elastic-opentelemetry-instrumentation-openai: formats test yaml same as upstream (#30)

Co-authored-by: Adrian Cole <[email protected]>

Author: xrmx

instrumentation/elastic-opentelemetry-instrumentation-openai/README.md

@@ -96,27 +96,38 @@ Integration tests default to using ollama, to avoid cost and leaking sensitive i
 However, unit test recordings should use the authoritative OpenAI platform unless the test is
 about a specific portability corner case.
 
-To refresh a test, delete its cassette file in tests/cassettes and make sure you have the
-following environment variables set for OpenAI recordings:
+To refresh a test, delete its cassette file in tests/cassettes and make sure you have environment
+variables set for recordings, detailed later.
+
+If writing a new test, start with the test logic with no assertions. If extending an existing unit test
+rather than writing a new one, remove the corresponding recorded response from [cassettes](./tests/cassettes/)
+instead.
+
+Then, run `pytest` as normal. It will execute a request against the LLM and record it. Update the
+test with correct assertions until it passes. Following executions of `pytest` will use the recorded
+response without querying the LLM.
+
+### OpenAI Environment Variables
 
 * `OPENAI_API_KEY` - from https://platform.openai.com/settings/profile?tab=api-keys
   * It should look like `sk-...` 
 
-and the following for Azure recordings, deployment url and api key are available for each deployment
-in https://oai.azure.com/resource/deployments:
+### Azure OpenAI Environment Variables
+
+Azure is different from OpenAI primarily in that a URL has an implicit model. This means it ignores
+the model parameter set by the OpenAI SDK. The implication is that one endpoint cannot serve both
+chat and embeddings at the same time. Hence, we need separate environment variables for chat and
+embeddings. In either case, the `DEPLOYMENT_URL` is the "Endpoint Target URI" and the `API_KEY` is
+the `Endpoint Key` for a corresponding deployment in https://oai.azure.com/resource/deployments
 
 * `AZURE_CHAT_COMPLETIONS_DEPLOYMENT_URL`
+  * It should look like https://endpoint.com/openai/deployments/my-deployment/chat/completions?api-version=2023-05-15
 * `AZURE_CHAT_COMPLETIONS_API_KEY`
+  * It should be in hex like `abc01...` and possibly the same as `AZURE_EMBEDDINGS_API_KEY`
 * `AZURE_EMBEDDINGS_DEPLOYMENT_URL`
+  * It should look like https://endpoint.com/openai/deployments/my-deployment/embeddings?api-version=2023-05-15
 * `AZURE_EMBEDDINGS_API_KEY`
-
-If writing a new test, start with the test logic with no assertions. If extending an existing unit test
-rather than writing a new one, remove the corresponding recorded response from [cassettes](./tests/cassettes/)
-instead.
-
-Then, run `pytest` as normal. It will execute a request against the LLM and record it. Update the
-test with correct assertions until it passes. Following executions of `pytest` will use the recorded
-response without querying the LLM.
+  * It should be in hex like `abc01...` and possibly the same as `AZURE_CHAT_COMPLETIONS_API_KEY`
 
 ## License
 

instrumentation/elastic-opentelemetry-instrumentation-openai/tests/cassettes/.test_chat_completions/test_all_the_client_options[azure_provider_chat_completions].yaml

@@ -1,9 +1,21 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "user", "content": "Answer in up to 3 words: Which
-      ocean contains the falkland islands?"}], "model": "gpt-4o-mini", "frequency_penalty":
-      0, "max_tokens": 100, "presence_penalty": 0, "stop": "foo", "temperature": 1,
-      "top_p": 1}'
+    body: |-
+      {
+        "messages": [
+          {
+            "role": "user",
+            "content": "Answer in up to 3 words: Which ocean contains the falkland islands?"
+          }
+        ],
+        "model": "unused",
+        "frequency_penalty": 0,
+        "max_tokens": 100,
+        "presence_penalty": 0,
+        "stop": "foo",
+        "temperature": 1,
+        "top_p": 1
+      }
     headers:
       accept:
       - application/json
@@ -16,70 +28,133 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '249'
+      - '244'
       content-type:
       - application/json
       host:
       - test.openai.azure.com
       user-agent:
-      - AzureOpenAI/Python 1.50.0
+      - AzureOpenAI/Python 1.54.3
       x-stainless-arch:
-      - x64
+      - arm64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - Linux
+      - MacOS
       x-stainless-package-version:
-      - 1.50.0
+      - 1.54.3
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.10.12
+      - 3.12.6
     method: POST
-    uri: https://test.openai.azure.com/openai/deployments/test-azure-deployment/chat/completions?api-version=2023-03-15-preview
+    uri: https://test.openai.azure.com/openai/deployments/test-azure-deployment/chat/completions?api-version=2024-08-01-preview
   response:
     body:
-      string: '{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"South
-        Atlantic Ocean.","role":"assistant"}}],"created":1727962531,"id":"chatcmpl-AEGHLLqYkgJxUgLgX8RCLeL85irQR","model":"gpt-4o-mini","object":"chat.completion","system_fingerprint":"fp_878413d04d","usage":{"completion_tokens":4,"prompt_tokens":24,"total_tokens":28}}
-
-        '
+      string: |-
+        {
+          "choices": [
+            {
+              "content_filter_results": {
+                "hate": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "self_harm": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "sexual": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "violence": {
+                  "filtered": false,
+                  "severity": "safe"
+                }
+              },
+              "finish_reason": "stop",
+              "index": 0,
+              "logprobs": null,
+              "message": {
+                "content": "Atlantic Ocean",
+                "role": "assistant"
+              }
+            }
+          ],
+          "created": 1731466203,
+          "id": "chatcmpl-ASxkBZGOa53uXX1Ciygl77IrF8PbB",
+          "model": "gpt-4-32k",
+          "object": "chat.completion",
+          "prompt_filter_results": [
+            {
+              "prompt_index": 0,
+              "content_filter_results": {
+                "hate": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "self_harm": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "sexual": {
+                  "filtered": false,
+                  "severity": "safe"
+                },
+                "violence": {
+                  "filtered": false,
+                  "severity": "safe"
+                }
+              }
+            }
+          ],
+          "system_fingerprint": null,
+          "usage": {
+            "completion_tokens": 2,
+            "prompt_tokens": 24,
+            "total_tokens": 26
+          }
+        }
     headers:
+      Cache-Control:
+      - no-cache, must-revalidate
       Content-Length:
-      - '336'
+      - '805'
       Content-Type:
       - application/json
       Date:
-      - Thu, 03 Oct 2024 13:35:31 GMT
+      - Wed, 13 Nov 2024 02:50:02 GMT
       Set-Cookie: test_set_cookie
       Strict-Transport-Security:
       - max-age=31536000; includeSubDomains; preload
+      access-control-allow-origin:
+      - '*'
       apim-request-id:
-      - c017b850-54f6-40dd-9505-d1a9ee9a45b5
+      - f0e5ae5b-b609-4908-bedb-533ec71e9bfa
       azureml-model-session:
-      - d009-20240925074800
-      openai-organization: test_openai_org_key
+      - d156-20241010120317
+      openai-organization: test_openai_org_id
       x-accel-buffering:
       - 'no'
       x-content-type-options:
       - nosniff
-      x-envoy-upstream-service-time:
-      - '249'
       x-ms-client-request-id:
-      - c017b850-54f6-40dd-9505-d1a9ee9a45b5
+      - f0e5ae5b-b609-4908-bedb-533ec71e9bfa
       x-ms-rai-invoked:
       - 'true'
       x-ms-region:
-      - East US
+      - Switzerland North
       x-ratelimit-remaining-requests:
-      - '909'
+      - '78'
       x-ratelimit-remaining-tokens:
-      - '90883'
+      - '79884'
       x-request-id:
-      - fba991b8-1a4f-4c6e-8a53-8b826a61a78a
+      - 3a1ee803-cce9-472f-ad04-2d0757009288
     status:
       code: 200
       message: OK

instrumentation/elastic-opentelemetry-instrumentation-openai/tests/cassettes/.test_chat_completions/test_all_the_client_options[ollama_provider_chat_completions].yaml

@@ -1,9 +1,21 @@
 interactions:
 - request:
-    body: '{"messages": [{"role": "user", "content": "Answer in up to 3 words: Which
-      ocean contains the falkland islands?"}], "model": "qwen2.5:0.5b", "frequency_penalty":
-      0, "max_completion_tokens": 100, "presence_penalty": 0, "stop": "foo", "temperature":
-      1, "top_p": 1}'
+    body: |-
+      {
+        "messages": [
+          {
+            "role": "user",
+            "content": "Answer in up to 3 words: Which ocean contains the falkland islands?"
+          }
+        ],
+        "model": "qwen2.5:0.5b",
+        "frequency_penalty": 0,
+        "max_tokens": 100,
+        "presence_penalty": 0,
+        "stop": "foo",
+        "temperature": 1,
+        "top_p": 1
+      }
     headers:
       accept:
       - application/json
@@ -14,44 +26,63 @@ interactions:
       connection:
       - keep-alive
       content-length:
-      - '261'
+      - '250'
       content-type:
       - application/json
       host:
       - localhost:11434
       user-agent:
-      - OpenAI/Python 1.50.0
+      - OpenAI/Python 1.50.2
       x-stainless-arch:
-      - x64
+      - arm64
       x-stainless-async:
       - 'false'
       x-stainless-lang:
       - python
       x-stainless-os:
-      - Linux
+      - MacOS
       x-stainless-package-version:
-      - 1.50.0
+      - 1.50.2
       x-stainless-retry-count:
       - '0'
       x-stainless-runtime:
       - CPython
       x-stainless-runtime-version:
-      - 3.10.12
+      - 3.12.6
     method: POST
     uri: http://localhost:11434/v1/chat/completions
   response:
     body:
-      string: '{"id":"chatcmpl-398","object":"chat.completion","created":1727962341,"model":"qwen2.5:0.5b","system_fingerprint":"fp_ollama","choices":[{"index":0,"message":{"role":"assistant","content":"The
-        Great British Oceanic Peninsula."},"finish_reason":"stop"}],"usage":{"prompt_tokens":46,"completion_tokens":8,"total_tokens":54}}
-
-        '
+      string: |-
+        {
+          "id": "chatcmpl-46",
+          "object": "chat.completion",
+          "created": 1731311779,
+          "model": "qwen2.5:0.5b",
+          "system_fingerprint": "fp_ollama",
+          "choices": [
+            {
+              "index": 0,
+              "message": {
+                "role": "assistant",
+                "content": "The Falklands Islands are located in Atlantic Oceans."
+              },
+              "finish_reason": "stop"
+            }
+          ],
+          "usage": {
+            "prompt_tokens": 46,
+            "completion_tokens": 12,
+            "total_tokens": 58
+          }
+        }
     headers:
       Content-Length:
-      - '322'
+      - '339'
       Content-Type:
       - application/json
       Date:
-      - Thu, 03 Oct 2024 13:32:21 GMT
+      - Mon, 11 Nov 2024 07:56:19 GMT
       Set-Cookie: test_set_cookie
       openai-organization: test_openai_org_key
     status: