Pinecone cloud vector store in LangChain - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to initialize the Pinecone client with your API key.

LangChain

import pinecone
pinecone.init(api_key=[1])

Drag options to blanks, or click blank then click option'

Aapi_key

B"your-api-key"

C12345

Dpinecone_key

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the API key without quotes

Using a variable name instead of the key string

You must pass your Pinecone API key as a string to pinecone.init() to authenticate.

2fill in blank

medium

Complete the code to create a Pinecone index named 'example-index' with dimension 128.

LangChain

pinecone.create_index(name=[1], dimension=128)

Drag options to blanks, or click blank then click option'

A"example-index"

B"myindex"

Cexample_index

D'index128'

Attempts:

3 left

💡 Hint

Common Mistakes

Using variable names without quotes

Wrong index name string

The index name must be a string matching the desired name, here "example-index".

3fill in blank

hard

Fix the error in the code to connect to an existing Pinecone index named 'example-index'.

LangChain

index = pinecone.Index([1])

Drag options to blanks, or click blank then click option'

Aexample-index

B'index-example'

C"example-index"

Dindex_name

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the name without quotes

Using a wrong index name string

The index name must be passed as a string with quotes to pinecone.Index().

4fill in blank

hard

Fill both blanks to upsert vectors into the Pinecone index.

LangChain

vectors = [("id1", [0.1, 0.2, 0.3], [1])]
index.upsert(vectors=[2])

Drag options to blanks, or click blank then click option'

Ametadata

Bvectors

C['meta']

Ddata

Attempts:

3 left

💡 Hint

Common Mistakes

Passing wrong variable names

Using list literals instead of variable names

The tuple for vectors can include metadata as the third element, and the upsert method takes the list named vectors.

5fill in blank

hard

Fill all three blanks to query the Pinecone index for top 3 matches with a vector.

LangChain

query_response = index.query(
  vector=[1],
  top_k=[2],
  include_metadata=[3]
)

Drag options to blanks, or click blank then click option'

A[0.1, 0.2, 0.3]

B3

CTrue

DFalse

Attempts:

3 left

💡 Hint

Common Mistakes

Passing vector as a string

Wrong top_k number

Forgetting to include metadata

To query, pass the query vector as a list, set top_k to 3 for top 3 results, and include_metadata to True to get metadata in results.