Add additional LLM span attributes

.chloggen/839.yaml

@@ -0,0 +1,4 @@
+change_type: enhancement
+component: gen-ai
+note: Adding `gen_ai.request.top_k`, `gen_ai.request.presence_penalty`,  `gen_ai.request.frequency_penalty` and `gen_ai.request.stop_sequences` attributes.
+issues: [839]

docs/attributes-registry/gen-ai.md

@@ -19,6 +19,10 @@ This document defines the attributes used to describe telemetry in the context o
 | `gen_ai.request.model`           | string   | The name of the LLM a request is being made to.                                                  | `gpt-4`                                                                 | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
 | `gen_ai.request.temperature`     | double   | The temperature setting for the LLM request.                                                     | `0.0`                                                                   | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
 | `gen_ai.request.top_p`           | double   | The top_p sampling setting for the LLM request.                                                  | `1.0`                                                                   | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
+| `gen_ai.request.stop`           | string   | Up to 4 sequences where the API will stop generating further tokens.                             | `1.0`                                                                   | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
+| `gen_ai.request.top_k`           | double   | The top_k sampling setting for the LLM request.                                                  | `1.0`                                                                   | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
+| `gen_ai.request.frequency_penalty`           | double   | The frequency penalty setting for the LLM request.                                                  | `1.0`                                                                   | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
+| `gen_ai.request.presence_penalty`           | double   | The presence penalty setting for the LLM request.                                                  | `1.0`                                                                   | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
 | `gen_ai.response.finish_reasons` | string[] | Array of reasons the model stopped generating tokens, corresponding to each generation received. | `stop`                                                                  | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
 | `gen_ai.response.id`             | string   | The unique identifier for the completion.                                                        | `chatcmpl-123`                                                          | ![Experimental](https://img.shields.io/badge/-experimental-blue) |
 | `gen_ai.response.model`          | string   | The name of the LLM a response was generated from.                                               | `gpt-4-0613`                                                            | ![Experimental](https://img.shields.io/badge/-experimental-blue) |

model/registry/gen-ai.yaml

@@ -45,6 +45,26 @@ groups:
         brief: The top_p sampling setting for the LLM request.
         examples: [1.0]
         tag: llm-generic-request
+      - id: request.top_k
+        stability: experimental
+        type: double
+        brief: The top_k sampling setting for the LLM request.
+        examples: [1.0]
+      - id: request.stop_sequences
+        stability: experimental
+        type: string[]
+        brief: The stop sequences provided in the request.
+        examples: ['\n']
+      - id: request.frequency_penalty
+        stability: experimental
+        type: double
+        brief: The frequency penalty to provide.
+        examples: ['0.1']
+      - id: request.presence_penalty
+        stability: experimental
+        type: double
+        brief: The presence penalty to provide.
+        examples: ['0.1']
       - id: response.id
         stability: experimental
         type: string

model/trace/gen-ai.yaml

@@ -23,6 +23,14 @@ groups:
         requirement_level: recommended
       - ref: gen_ai.request.top_p
         requirement_level: recommended
+      - ref: gen_ai.request.top_k
+        requirement_level: recommended
+      - ref: gen_ai.request.stop
+        requirement_level: recommended
+      - ref: gen_ai.request.frequncy_penalty
+        requirement_level: recommended
+      - ref: gen_ai.request.presence_penalty
+        requirement_level: recommended
       - ref: gen_ai.response.id
         requirement_level: recommended
       - ref: gen_ai.response.model