAME = os.environ.get('OVH_AI_ENDPOINTS_EMBEDDING_MODEL_NAME') 
+
 
 
 from langchain_text_splitters import RecursiveCharacterTextSplitter
@@ -25,9 +29,9 @@
 # The function print the LLM answer.
 def chat_completion(new_message: str):
   # no need to use a token
-  model = ChatMistralAI(model="Mixtral-8x22B-Instruct-v0.1", 
-                        api_key="foo",
-                        endpoint='https://mixtral-8x22b-instruct-v01.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1', 
+  model = ChatMistralAI(model=_OVH_AI_ENDPOINTS_MODEL_NAME, 
+                        api_key=_OVH_AI_ENDPOINTS_ACCESS_TOKEN,
+                        endpoint=_OVH_AI_ENDPOINTS_MODEL_URL, 
                         max_tokens=1500, 
                         streaming=True)
 
@@ -42,7 +46,7 @@ def chat_completion(new_message: str):
   # Split documents into chunks and vectorize them
   text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
   splits = text_splitter.split_documents(docs)
-  vectorstore = Chroma.from_documents(documents=splits, embedding=OVHCloudEmbeddings(model_name="multilingual-e5-base", access_token=_OVH_AI_ENDPOINTS_ACCESS_TOKEN))
+  vectorstore = Chroma.from_documents(documents=splits, embedding=OVHCloudEmbeddings(model_name=_OVH_AI_ENDPOINTS_EMBEDDING_MODEL_NAME, access_token=_OVH_AI_ENDPOINTS_ACCESS_TOKEN))
 
   prompt = hub.pull("rlm/rag-prompt")
 
diff --git a/ai/ai-endpoints/python-langchain-chatbot/chat-bot-streaming.py b/ai/ai-endpoints/python-langchain-chatbot/chat-bot-streaming.py
@@ -6,16 +6,18 @@
 from langchain_core.prompts import ChatPromptTemplate
 
 ## Set the OVHcloud AI Endpoints token to use models
-_OVH_AI_ENDPOINTS_ACCESS_TOKEN = os.environ.get('OVH_AI_ENDPOINTS_TOKEN') 
+_OVH_AI_ENDPOINTS_ACCESS_TOKEN = os.environ.get('OVH_AI_ENDPOINTS_ACCESS_TOKEN') 
+_OVH_AI_ENDPOINTS_MODEL_NAME = os.environ.get('OVH_AI_ENDPOINTS_MODEL_NAME') 
+_OVH_AI_ENDPOINTS_MODEL_URL = os.environ.get('OVH_AI_ENDPOINTS_MODEL_URL') 
 
 # Function in charge to call the LLM model.
 # Question parameter is the user's question.
 # The function print the LLM answer.
 def chat_completion(new_message: str):
   # no need to use a token
-  model = ChatMistralAI(model="Mixtral-8x22B-Instruct-v0.1", 
+  model = ChatMistralAI(model=_OVH_AI_ENDPOINTS_MODEL_NAME, 
                         api_key=_OVH_AI_ENDPOINTS_ACCESS_TOKEN,
-                        endpoint='https://mixtral-8x22b-instruct-v01.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1', 
+                        endpoint=_OVH_AI_ENDPOINTS_MODEL_URL, 
                         max_tokens=1500, 
                         streaming=True)
 
diff --git a/ai/ai-endpoints/python-langchain-chatbot/chat-bot.py b/ai/ai-endpoints/python-langchain-chatbot/chat-bot.py
@@ -5,16 +5,18 @@
 from langchain_core.prompts import ChatPromptTemplate
 
 ## Set the OVHcloud AI Endpoints token to use models
-_OVH_AI_ENDPOINTS_ACCESS_TOKEN = os.environ.get('OVH_AI_ENDPOINTS_TOKEN') 
+_OVH_AI_ENDPOINTS_ACCESS_TOKEN = os.environ.get('OVH_AI_ENDPOINTS_ACCESS_TOKEN') 
+_OVH_AI_ENDPOINTS_MODEL_NAME = os.environ.get('OVH_AI_ENDPOINTS_MODEL_NAME') 
+_OVH_AI_ENDPOINTS_MODEL_URL = os.environ.get('OVH_AI_ENDPOINTS_MODEL_URL') 
 
 # Function in charge to call the LLM model.
 # Question parameter is the user's question.
 # The function print the LLM answer.
 def chat_completion(question: str):
   # no need to use a token
-  model = ChatMistralAI(model="Mixtral-8x22B-Instruct-v0.1", 
+  model = ChatMistralAI(model=_OVH_AI_ENDPOINTS_MODEL_NAME, 
                         api_key=_OVH_AI_ENDPOINTS_ACCESS_TOKEN,
-                        endpoint='https://mixtral-8x22b-instruct-v01.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1', 
+                        endpoint=_OVH_AI_ENDPOINTS_MODEL_URL, 
                         max_tokens=1500)
 
   prompt = ChatPromptTemplate.from_messages([
diff --git a/ai/ai-endpoints/quarkus-langchain4j/src/main/resources/application.properties b/ai/ai-endpoints/quarkus-langchain4j/src/main/resources/application.properties
@@ -1,14 +1,14 @@
 ### Global configurations
 # Base URL for Mistral AI endpoints
-quarkus.langchain4j.mistralai.base-url=https://mistral-7b-instruct-v02.endpoints.kepler.ai.cloud.ovh.net/api/openai_compat/v1
+quarkus.langchain4j.mistralai.base-url=${OVH_AI_ENDPOINTS_MODEL_URL}
 # Activate or not the log during the request
 quarkus.langchain4j.mistralai.log-requests=true
 # Activate or not the log during the response
 quarkus.langchain4j.mistralai.log-responses=true
 # Delay before raising a timeout exception                    
 quarkus.langchain4j.mistralai.timeout=60s    
 # No key is needed
-quarkus.langchain4j.mistralai.api-key=foo
+quarkus.langchain4j.mistralai.api-key=${OVH_AI_ENDPOINTS_ACCESS_TOKEN}
 
 # Activate or not the Mistral AI embedding model                      
 quarkus.langchain4j.mistralai.embedding-model.enabled=false
@@ -17,7 +17,7 @@ quarkus.langchain4j.mistralai.embedding-model.enabled=false
 # Activate or not the Mistral AI chat model
 quarkus.langchain4j.mistralai.chat-model.enabled=true              
 # Chat model name used
-quarkus.langchain4j.mistralai.chat-model.model-name=Mistral-7B-Instruct-v0.2
+quarkus.langchain4j.mistralai.chat-model.model-name=${OVH_AI_ENDPOINTS_MODEL_NAME}
 # Number of tokens to use
 quarkus.langchain4j.mistralai.chat-model.max-tokens=1024
 
