🔄 Sync code examples from docs-code-eval

models/ref/sdk-coding-cheat-sheet.mdx

@@ -12,9 +12,6 @@ Select a card to view code examples in that category.
   <Card title="Runs" href="/models/ref/sdk-coding-cheat-sheet/runs">
     Code examples to initialize, manage, and fork W&B runs
   </Card>
-  <Card title="Sweeps" href="/models/ref/sdk-coding-cheat-sheet/sweeps">
-    Code examples to configure, create, and run hyperparameter sweeps with W&B
-  </Card>
   <Card title="Logging" href="/models/ref/sdk-coding-cheat-sheet/logging">
     Code examples to log metrics, hyperparameters, tables, and custom data to W&B
   </Card>

models/ref/sdk-coding-cheat-sheet/artifacts.mdx

@@ -75,3 +75,4 @@ Create, update, download, and manage W&B Artifacts for data versioning.
 ## Given an existing artifact, update its description, metadata, and aliases without creating a new run
 
 <ArtifactUpdateExisting />
+

models/ref/sdk-coding-cheat-sheet/logging.mdx

@@ -60,3 +60,4 @@ Log metrics, hyperparameters, tables, and custom data to W&B.
 ## Log a table
 
 <LogTable />
+

models/ref/sdk-coding-cheat-sheet/registry.mdx

@@ -45,3 +45,4 @@ Work with W&B Model Registry to organize and manage model versions.
 ## Remove a tag from a collection in a registry
 
 <RegistryCollectionTagsRemove />
+

models/ref/sdk-coding-cheat-sheet/runs.mdx

@@ -55,3 +55,4 @@ Initialize and manage W&B runs to organize your experiments and track your work.
 ## Add one or more tags to previously saved runs
 
 <RunsUpdateTagPublicApi />
+

snippets/CodeSnippet.jsx

@@ -12,7 +12,6 @@
  * AUTO-GENERATED: Do not edit manually. Run sync_code_examples.sh to regenerate.
  */
 
-
 // Import all MDX-wrapped code examples
 import ArtifactAddAlias from '/snippets/_includes/code-examples/artifact_add_alias.mdx';
 import ArtifactAddAliasExisting from '/snippets/_includes/code-examples/artifact_add_alias_existing.mdx';
@@ -61,6 +60,13 @@ import SweepConfig from '/snippets/_includes/code-examples/sweep_config.mdx';
 import SweepCreate from '/snippets/_includes/code-examples/sweep_create.mdx';
 import SweepInitialize from '/snippets/_includes/code-examples/sweep_initialize.mdx';
 import SweepStart from '/snippets/_includes/code-examples/sweep_start.mdx';
+import WeaveEvalBasic from '/snippets/_includes/code-examples/weave_eval_basic.mdx';
+import WeaveExportMetrics from '/snippets/_includes/code-examples/weave_export_metrics.mdx';
+import WeavePublishDataset from '/snippets/_includes/code-examples/weave_publish_dataset.mdx';
+import WeaveScoringFunction from '/snippets/_includes/code-examples/weave_scoring_function.mdx';
+import WeaveTraceCall from '/snippets/_includes/code-examples/weave_trace_call.mdx';
+import WeaveTraceImages from '/snippets/_includes/code-examples/weave_trace_images.mdx';
+import WeaveTraceOp from '/snippets/_includes/code-examples/weave_trace_op.mdx';
 
 // Map filenames to imported content
 const snippets = {
@@ -111,19 +117,26 @@ const snippets = {
   'sweep_create.py': SweepCreate,
   'sweep_initialize.py': SweepInitialize,
   'sweep_start.py': SweepStart,
+  'weave_eval_basic.py': WeaveEvalBasic,
+  'weave_export_metrics.py': WeaveExportMetrics,
+  'weave_publish_dataset.py': WeavePublishDataset,
+  'weave_scoring_function.py': WeaveScoringFunction,
+  'weave_trace_call.py': WeaveTraceCall,
+  'weave_trace_images.py': WeaveTraceImages,
+  'weave_trace_op.py': WeaveTraceOp,
 };
 
 export const CodeSnippet = ({ file }) => {
   const Component = snippets[file];
-
+  
   if (!Component) {
     return (
       <div style={{ padding: '1rem', background: '#fee', border: '1px solid #fcc', borderRadius: '4px' }}>
         <p style={{ margin: 0, color: '#c00' }}>Code snippet not found: {file}</p>
       </div>
     );
   }
-
+  
   return <Component />;
 };
 

snippets/_includes/code-examples/weave_eval_basic.mdx

@@ -0,0 +1,71 @@
+```python
+'''
+Create a basic Weave evaluation pipeline for scoring responses from a model.
+'''
+import json
+import asyncio
+import openai
+import weave
+from weave.scorers import MultiTaskBinaryClassificationF1
+
+# Initialize Weave once
+weave.init('your-team-name/your-project-name')
+
+# Define Model
+class ExtractFruitsModel(weave.Model):
+    model_name: str
+    prompt_template: str
+
+    @weave.op()
+    async def predict(self, sentence: str) -> dict:
+        client = openai.AsyncClient()
+        response = await client.chat.completions.create(
+            model=self.model_name,
+            messages=[{"role": "user", "content": self.prompt_template.format(sentence=sentence)}],
+        )
+        result = response.choices[0].message.content
+        if result is None:
+            raise ValueError("No response from model")
+        return json.loads(result)
+
+# Instantiate model
+model = ExtractFruitsModel(
+    model_name='gpt-3.5-turbo-1106',
+    prompt_template='Extract fields ("fruit": <str>, "color": <str>, "flavor": <str>) from the following text, as json: {sentence}'
+)
+
+# Create and publish dataset
+sentences = ["There are many fruits that were found on the recently discovered planet Goocrux. There are neoskizzles that grow there, which are purple and taste like candy.",
+"Pounits are a bright green color and are more savory than sweet.",
+"Finally, there are fruits called glowls, which have a very sour and bitter taste which is acidic and caustic, and a pale orange tinge to them."]
+labels = [
+    {'fruit': 'neoskizzles', 'color': 'purple', 'flavor': 'candy'},
+    {'fruit': 'pounits', 'color': 'bright green', 'flavor': 'savory'},
+    {'fruit': 'glowls', 'color': 'pale orange', 'flavor': 'sour and bitter'}
+]
+examples = [
+    {'id': '0', 'sentence': sentences[0], 'target': labels[0]},
+    {'id': '1', 'sentence': sentences[1], 'target': labels[1]},
+    {'id': '2', 'sentence': sentences[2], 'target': labels[2]}
+]
+
+dataset = weave.Dataset(name='fruits', rows=examples)
+weave.publish(dataset)
+
+# Define a scoring function
+@weave.op()
+def fruit_name_score(target: dict, output: dict) -> dict:
+    return {'correct': target['fruit'] == output['fruit']}
+
+# Run the evaluation
+evaluation = weave.Evaluation(
+    name='fruit_eval',
+    dataset=dataset,
+    scorers=[
+        MultiTaskBinaryClassificationF1(class_names=["fruit", "color", "flavor"]),
+        fruit_name_score
+    ],
+)
+
+print(asyncio.run(evaluation.evaluate(model)))
+```

snippets/_includes/code-examples/weave_eval_basic.py

@@ -0,0 +1,69 @@
+'''
+Create a basic Weave evaluation pipeline for scoring responses from a model.
+'''
+import json
+import asyncio
+import openai
+import weave
+from weave.scorers import MultiTaskBinaryClassificationF1
+
+# Initialize Weave once
+weave.init('your-team-name/your-project-name')
+
+# Define Model
+class ExtractFruitsModel(weave.Model):
+    model_name: str
+    prompt_template: str
+
+    @weave.op()
+    async def predict(self, sentence: str) -> dict:
+        client = openai.AsyncClient()
+        response = await client.chat.completions.create(
+            model=self.model_name,
+            messages=[{"role": "user", "content": self.prompt_template.format(sentence=sentence)}],
+        )
+        result = response.choices[0].message.content
+        if result is None:
+            raise ValueError("No response from model")
+        return json.loads(result)
+
+# Instantiate model
+model = ExtractFruitsModel(
+    model_name='gpt-3.5-turbo-1106',
+    prompt_template='Extract fields ("fruit": <str>, "color": <str>, "flavor": <str>) from the following text, as json: {sentence}'
+)
+
+# Create and publish dataset
+sentences = ["There are many fruits that were found on the recently discovered planet Goocrux. There are neoskizzles that grow there, which are purple and taste like candy.",
+"Pounits are a bright green color and are more savory than sweet.",
+"Finally, there are fruits called glowls, which have a very sour and bitter taste which is acidic and caustic, and a pale orange tinge to them."]
+labels = [
+    {'fruit': 'neoskizzles', 'color': 'purple', 'flavor': 'candy'},
+    {'fruit': 'pounits', 'color': 'bright green', 'flavor': 'savory'},
+    {'fruit': 'glowls', 'color': 'pale orange', 'flavor': 'sour and bitter'}
+]
+examples = [
+    {'id': '0', 'sentence': sentences[0], 'target': labels[0]},
+    {'id': '1', 'sentence': sentences[1], 'target': labels[1]},
+    {'id': '2', 'sentence': sentences[2], 'target': labels[2]}
+]
+
+dataset = weave.Dataset(name='fruits', rows=examples)
+weave.publish(dataset)
+
+# Define a scoring function
+@weave.op()
+def fruit_name_score(target: dict, output: dict) -> dict:
+    return {'correct': target['fruit'] == output['fruit']}
+
+# Run the evaluation
+evaluation = weave.Evaluation(
+    name='fruit_eval',
+    dataset=dataset,
+    scorers=[
+        MultiTaskBinaryClassificationF1(class_names=["fruit", "color", "flavor"]),
+        fruit_name_score
+    ],
+)
+
+print(asyncio.run(evaluation.evaluate(model)))

snippets/_includes/code-examples/weave_export_metrics.mdx

@@ -0,0 +1,42 @@
+```python
+'''
+Retrieve metrics about your calls
+'''
+
+import requests
+import json
+import os
+
+# Weave API URL
+url = "https://trace.wandb.ai/calls/stats"
+
+# Configure the types of metrics to retrieve for a specified time range
+payload = {
+    "project_id": "<your-team-name/your-project-name>",
+# Specify time range
+    "start": "2026-03-01T00:00:00Z",
+    "end": "2026-03-10T00:00:00Z",
+# Specify the size of the buckets, in seconds.
+    "granularity": 86400,
+    "filter": {
+        "trace_roots_only": True,
+        "op_names": ["web_app"]
+    },
+# Specify metrics and their aggregate function
+    "usage_metrics": [
+        {"metric": "total_tokens", "aggregations": ["sum"]},
+        {"metric": "total_cost", "aggregations": ["sum"]}
+    ],
+    "call_metrics": [
+        {"metric": "call_count", "aggregations": ["sum"]},
+        {"metric": "error_count", "aggregations": ["sum"]},
+        {"metric": "latency_ms", "aggregations": ["avg", "min", "max"], "percentiles": [50, 95, 99]}
+    ]
+}
+
+API_KEY = os.getenv("WANDB_API_KEY")
+
+response = requests.post(url, json=payload, auth=("api", API_KEY))
+
+print(json.dumps(response.json(), indent=2))
+```

snippets/_includes/code-examples/weave_export_metrics.py

@@ -0,0 +1,40 @@
+'''
+Retrieve metrics about your calls
+'''
+
+import requests
+import json
+import os
+
+# Weave API URL
+url = "https://trace.wandb.ai/calls/stats"
+
+# Configure the types of metrics to retrieve for a specified time range
+payload = {
+    "project_id": "<your-team-name/your-project-name>",
+# Specify time range
+    "start": "2026-03-01T00:00:00Z",
+    "end": "2026-03-10T00:00:00Z",
+# Specify the size of the buckets, in seconds.
+    "granularity": 86400,
+    "filter": {
+        "trace_roots_only": True,
+        "op_names": ["web_app"]
+    },
+# Specify metrics and their aggregate function
+    "usage_metrics": [
+        {"metric": "total_tokens", "aggregations": ["sum"]},
+        {"metric": "total_cost", "aggregations": ["sum"]}
+    ],
+    "call_metrics": [
+        {"metric": "call_count", "aggregations": ["sum"]},
+        {"metric": "error_count", "aggregations": ["sum"]},
+        {"metric": "latency_ms", "aggregations": ["avg", "min", "max"], "percentiles": [50, 95, 99]}
+    ]
+}
+
+API_KEY = os.getenv("WANDB_API_KEY")
+
+response = requests.post(url, json=payload, auth=("api", API_KEY))
+
+print(json.dumps(response.json(), indent=2))

snippets/_includes/code-examples/weave_publish_dataset.mdx

@@ -0,0 +1,29 @@
+```python
+'''
+Publish a dataset to Weave
+'''
+
+import weave
+from weave import Dataset
+# Initialize Weave
+weave.init('<your-team-name>/<your-project-name>')
+
+# Create a dataset
+dataset = Dataset(
+    name='grammar',
+    rows=[
+        {'id': '0', 'sentence': "He no likes ice cream.", 'correction': "He doesn't like ice cream."},
+        {'id': '1', 'sentence': "She goed to the store.", 'correction': "She went to the store."},
+        {'id': '2', 'sentence': "They plays video games all day.", 'correction': "They play video games all day."}
+    ]
+)
+
+# Publish the dataset
+weave.publish(dataset)
+
+# Retrieve the dataset
+dataset_ref = weave.ref('grammar').get()
+
+# Access a specific example in the dataset
+example_label = dataset_ref.rows[2]['sentence']
+```

snippets/_includes/code-examples/weave_publish_dataset.py

@@ -0,0 +1,27 @@
+'''
+Publish a dataset to Weave
+'''
+
+import weave
+from weave import Dataset
+# Initialize Weave
+weave.init('<your-team-name>/<your-project-name>')
+
+# Create a dataset
+dataset = Dataset(
+    name='grammar',
+    rows=[
+        {'id': '0', 'sentence': "He no likes ice cream.", 'correction': "He doesn't like ice cream."},
+        {'id': '1', 'sentence': "She goed to the store.", 'correction': "She went to the store."},
+        {'id': '2', 'sentence': "They plays video games all day.", 'correction': "They play video games all day."}
+    ]
+)
+
+# Publish the dataset
+weave.publish(dataset)
+
+# Retrieve the dataset
+dataset_ref = weave.ref('grammar').get()
+
+# Access a specific example in the dataset
+example_label = dataset_ref.rows[2]['sentence']

snippets/_includes/code-examples/weave_scoring_function.mdx

@@ -0,0 +1,20 @@
+```python
+'''
+Define custom scoring function
+'''
+
+import weave
+
+# Collect your examples
+examples = [
+    {"question": "What is the capital of France?", "expected": "Paris"},
+    {"question": "Who wrote 'To Kill a Mockingbird'?", "expected": "Harper Lee"},
+    {"question": "What is the square root of 64?", "expected": "8"},
+]
+
+# Define any custom scoring function
+@weave.op()
+def match_score1(expected: str, output: dict) -> dict:
+    # Define the logic to score the output
+    return {'match': expected == output['generated_text']}
+```