feat: Add Mistral embedding

README.md

@@ -61,7 +61,7 @@ The following environment variables are required to run the application:
 - `PDF_EXTRACT_IMAGES`: (Optional) A boolean value indicating whether to extract images from PDF files. Default value is "False".
 - `DEBUG_RAG_API`: (Optional) Set to "True" to show more verbose logging output in the server console, and to enable postgresql database routes
 - `CONSOLE_JSON`: (Optional) Set to "True" to log as json for Cloud Logging aggregations
-- `EMBEDDINGS_PROVIDER`: (Optional) either "openai", "bedrock", "azure", "huggingface", "huggingfacetei" or "ollama", where "huggingface" uses sentence_transformers; defaults to "openai"
+- `EMBEDDINGS_PROVIDER`: (Optional) either "openai", "bedrock", "azure", "huggingface", "huggingfacetei", "ollama" or "mistral", where "huggingface" uses sentence_transformers; defaults to "openai"
 - `EMBEDDINGS_MODEL`: (Optional) Set a valid embeddings model to use from the configured provider.
     - **Defaults**
     - openai: "text-embedding-3-small"
@@ -70,6 +70,7 @@ The following environment variables are required to run the application:
     - huggingfacetei: "http://huggingfacetei:3000". Hugging Face TEI uses model defined on TEI service launch.
     - ollama: "nomic-embed-text"
     - bedrock: "amazon.titan-embed-text-v1"
+    - mistral: "mistral-embed"
 - `RAG_AZURE_OPENAI_API_VERSION`: (Optional) Default is `2023-05-15`. The version of the Azure OpenAI API.
 - `RAG_AZURE_OPENAI_API_KEY`: (Optional) The API key for Azure OpenAI service.
     - Note: `AZURE_OPENAI_API_KEY` will work but `RAG_AZURE_OPENAI_API_KEY` will override it in order to not conflict with LibreChat setting.
@@ -83,6 +84,7 @@ The following environment variables are required to run the application:
 - `AWS_DEFAULT_REGION`: (Optional) defaults to `us-east-1`
 - `AWS_ACCESS_KEY_ID`: (Optional) needed for bedrock embeddings
 - `AWS_SECRET_ACCESS_KEY`: (Optional) needed for bedrock embeddings
+- `MISTRAL_API_KEY`: (Optional) needed for mistral embeddings
 
 Make sure to set these environment variables before running the application. You can set them in a `.env` file or as system environment variables.
 

app/config.py

@@ -25,7 +25,7 @@ class EmbeddingsProvider(Enum):
     HUGGINGFACETEI = "huggingfacetei"
     OLLAMA = "ollama"
     BEDROCK = "bedrock"
-
+    MISTRAL = "mistral"
 
 def get_env_variable(
     var_name: str, default_value: str = None, required: bool = False
@@ -176,6 +176,7 @@ async def dispatch(self, request, call_next):
 OLLAMA_BASE_URL = get_env_variable("OLLAMA_BASE_URL", "http://ollama:11434")
 AWS_ACCESS_KEY_ID = get_env_variable("AWS_ACCESS_KEY_ID", "")
 AWS_SECRET_ACCESS_KEY = get_env_variable("AWS_SECRET_ACCESS_KEY", "")
+MISTRAL_API_KEY = get_env_variable("MISTRAL_API_KEY", "")
 
 ## Embeddings
 
@@ -226,6 +227,13 @@ def init_embeddings(provider, model):
             model_id=model,
             region_name=AWS_DEFAULT_REGION,
         )
+    elif provider == EmbeddingsProvider.MISTRAL:
+        from langchain_mistralai import MistralAIEmbeddings
+
+        return MistralAIEmbeddings(
+            model=model,
+            api_key=MISTRAL_API_KEY,
+        )
     else:
         raise ValueError(f"Unsupported embeddings provider: {provider}")
 
@@ -253,6 +261,10 @@ def init_embeddings(provider, model):
         "EMBEDDINGS_MODEL", "amazon.titan-embed-text-v1"
     )
     AWS_DEFAULT_REGION = get_env_variable("AWS_DEFAULT_REGION", "us-east-1")
+elif EMBEDDINGS_PROVIDER == EmbeddingsProvider.MISTRAL:
+    EMBEDDINGS_MODEL = get_env_variable(
+        "EMBEDDINGS_MODEL", "mistral-embed"
+    )
 else:
     raise ValueError(f"Unsupported embeddings provider: {EMBEDDINGS_PROVIDER}")
 

requirements.txt

@@ -30,6 +30,7 @@ pymongo==4.6.3
 langchain-mongodb==0.2.0
 langchain-ollama==0.2.0
 langchain-huggingface==0.1.0
+langchain-mistralai==0.2.1
 cryptography==44.0.1
 python-magic==0.4.27
 python-pptx==0.6.23