feat(llm - embed): Add support for Azure OpenAI (#1698)

* Add support for Azure OpenAI

* fix: wrong default api_version

Should be dashes instead of underscores.
see: https://learn.microsoft.com/en-us/azure/ai-services/openai/reference

* fix: code styling

applied "make check" changes

* refactor: extend documentation

* mention azopenai as available option and extras
* add recommended section
* include settings-azopenai.yaml configuration file

* fix: documentation

private_gpt/components/embedding/embedding_component.py

@@ -72,6 +72,24 @@ class EmbeddingComponent:
                     model_name=ollama_settings.embedding_model,
                     base_url=ollama_settings.api_base,
                 )
+            case "azopenai":
+                try:
+                    from llama_index.embeddings.azure_openai import (  # type: ignore
+                        AzureOpenAIEmbedding,
+                    )
+                except ImportError as e:
+                    raise ImportError(
+                        "Azure OpenAI dependencies not found, install with `poetry install --extras embeddings-azopenai`"
+                    ) from e
+
+                azopenai_settings = settings.azopenai
+                self.embedding_model = AzureOpenAIEmbedding(
+                    model=azopenai_settings.embedding_model,
+                    deployment_name=azopenai_settings.embedding_deployment_name,
+                    api_key=azopenai_settings.api_key,
+                    azure_endpoint=azopenai_settings.azure_endpoint,
+                    api_version=azopenai_settings.api_version,
+                )
             case "mock":
                 # Not a random number, is the dimensionality used by
                 # the default embedding model

private_gpt/components/llm/llm_component.py

@@ -132,5 +132,23 @@ class LLMComponent:
                     context_window=settings.llm.context_window,
                     additional_kwargs=settings_kwargs,
                 )
+            case "azopenai":
+                try:
+                    from llama_index.llms.azure_openai import (  # type: ignore
+                        AzureOpenAI,
+                    )
+                except ImportError as e:
+                    raise ImportError(
+                        "Azure OpenAI dependencies not found, install with `poetry install --extras llms-azopenai`"
+                    ) from e
+
+                azopenai_settings = settings.azopenai
+                self.llm = AzureOpenAI(
+                    model=azopenai_settings.llm_model,
+                    deployment_name=azopenai_settings.llm_deployment_name,
+                    api_key=azopenai_settings.api_key,
+                    azure_endpoint=azopenai_settings.azure_endpoint,
+                    api_version=azopenai_settings.api_version,
+                )
             case "mock":
                 self.llm = MockLLM()

private_gpt/settings/settings.py

@@ -81,7 +81,9 @@ class DataSettings(BaseModel):
 
 
 class LLMSettings(BaseModel):
-    mode: Literal["llamacpp", "openai", "openailike", "sagemaker", "mock", "ollama"]
+    mode: Literal[
+        "llamacpp", "openai", "openailike", "azopenai", "sagemaker", "mock", "ollama"
+    ]
     max_new_tokens: int = Field(
         256,
         description="The maximum number of token that the LLM is authorized to generate in one completion.",
@@ -152,7 +154,7 @@ class HuggingFaceSettings(BaseModel):
 
 
 class EmbeddingSettings(BaseModel):
-    mode: Literal["huggingface", "openai", "sagemaker", "ollama", "mock"]
+    mode: Literal["huggingface", "openai", "azopenai", "sagemaker", "ollama", "mock"]
     ingest_mode: Literal["simple", "batch", "parallel"] = Field(
         "simple",
         description=(
@@ -239,6 +241,25 @@ class OllamaSettings(BaseModel):
     )
 
 
+class AzureOpenAISettings(BaseModel):
+    api_key: str
+    azure_endpoint: str
+    api_version: str = Field(
+        "2023_05_15",
+        description="The API version to use for this operation. This follows the YYYY-MM-DD format.",
+    )
+    embedding_deployment_name: str
+    embedding_model: str = Field(
+        "text-embedding-ada-002",
+        description="OpenAI Model to use. Example: 'text-embedding-ada-002'.",
+    )
+    llm_deployment_name: str
+    llm_model: str = Field(
+        "gpt-35-turbo",
+        description="OpenAI Model to use. Example: 'gpt-4'.",
+    )
+
+
 class UISettings(BaseModel):
     enabled: bool
     path: str
@@ -349,6 +370,7 @@ class Settings(BaseModel):
     sagemaker: SagemakerSettings
     openai: OpenAISettings
     ollama: OllamaSettings
+    azopenai: AzureOpenAISettings
     vectorstore: VectorstoreSettings
     nodestore: NodeStoreSettings
     qdrant: QdrantSettings | None = None