🐛 [Gen AI Tooling] Let user choose the number of chunk embeded per request.

gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/models/em/azureopenai/azure_openai_em_setting.py

@@ -38,7 +38,7 @@ class AzureOpenAIEMSetting(BaseEMSetting):
     )
     api_key: SecretKey = Field(
         description='The secret that stores the API key used to authenticate requests to the AI Provider API.',
-        examples=[RawSecretKey(secret='ab7-************-A1IV4B')]
+        examples=[RawSecretKey(secret='ab7-************-A1IV4B')],
     )
     deployment_name: str = Field(
         description='The deployment name you chose when you deployed the model.',
@@ -55,3 +55,7 @@ class AzureOpenAIEMSetting(BaseEMSetting):
         description='The API version to use for this operation.',
         examples=['2023-05-15'],
     )
+    number_of_chunk_per_request: int = Field(
+        description='The number of chunks sent per request, take care of your rate limits. Default value is 50',
+        default=50,
+    )

gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/models/em/openai/openai_em_setting.py

@@ -37,11 +37,15 @@ class OpenAIEMSetting(BaseEMSetting):
     )
     api_key: SecretKey = Field(
         description='The secret that stores the API key used to authenticate requests to the AI Provider API.',
-        examples=[RawSecretKey(secret='ab7-************-A1IV4B')]
+        examples=[RawSecretKey(secret='ab7-************-A1IV4B')],
     )
     model: str = Field(description='The model id', examples=['text-embedding-ada-002'])
     base_url: str = Field(
         description='The OpenAI endpoint base URL',
         examples=['https://api.openai.com/v1'],
-        default='https://api.openai.com/v1'
-    )
+        default='https://api.openai.com/v1',
+    )
+    number_of_chunk_per_request: int = Field(
+        description='The number of chunks sent per request, take care of your rate limits. Default value is 50.',
+        default=50,
+    )

gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/services/langchain/factories/em/azure_openai_em_factory.py

@@ -1,4 +1,4 @@
-#   Copyright (C) 2023-2024 Credit Mutuel Arkea
+#   Copyright (C) 2023-2025 Credit Mutuel Arkea
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.
@@ -47,8 +47,9 @@ def get_embedding_model(self) -> Embeddings:
             azure_endpoint=str(self.setting.api_base),
             azure_deployment=self.setting.deployment_name,
             # the model is not Nullable, it has a default value
-            model=self.setting.model or OpenAIEmbeddings.__fields__["model"].default,
+            model=self.setting.model or OpenAIEmbeddings.__fields__['model'].default,
             timeout=application_settings.em_provider_timeout,
+            chunk_size=self.setting.number_of_chunk_per_request,
         )
 
     @openai_exception_handler(provider='AzureOpenAIService')

gen-ai/orchestrator-server/src/main/python/server/src/gen_ai_orchestrator/services/langchain/factories/em/openai_em_factory.py

@@ -1,4 +1,4 @@
-#   Copyright (C) 2023-2024 Credit Mutuel Arkea
+#   Copyright (C) 2023-2025 Credit Mutuel Arkea
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
 #   you may not use this file except in compliance with the License.
@@ -50,6 +50,7 @@ def get_embedding_model(self) -> Embeddings:
             base_url=self.setting.base_url,
             model=self.setting.model,
             timeout=application_settings.em_provider_timeout,
+            chunk_size=self.setting.chunk_size,
         )
 
     @openai_exception_handler(provider='OpenAI')