Feat: Add deepseek to llm_factories (#6051)

### What problem does this PR solve?

AWS Bedrock has made deepseek-r1 available on its serverless inference.

This adds the R1 serverless model for use via the bedrock model
abilities.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

conf/llm_factories.json

             "tags": "LLM,TEXT EMBEDDING",
             "status": "1",
             "llm": [
+                {
+                    "llm_name": "deepseek.r1-v1:0",
+                    "tags": "LLM,CHAT,128k",
+                    "max_tokens": 128000,
+                    "model_type": "chat"
+                },
                 {
                     "llm_name": "ai21.j2-ultra-v1",
                     "tags": "LLM,CHAT,8k",