LANGSMITH_API_KEY=lsv2_pt_your_api_key_here          # Required
LANGSMITH_PROJECT=your-project-name                   # Check this to know which project has traces
LANGSMITH_WORKSPACE_ID=your-workspace-id              # Optional: for org-scoped keys

pip install langsmith

npm install langsmith

curl -sSL https://raw.githubusercontent.com/langchain-ai/langsmith-cli/main/scripts/install.sh | sh

undefined

<python>
```python
import json
from pathlib import Path
from langsmith import Client

client = Client()

</python>

<typescript>
```typescript
import { Client } from "langsmith";
import { readFileSync, writeFileSync, readdirSync } from "fs";
import { join } from "path";

const client = new Client();

// 2. Process traces into dataset examples
const examples: Array<{trace_id?: string, inputs: Record<string, any>, outputs: Record<string, any>}> = [];
const files = readdirSync("./traces").filter(f => f.endsWith(".jsonl"));

for (const file of files) {
  const lines = readFileSync(join("./traces", file), "utf-8").trim().split("\n");
  const runs = lines.map(line => JSON.parse(line));
  const root = runs.find(r => r.parent_run_id == null);
  if (root?.inputs && root?.outputs) {
    examples.push({ trace_id: root.trace_id, inputs: root.inputs, outputs: root.outputs });
  }
}

// 3. Save locally
writeFileSync("/tmp/dataset.json", JSON.stringify(examples, null, 2));

undefined

undefined

</python>

<typescript>
```typescript
import { Client } from "langsmith";

const client = new Client();

// Create dataset and add examples
const dataset = await client.createDataset("My Dataset", {
  description: "Evaluation dataset",
});

await client.createExamples({
  inputs: [{ query: "What is AI?" }, { query: "Explain RAG" }],
  outputs: [{ answer: "AI is..." }, { answer: "RAG is..." }],
  datasetName: "My Dataset",
});

{"trace_id": "...", "inputs": {"query": "What are the top genres?"}, "outputs": {"response": "The top genres are..."}}

{"trace_id": "...", "inputs": {"messages": [...]}, "outputs": {"content": "..."}, "metadata": {"node_name": "model"}}

{"trace_id": "...", "inputs": {"query": "..."}, "outputs": {"expected_trajectory": ["tool_a", "tool_b", "tool_c"]}}

{"trace_id": "...", "inputs": {"question": "How do I..."}, "outputs": {"answer": "...", "retrieved_chunks": ["..."], "cited_chunks": ["..."]}}

undefined

</script_usage>

<example_workflow>
Complete workflow from traces to uploaded LangSmith dataset:

```bash

</example_workflow>

<troubleshooting>
**Dataset upload fails:**
- Verify LANGSMITH_API_KEY is set
- Check JSON file is valid: each element needs `inputs` (and optionally `outputs`)
- Dataset name must be unique, or delete existing first with `langsmith dataset delete`

**Empty dataset after upload:**
- Verify JSON file contains an array of objects with `inputs` key
- Check file isn't empty: `langsmith example list --dataset "Name"`

**Export has no data:**
- Ensure traces were exported with `--full` flag to include inputs/outputs
- Verify traces have both `inputs` and `outputs` populated

**Example count mismatch:**
- Use `langsmith dataset get "Name"` to check remote count
- Compare with local file to verify upload completeness
</troubleshooting>
</output>