LangSmithLoader integration

import getpass
import os

if not os.environ.get("LANGSMITH_API_KEY"):
    os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")

os.environ["LANGSMITH_TRACING"] = "true"

pip install -qU langchain-core

from langsmith import Client as LangSmithClient

ls_client = LangSmithClient()

dataset_name = "LangSmith Few Shot Datasets Notebook"
dataset_public_url = (
    "https://smith.langchain.com/public/55658626-124a-4223-af45-07fb774a6212/d"
)

ls_client.clone_public_dataset(dataset_public_url)

from langchain_core.document_loaders import LangSmithLoader

loader = LangSmithLoader(
    dataset_name=dataset_name,
    content_key="question",
    limit=50,
    # format_content=...,
    # ...
)

docs = loader.load()
print(docs[0].page_content)

Show me an example using Weaviate, but customizing the vectorStoreRetriever to return the top 10 k nearest neighbors.

print(docs[0].metadata["inputs"])

{'question': 'Show me an example using Weaviate, but customizing the vectorStoreRetriever to return the top 10 k nearest neighbors. '}

print(docs[0].metadata["outputs"])

{'answer': 'To customize the Weaviate client and return the top 10 k nearest neighbors, you can utilize the `as_retriever` method with the appropriate parameters. Here\'s how you can achieve this:\n\n\`\`\`python\n# Assuming you have imported the necessary modules and classes\n\n# Create the Weaviate client\nclient = weaviate.Client(url=os.environ["WEAVIATE_URL"], ...)\n\n# Initialize the Weaviate wrapper\nweaviate = Weaviate(client, index_name, text_key)\n\n# Customize the client to return top 10 k nearest neighbors using as_retriever\ncustom_retriever = weaviate.as_retriever(\n    search_type="similarity",\n    search_kwargs={\n        \'k\': 10  # Customize the value of k as needed\n    }\n)\n\n# Now you can use the custom_retriever to perform searches\nresults = custom_retriever.search(query, ...)\n\`\`\`'}

list(docs[0].metadata.keys())

['dataset_id',
 'inputs',
 'outputs',
 'metadata',
 'id',
 'created_at',
 'modified_at',
 'runs',
 'source_run_id']

page = []
for doc in loader.lazy_load():
    page.append(doc)
    if len(page) >= 10:
        # do some paged operation, e.g.
        # index.upsert(page)
        # page = []
        break
len(page)

10