feat(llm): expand LLM provider options and improve model selection UI

- Added new LLM providers including Google, Azure OpenAI, Bedrock, and others to the backend.
- Updated the model selection UI to dynamically display available models based on the selected provider.
- Enhanced the provider change handling to reset the model selection when the provider is changed.
- Improved the overall user experience by providing contextual information for model selection.

surfsense_backend/app/db.py

@@ -86,32 +86,33 @@ class LiteLLMProvider(str, Enum):
 
     OPENAI = "OPENAI"
     ANTHROPIC = "ANTHROPIC"
+    GOOGLE = "GOOGLE"
+    AZURE_OPENAI = "AZURE_OPENAI"
+    BEDROCK = "BEDROCK"
+    VERTEX_AI = "VERTEX_AI"
     GROQ = "GROQ"
     COHERE = "COHERE"
-    HUGGINGFACE = "HUGGINGFACE"
-    AZURE_OPENAI = "AZURE_OPENAI"
-    GOOGLE = "GOOGLE"
-    AWS_BEDROCK = "AWS_BEDROCK"
-    OLLAMA = "OLLAMA"
     MISTRAL = "MISTRAL"
-    TOGETHER_AI = "TOGETHER_AI"
-    OPENROUTER = "OPENROUTER"
-    REPLICATE = "REPLICATE"
-    PALM = "PALM"
-    VERTEX_AI = "VERTEX_AI"
-    ANYSCALE = "ANYSCALE"
-    PERPLEXITY = "PERPLEXITY"
-    DEEPINFRA = "DEEPINFRA"
-    AI21 = "AI21"
-    NLPCLOUD = "NLPCLOUD"
-    ALEPH_ALPHA = "ALEPH_ALPHA"
-    PETALS = "PETALS"
-    COMETAPI = "COMETAPI"
-    # Chinese LLM Providers (OpenAI-compatible)
     DEEPSEEK = "DEEPSEEK"
+    XAI = "XAI"
+    OPENROUTER = "OPENROUTER"
+    TOGETHER_AI = "TOGETHER_AI"
+    FIREWORKS_AI = "FIREWORKS_AI"
+    REPLICATE = "REPLICATE"
+    PERPLEXITY = "PERPLEXITY"
+    OLLAMA = "OLLAMA"
     ALIBABA_QWEN = "ALIBABA_QWEN"
     MOONSHOT = "MOONSHOT"
     ZHIPU = "ZHIPU"
+    ANYSCALE = "ANYSCALE"
+    DEEPINFRA = "DEEPINFRA"
+    CEREBRAS = "CEREBRAS"
+    SAMBANOVA = "SAMBANOVA"
+    AI21 = "AI21"
+    CLOUDFLARE = "CLOUDFLARE"
+    DATABRICKS = "DATABRICKS"
+    COMETAPI = "COMETAPI"
+    HUGGINGFACE = "HUGGINGFACE"
     CUSTOM = "CUSTOM"
 
 

surfsense_backend/app/services/llm_service.py

@@ -61,11 +61,26 @@ async def validate_llm_config(
                 "AZURE_OPENAI": "azure",
                 "OPENROUTER": "openrouter",
                 "COMETAPI": "cometapi",
-                # Chinese LLM providers (OpenAI-compatible)
+                "XAI": "xai",
+                "BEDROCK": "bedrock",
+                "AWS_BEDROCK": "bedrock",  # Legacy support (backward compatibility)
+                "VERTEX_AI": "vertex_ai",
+                "TOGETHER_AI": "together_ai",
+                "FIREWORKS_AI": "fireworks_ai",
+                "REPLICATE": "replicate",
+                "PERPLEXITY": "perplexity",
+                "ANYSCALE": "anyscale",
+                "DEEPINFRA": "deepinfra",
+                "CEREBRAS": "cerebras",
+                "SAMBANOVA": "sambanova",
+                "AI21": "ai21",
+                "CLOUDFLARE": "cloudflare",
+                "DATABRICKS": "databricks",
+                # Chinese LLM providers
                 "DEEPSEEK": "openai",
                 "ALIBABA_QWEN": "openai",
                 "MOONSHOT": "openai",
-                "ZHIPU": "openai",
+                "ZHIPU": "openai",  # GLM needs special handling
             }
             provider_prefix = provider_map.get(provider, provider.lower())
             model_string = f"{provider_prefix}/{model_name}"
@@ -187,12 +202,26 @@ async def get_user_llm_instance(
                 "AZURE_OPENAI": "azure",
                 "OPENROUTER": "openrouter",
                 "COMETAPI": "cometapi",
-                # Chinese LLM providers (OpenAI-compatible)
-                "DEEPSEEK": "openai",  # DeepSeek uses OpenAI-compatible API
-                "ALIBABA_QWEN": "openai",  # Qwen uses OpenAI-compatible API
-                "MOONSHOT": "openai",  # Moonshot (Kimi) uses OpenAI-compatible API
-                "ZHIPU": "openai",  # Zhipu (GLM) uses OpenAI-compatible API
-                # Add more mappings as needed
+                "XAI": "xai",
+                "BEDROCK": "bedrock",
+                "AWS_BEDROCK": "bedrock",  # Legacy support (backward compatibility)
+                "VERTEX_AI": "vertex_ai",
+                "TOGETHER_AI": "together_ai",
+                "FIREWORKS_AI": "fireworks_ai",
+                "REPLICATE": "replicate",
+                "PERPLEXITY": "perplexity",
+                "ANYSCALE": "anyscale",
+                "DEEPINFRA": "deepinfra",
+                "CEREBRAS": "cerebras",
+                "SAMBANOVA": "sambanova",
+                "AI21": "ai21",
+                "CLOUDFLARE": "cloudflare",
+                "DATABRICKS": "databricks",
+                # Chinese LLM providers
+                "DEEPSEEK": "openai",
+                "ALIBABA_QWEN": "openai",
+                "MOONSHOT": "openai",
+                "ZHIPU": "openai",
             }
             provider_prefix = provider_map.get(
                 llm_config.provider.value, llm_config.provider.value.lower()