fix: prompt/completion format

docs/ai/llm-spans.md

@@ -65,7 +65,7 @@ The event name MUST be `gen_ai.llm.content.prompt`.
 
 | Attribute  | Type | Description  | Examples  | Requirement Level |
 |---|---|---|---|---|
-| [`gen_ai.llm.prompt`](../attributes-registry/llm.md) | string | The full prompt string sent to an LLM in a request. [1] | `\\n\\nHuman:You are an AI assistant that tells jokes. Can you tell me a joke about OpenTelemetry?\\n\\nAssistant:` | Recommended |
+| [`gen_ai.llm.prompt`](../attributes-registry/llm.md) | string | The full prompt sent to an LLM, as a stringified JSON in OpenAI's format. [1] | `[{'role': 'user', 'content': 'What is the capital of France?'}]` | Recommended |
 
 **[1]:** The full prompt sent to an LLM in a request, structured as a JSON in OpenAI's format.
 <!-- endsemconv -->
@@ -75,7 +75,7 @@ The event name MUST be `gen_ai.llm.content.completion`.
 
 | Attribute  | Type | Description  | Examples  | Requirement Level |
 |---|---|---|---|---|
-| [`gen_ai.llm.completion`](../attributes-registry/llm.md) | string | The full response string from an LLM in a response. [1] | `Why did the developer stop using OpenTelemetry? Because they couldnt trace their steps!` | Recommended |
+| [`gen_ai.llm.completion`](../attributes-registry/llm.md) | string | The full response received from the LLM, as a stringified JSON in OpenAI's format. [1] | `[{'role': 'assistant', 'content': 'The capital of France is Paris.'}]` | Recommended |
 
 **[1]:** The full response from an LLM, structured as a JSON in OpenAI's format.
 <!-- endsemconv -->

docs/attributes-registry/llm.md

@@ -9,10 +9,6 @@
   * [Request Attributes](#request-attributes)
   * [Response Attributes](#response-attributes)
   * [Event Attributes](#event-attributes)
-- [OpenAI Attributes](#openai-attributes)
-  * [Request Attributes](#request-attributes-1)
-  * [Response Attributes](#response-attributes-1)
-  * [Event Attributes](#event-attributes-1)
 
 <!-- tocstop -->
 
@@ -47,6 +43,6 @@
 <!-- semconv registry.llm(omit_requirement_level,tag=llm-generic-events) -->
 | Attribute  | Type | Description  | Examples  |
 |---|---|---|---|
-| `gen_ai.llm.completion` | string | The full response string from an LLM in a response. | `Why did the developer stop using OpenTelemetry? Because they couldnt trace their steps!` |
-| `gen_ai.llm.prompt` | string | The full prompt string sent to an LLM in a request. | `\\n\\nHuman:You are an AI assistant that tells jokes. Can you tell me a joke about OpenTelemetry?\\n\\nAssistant:` |
+| `gen_ai.llm.completion` | string | The full response received from the LLM, as a stringified JSON in OpenAI's format. | `[{'role': 'assistant', 'content': 'The capital of France is Paris.'}]` |
+| `gen_ai.llm.prompt` | string | The full prompt sent to an LLM, as a stringified JSON in OpenAI's format. | `[{'role': 'user', 'content': 'What is the capital of France?'}]` |
 <!-- endsemconv -->

model/registry/llm.yaml

@@ -57,11 +57,11 @@ groups:
         tag: llm-generic-response
       - id: prompt
         type: string
-        brief: The full prompt string sent to an LLM in a request.
-        examples: ['\\n\\nHuman:You are an AI assistant that tells jokes. Can you tell me a joke about OpenTelemetry?\\n\\nAssistant:']
+        brief: The full prompt sent to an LLM, as a stringified JSON in OpenAI's format.
+        examples: ["[{'role': 'user', 'content': 'What is the capital of France?'}]"]
         tag: llm-generic-events
       - id: completion
         type: string
-        brief: The full response string from an LLM in a response.
-        examples: ['Why did the developer stop using OpenTelemetry? Because they couldnt trace their steps!']
+        brief:  The full response received from the LLM, as a stringified JSON in OpenAI's format.
+        examples: ["[{'role': 'assistant', 'content': 'The capital of France is Paris.'}]"]
         tag: llm-generic-events