LogoLogo
API ReferenceGitHubSlackService StatusLogin
v3.8.16
v3.8.16
  • Deep Lake Docs
  • Vector Store Quickstart
  • Deep Learning Quickstart
  • Storage & Credentials
    • Storage Options
    • User Authentication
    • Storing Deep Lake Data in Your Own Cloud
      • Microsoft Azure
        • Provisioning Federated Credentials
        • Enabling CORS
      • Amazon Web Services
        • Provisioning Role-Based Access
        • Enabling CORS
  • List of ML Datasets
  • 🏢High-Performance Features
    • Introduction
    • Performant Dataloader
    • Tensor Query Language (TQL)
      • TQL Syntax
      • Sampling Datasets
    • Deep Memory
      • How it Works
    • Index for ANN Search
      • Caching and Optimization
    • Managed Tensor Database
      • REST API
      • Migrating Datasets to the Tensor Database
  • 📚EXAMPLE CODE
    • Getting Started
      • Vector Store
        • Step 1: Hello World
        • Step 2: Creating Deep Lake Vector Stores
        • Step 3: Performing Search in Vector Stores
        • Step 4: Customizing Vector Stores
      • Deep Learning
        • Step 1: Hello World
        • Step 2: Creating Deep Lake Datasets
        • Step 3: Understanding Compression
        • Step 4: Accessing and Updating Data
        • Step 5: Visualizing Datasets
        • Step 6: Using Activeloop Storage
        • Step 7: Connecting Deep Lake Datasets to ML Frameworks
        • Step 8: Parallel Computing
        • Step 9: Dataset Version Control
        • Step 10: Dataset Filtering
    • Tutorials (w Colab)
      • Vector Store Tutorials
        • Vector Search Options
          • Deep Lake Vector Store API
          • REST API
          • LangChain API
        • Image Similarity Search
        • Deep Lake Vector Store in LangChain
        • Deep Lake Vector Store in LlamaIndex
        • Improving Search Accuracy using Deep Memory
      • Deep Learning Tutorials
        • Creating Datasets
          • Creating Complex Datasets
          • Creating Object Detection Datasets
          • Creating Time-Series Datasets
          • Creating Datasets with Sequences
          • Creating Video Datasets
        • Training Models
          • Splitting Datasets for Training
          • Training an Image Classification Model in PyTorch
          • Training Models Using MMDetection
          • Training Models Using PyTorch Lightning
          • Training on AWS SageMaker
          • Training an Object Detection and Segmentation Model in PyTorch
        • Updating Datasets
        • Data Processing Using Parallel Computing
      • Concurrent Writes
        • Concurrency Using Zookeeper Locks
    • Playbooks
      • Querying, Training and Editing Datasets with Data Lineage
      • Evaluating Model Performance
      • Training Reproducibility Using Deep Lake and Weights & Biases
      • Working with Videos
    • Low-Level API Summary
  • 🔬Technical Details
    • Best Practices
      • Creating Datasets at Scale
      • Training Models at Scale
      • Storage Synchronization and "with" Context
      • Restoring Corrupted Datasets
      • Concurrent Writes
    • Data Layout
    • Version Control and Querying
    • Dataset Visualization
    • Tensor Relationships
    • Visualizer Integration
    • Shuffling in dataloaders
    • How to Contribute
Powered by GitBook
On this page
  • Search Options for Deep Lake Vector Stores in the Deep Lake API
  • Vector Search on the Client
  • Vector Search Using the Managed Tensor Database (Server-Side)

Was this helpful?

  1. EXAMPLE CODE
  2. Tutorials (w Colab)
  3. Vector Store Tutorials
  4. Vector Search Options

Deep Lake Vector Store API

Running Vector Search in the Deep Lake Vector Store module.

Search Options for Deep Lake Vector Stores in the Deep Lake API

This tutorial requires installation of:

!pip3 install "deeplake[enterprise]" langchain openai tiktoken

Vector Search on the Client

Let's load the same vector store used in the Quickstart and run embeddings search based on a user prompt using the Deep Lake Vector Store module. (Note: DeepLakeVectorStore class is deprecated, but you can still use it. The new API for calling Deep Lake's Vector Store is: VectorStore)

from deeplake.core.vectorstore import VectorStore
import openai
import os

os.environ['OPENAI_API_KEY'] = <OPENAI_API_KEY>

vector_store_path = 'hub://activeloop/paul_graham_essay'

vector_store = VectorStore(
    path = vector_store_path,
    read_only = True
)

Next, let's define an embedding function using OpenAI. It must work for a single string and a list of strings so that it can be used to embed a prompt and a batch of texts.

def embedding_function(texts, model = "text-embedding-ada-002"):
   
   if isinstance(texts, str):
       texts = [texts]

   texts = [t.replace("\n", " ") for t in texts]
   return [data['embedding']for data in openai.Embedding.create(input = texts, model=model)['data']]

Simple Vector Search

Let's run a simple vector search using default options, which performs a simple cosine similarity search in Python on the client.

prompt = "What are the first programs he tried writing?"

search_results = vector_store.search(embedding_data=prompt, 
                                     embedding_function=embedding_function)

The search_results is a dictionary with keys for the text, score, id, and metadata, with data ordered by score. By default, it returns 4 samples ordered by similarity score, and if we examine the first returned text, it appears to contain the text about trust and safety models that is relevant to the prompt.

search_results['text'][0]

Returns:

What I Worked On

February 2021

Before college the two main things I worked on, outside of school, were writing and programming. I didn't write essays. I wrote what beginning writers were supposed to write then, and probably still are: short stories. My stories were awful. They had hardly any plot, just characters with strong feelings, which I imagined made them deep.

The first programs I tried writing were on the IBM 1401 that our school district used for what was then called "data processing." This was in 9th grade, so I was 13 or 14. The school district's 1401 happened to be in the basement of our junior high school, and my friend Rich Draves and I got permission to use it. It was like a mini Bond villain's lair down there, with all these alien-looking machines — CPU, disk drives, printer, card reader — sitting up on a raised floor under bright fluorescent lights.

Filter Search Using UDFs

def filter_fn(x):
    # x is a single row in Deep Lake, 'text' is the tensor name, .data()['value'] is the method for fetching the data
    return "program" in x['text'].data()['value'].lower()

Let's run the vector search with the filter above, and return more samples (k = 10), and perform similarity search using L2 metric (distance_metric = "l2"):

prompt = "What are the first programs he tried writing?"

search_results_filter = vector_store.search(embedding_data = prompt, 
                                            embedding_function = embedding_function,
                                            filter = filter_fn,
                                            k = 10,
                                            distance_metric = 'l2',
                                            exec_option = "python")

We can verity that the word "program" is present in all of the results:

all(["program" in result for result in search_results_filter["text"]])

# Returns True

UDFs are only supported with query execution using the Python engine, so in the search above, exec_option = "python" should be specified.

Filter Search Using Metadata Filters

Instead of using UDFs, a filter can be specified using dictionary syntax. For json tensors, the syntax is filter = {"tensor_name": {"key": "value"}}. For text tensors, it is filter = {"tensor": "value"}. In all cases, an exact match is performed.

search_results_filter = vector_store.search(embedding_data = prompt, 
                                            embedding_function = embedding_function,
                                            filter = {"metadata": {"source": "paul_graham_essay.txt"}})

Filter Search using TQL

Let's load a larger Vector Store for running more interesting queries:

vector_store_path = "hub://activeloop/twitter-algorithm"

vector_store = VectorStore(
    path = vector_store_path,
    read_only = True
)

NOTE: this Vector Store is stored in us-east, and query performance may vary significantly depending on your location. In real-world use-cases, users would store their Vector Stores in regions optimized for their use case.

We are interested in answering a prompt based on the question:

prompt = "What does the python code do?"

Therefore, we apply a filter to only search for text that contains the word "python" and metadata where the source key contains ".py".

embedding = embedding_function(prompt)[0]

# Format the embedding array or list as a string, so it can be passed in the REST API request.
embedding_string = ",".join([str(item) for item in embedding])

tql_query = f"select * from (select text, metadata, cosine_similarity(embedding, ARRAY[{embedding_string}]) as score where contains(text, 'python') or contains(metadata['source'], '.py')) order by score desc limit 5"
search_results = vector_store.search(query = tql_query)

Vector Search Using the Managed Tensor Database (Server-Side)

# vector_store = VectorStore(
#     path = "hub://<org_id>/<dataset_name>",
#     runtime = {"tensor_db": True}
# )

search_results = vector_store.search(embedding_data=prompt, 
                                     embedding_function=embedding_function)
PreviousVector Search OptionsNextREST API

Was this helpful?

Vector search can be combined with other search logic for performing more advanced queries. Let's define a function compatible with for filtering data before the vector search. The function below will filter samples that contain the word "program" in the text tensor.

Deep Lake offers advanced search that executes queries with higher performance in C++, and offers querying using Deep Lake's .

In order to use Compute Engine, Deep Lake data must be stored in Deep Lake Storage, or in the user's cloud while being connected to Deep Lake using .

Now let's run a search that includes filtering of text, metadata, and embedding tensors. We do this using by combining embedding search syntax (cosine_similarity(embedding, ...)) and filtering syntax (where ....).

For Vector Stored in the , queries will automatically execute on the database (instead of the client). Vector Stores are created in the Managed Tensor Database by specifying vector_store_path = hub://org_id/dataset_name and runtime = {"tensor_db": True} during Vector Store creation.

If Vector Stores are not in the Managed Tensor Database, :

📚
deeplake.filter
Tensor Query Language (TQL)
Managed Credentials
TQL
Managed Tensor Database
they can be migrated using these steps