feat: together now supports base64 embedding encoding

recordings for: ./scripts/integration-tests.sh --stack-config server:ci-tests --suite base --setup together --subdirs inference --pattern openai

tests/integration/recordings/responses/d2e057a81717.json

@@ -0,0 +1,61 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://api.together.xyz/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Test trace openai with temperature 1"
+        }
+      ],
+      "max_tokens": 100,
+      "stream": false,
+      "temperature": 0.7
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "oCfxJ43-4Yz4kd-984c2b99bc6a9045",
+        "choices": [
+          {
+            "finish_reason": "length",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": "I'll do my best to generate a response with a temperature of 1. \n\nIn the context of language models like myself, temperature is a parameter that controls the level of randomness or creativity in the generated text. A temperature of 1 is relatively high, which means the model will produce more diverse and potentially less coherent text.\n\nHere's a response with a temperature of 1:\n\n\"The stars shone brightly in the midnight sky, like diamonds scattered across the velvet expanse. The world was bath",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": null,
+              "audio": null,
+              "function_call": null,
+              "tool_calls": []
+            },
+            "seed": 8314651915728863000
+          }
+        ],
+        "created": 1758820596,
+        "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": null,
+        "usage": {
+          "completion_tokens": 100,
+          "prompt_tokens": 43,
+          "total_tokens": 143,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null,
+          "cached_tokens": 0
+        },
+        "prompt": []
+      }
+    },
+    "is_streaming": false
+  }
+}