Merge branch 'master' into DOCS-1062

docs/docs/guides/evaluation/scorers.md

@@ -260,4 +260,3 @@ The following section describes how to output the standard final summarization f
 
   </TabItem>
 </Tabs>
-

docs/docs/guides/integrations/local_models.md

@@ -14,7 +14,6 @@ First and most important, is the `base_url` change during the `openai.OpenAI()`
 
 ```python
 client = openai.OpenAI(
-    api_key='fake',
     base_url="http://localhost:1234",
 )
 ```

docs/docs/guides/integrations/notdiamond.md

@@ -68,7 +68,6 @@ preference_id = train_router(
     response_column="actual",
     language="en",
     maximize=True,
-    api_key=api_key,
 )
 ```
 

docs/docs/guides/tracking/ops.md

@@ -116,6 +116,39 @@ A Weave op is a versioned function that automatically logs all calls.
   </TabItem>
 </Tabs>
 
+## Control sampling rate
+
+<Tabs groupId="programming-language">
+  <TabItem value="python" label="Python" default>
+    You can control how frequently an op's calls are traced by setting the `tracing_sample_rate` parameter in the `@weave.op` decorator. This is useful for high-frequency ops where you only need to trace a subset of calls.
+
+     Note that sampling rates are only applied to root calls. If an op has a sample rate, but is called by another op first, then that sampling rate will be ignored.
+
+    ```python
+    @weave.op(tracing_sample_rate=0.1)  # Only trace ~10% of calls
+    def high_frequency_op(x: int) -> int:
+        return x + 1
+
+    @weave.op(tracing_sample_rate=1.0)  # Always trace (default)
+    def always_traced_op(x: int) -> int:
+        return x + 1
+    ```
+
+    When an op's call is not sampled:
+    - The function executes normally
+    - No trace data is sent to Weave
+    - Child ops are also not traced for that call
+
+    The sampling rate must be between 0.0 and 1.0 inclusive.
+
+  </TabItem>
+  <TabItem value="typescript" label="TypeScript">
+    ```plaintext
+    This feature is not available in TypeScript yet. Stay tuned!
+    ```
+  </TabItem>
+</Tabs>
+
 ### Control call link output 
 
 If you want to suppress the printing of call links during logging, you can use the `WEAVE_PRINT_CALL_LINK` environment variable to `false`. This can be useful if you want to reduce  output verbosity and reduce clutter in your logs.

docs/docs/quickstart.md

@@ -50,7 +50,7 @@ _In this example, we're using openai so you will need to add an OpenAI [API key]
     import weave
     from openai import OpenAI
 
-    client = OpenAI(api_key="...")
+    client = OpenAI()
 
     # Weave will track the inputs, outputs and code of this function
     # highlight-next-line

docs/docs/tutorial-tracing_2.md

@@ -24,7 +24,7 @@ Building on our [basic tracing example](/quickstart), we will now add additional
     import json
     from openai import OpenAI
 
-    client = OpenAI(api_key="...")
+    client = OpenAI()
 
     # highlight-next-line
     @weave.op()

pyproject.toml

@@ -226,7 +226,7 @@ module = "weave_query.*"
 ignore_errors = true
 
 [tool.bumpversion]
-current_version = "0.51.24-dev0"
+current_version = "0.51.25-dev0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

tests/conftest.py

@@ -477,7 +477,9 @@ def __getattribute__(self, name):
     return ServerRecorder(server)
 
 
-def create_client(request) -> weave_init.InitializedClient:
+def create_client(
+    request, autopatch_settings: typing.Optional[autopatch.AutopatchSettings] = None
+) -> weave_init.InitializedClient:
     inited_client = None
     weave_server_flag = request.config.getoption("--weave-server")
     server: tsi.TraceServerInterface
@@ -513,7 +515,7 @@ def create_client(request) -> weave_init.InitializedClient:
             entity, project, make_server_recorder(server)
         )
         inited_client = weave_init.InitializedClient(client)
-        autopatch.autopatch()
+        autopatch.autopatch(autopatch_settings)
 
     return inited_client
 
@@ -527,19 +529,21 @@ def client(request):
         yield inited_client.client
     finally:
         inited_client.reset()
+        autopatch.reset_autopatch()
 
 
 @pytest.fixture()
 def client_creator(request):
     """This fixture is useful for delaying the creation of the client (ex. when you want to set settings first)"""
 
     @contextlib.contextmanager
-    def client():
-        inited_client = create_client(request)
+    def client(autopatch_settings: typing.Optional[autopatch.AutopatchSettings] = None):
+        inited_client = create_client(request, autopatch_settings)
         try:
             yield inited_client.client
         finally:
             inited_client.reset()
+            autopatch.reset_autopatch()
 
     yield client
 

tests/integrations/openai/cassettes/test_autopatch/test_configuration_with_dicts.yaml

@@ -0,0 +1,102 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"user","content":"tell me a joke"}],"model":"gpt-4o"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '74'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.57.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.57.2
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.0rc2
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jFJNa9wwEL37V0x1yWVd7P3KspcSSKE5thvooSlGK40tJbJGSOOSNOx/
+        L/Z+2KEp9KLDe/Me743mNQMQVostCGUkqza4/Eav1f1O/v4aVvvbL/Pdt7tVHUp1s/vsnhsx6xW0
+        f0TFZ9VHRW1wyJb8kVYRJWPvWl4vFpvNYl2UA9GSRtfLmsD5kvJ5MV/mxSYv1iehIaswiS38yAAA
+        Xoe3j+g1PostFLMz0mJKskGxvQwBiEiuR4RMySaWnsVsJBV5Rj+k/m5eQJO/YkhP6JDJJ6htYxhQ
+        KgPEBuOnB//g7w2eJ438hcAGoek4fZgaR6y7JPtevnPuhB8uSR01IdI+nfgLXltvk6kiykS+T5WY
+        ghjYQwbwc9hI96akCJHawBXTE/resCyPdmL8ggm5PJFMLN2Iz1ezd9wqjSytS5ONCiWVQT0qx/XL
+        TluaENmk899h3vM+9ra++R/7kVAKA6OuQkRt1dvC41jE/kD/NXbZ8RBYpJfE2Fa19Q3GEO3xRupQ
+        qWslC9xLJUV2yP4AAAD//wMA4O+DUSwDAAA=
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f01fe3aabd037cf-YYZ
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 11 Dec 2024 02:20:01 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=xqe_jHZdTV5LijJQYQ3GMY5MjtVrCyxbFO4glgLvgD0-1733883601-1.0.1.1-p.DDUca_cHppJu2hXzzA0CXU1mtalxHUNfBWVgPIQj.UkU603pbNscCvSIi4_Zjlz9Zuc3.hjlvoyZxcDBJTsw;
+        path=/; expires=Wed, 11-Dec-24 02:50:01 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=WEjxXqkGswaEDhllTROGX_go9tgaWNJcUJ3cCd50xDI-1733883601764-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - wandb
+      openai-processing-ms:
+      - '607'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999979'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_8592a74b531c806f65c63c7471101cb6
+    status:
+      code: 200
+      message: OK
+version: 1

tests/integrations/openai/cassettes/test_autopatch/test_disabled_integration_doesnt_patch.yaml

@@ -0,0 +1,102 @@
+interactions:
+- request:
+    body: '{"messages":[{"role":"user","content":"tell me a joke"}],"model":"gpt-4o"}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      connection:
+      - keep-alive
+      content-length:
+      - '74'
+      content-type:
+      - application/json
+      host:
+      - api.openai.com
+      user-agent:
+      - OpenAI/Python 1.57.2
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 1.57.2
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.13.0rc2
+    method: POST
+    uri: https://api.openai.com/v1/chat/completions
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//jFLJbtswEL3rK6a85GIV8lYvl6KX9NQFrYEckkKgyZHImOII5KiJEfjf
+        C8qLHDQFeuHhbXgzw5cMQFgt1iCUkaya1uWf9Hyuv5H29ebu89Pt80Z9//H0RS2nX/e3LEbJQdtH
+        VHx2vVfUtA7Zkj/SKqBkTKnjxXS6XCwWk3FPNKTRJVvdcj6jfFJMZnmxzIsPJ6MhqzCKNdxnAAAv
+        /Zsqeo3PYg3F6Iw0GKOsUawvIgARyCVEyBhtZOmPdU+kIs/o+9Y/u4AjMBjwJoIEZ2vDuUEZGDU8
+        0g6hogB76tYP/sHfmT1o8jcMcYcOmXyEKlkApTJAbDB8TMKNwbPSyN8IbBDqjuO76xoBqy7KtAXf
+        OXfCD5e5HNVtoG088Re8st5GUwaUkXyaITK1omcPGcCvfn/dq5WINlDTcsm0Q58Cx+NjnBgONpCT
+        2YlkYukGfDofvZFWamRpXbzav1BSGdSDcziW7LSlKyK7mvnvMm9lH+e2vv6f+IFQCltGXbYBtVWv
+        Bx5kAdN3/pfssuO+sIj7yNiUlfU1hjbY44+q2nKl54XSq1WxFdkh+wMAAP//AwAWTTnuWgMAAA==
+    headers:
+      CF-Cache-Status:
+      - DYNAMIC
+      CF-RAY:
+      - 8f016eadbff439d2-YYZ
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Wed, 11 Dec 2024 00:42:01 GMT
+      Server:
+      - cloudflare
+      Set-Cookie:
+      - __cf_bm=8FO1yMjc3pMQWRpWrkIe5mcs39GLeqQPmgHQq0YTT8s-1733877721-1.0.1.1-i4G06DBN08aH1F1H73U_TB9OLK3jLsV1jXydB1cQ4Hqx7I.r8xDn.7hFRZe2hy3D_nABTG1nDcdDoXL_wYiqug;
+        path=/; expires=Wed, 11-Dec-24 01:12:01 GMT; domain=.api.openai.com; HttpOnly;
+        Secure; SameSite=None
+      - _cfuvid=jxwySgtriPkUP8L2os1nb_gRq_SSUo3yWFUyJmHPmGY-1733877721989-0.0.1.1-604800000;
+        path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
+      Transfer-Encoding:
+      - chunked
+      X-Content-Type-Options:
+      - nosniff
+      access-control-expose-headers:
+      - X-Request-ID
+      alt-svc:
+      - h3=":443"; ma=86400
+      openai-organization:
+      - wandb
+      openai-processing-ms:
+      - '652'
+      openai-version:
+      - '2020-10-01'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-ratelimit-limit-requests:
+      - '10000'
+      x-ratelimit-limit-tokens:
+      - '30000000'
+      x-ratelimit-remaining-requests:
+      - '9999'
+      x-ratelimit-remaining-tokens:
+      - '29999979'
+      x-ratelimit-reset-requests:
+      - 6ms
+      x-ratelimit-reset-tokens:
+      - 0s
+      x-request-id:
+      - req_1c86d4fda2ad715edfd41bcd2f4bdd89
+    status:
+      code: 200
+      message: OK
+version: 1