0Pricing
Vector Databases: Pinecone, Weaviate & pgvector · Leçon

Requêtes GraphQL dans Weaviate

Maîtrisez l’interrogation de vos données Weaviate à l’aide de sa puissante API GraphQL pour la recherche sémantique et la récupération de données.

Requêtes GraphQL dans Weaviate est une leçon Vector Databases: Pinecone, Weaviate & pgvector gratuite sur CoddyKit. Ceci est la leçon 3 sur 4. Tu peux lire la leçon complète ci-dessous gratuitement — puis la pratiquer en direct dans le navigateur avec un éditeur de code intégré et un tuteur IA 24/7. Elle fait partie du parcours d'apprentissage Vector Databases: Pinecone, Weaviate & pgvector, et ta progression se synchronise sur le web et l'application CoddyKit. Le cours Vector Databases: Pinecone, Weaviate & pgvector comprend 4 leçons au total.

Certaines parties de cette leçon n'ont pas encore été traduites et s'affichent en anglais.

Weaviate's GraphQL Power

Welcome! In this lesson, you'll master querying your Weaviate data. Weaviate uses GraphQL, a powerful query language, for flexible and efficient data retrieval.

GraphQL allows you to request exactly the data you need, nothing more, nothing less. This is especially useful for complex searches, including vector similarity.

Basic Data Retrieval: Get

The foundation of querying in Weaviate is the Get operation. It allows you to fetch data objects from a specific class defined in your schema.

  • Specify the class name (e.g., Article).
  • Select the properties you want to retrieve (e.g., title, content).
  • Weaviate will return all objects of that class with the specified properties.

Get All Objects Example

Let's see a basic Get query in action. This Python code connects to your Weaviate instance and fetches the title and content of all Article objects.

(Ensure you have a Weaviate instance running locally at http://localhost:8080 and an 'Article' class with some data.)

import weaviate

# Connect to your Weaviate instance
# For local: http://localhost:8080
client = weaviate.Client(url="http://localhost:8080")

# Perform a basic Get query for 'Article' objects
try:
    response = client.query.get("Article", ["title", "content"]).do()
    print("--- Retrieved Articles ---")
    for article in response["data"]["Get"]["Article"]:
        print(f"Title: {article['title']}")
except Exception as e:
    print(f"Error during query: {e}")

Filtering Data with 'where'

Often, you don't want all objects, but specific ones. The where filter allows you to add conditions to your queries, narrowing down the results.

  • You can filter by property values (text, number, boolean, date).
  • Use operators like Equal, Like, GreaterThan, etc.
  • Combine multiple conditions with _and or _or clauses.

Filter by Property Value

This example shows how to use the where filter to find articles written by a specific author. We'll look for articles where the author property matches 'Jane Doe'.

import weaviate

client = weaviate.Client(url="http://localhost:8080")

# Define the 'where' filter
where_filter = {
    "path": ["author"],
    "operator": "Equal",
    "valueText": "Jane Doe"
}

# Perform the Get query with the filter
try:
    response = client.query.get("Article", ["title", "author"])
                          .with_where(where_filter).do()
    print("--- Articles by Jane Doe ---")
    for article in response["data"]["Get"]["Article"]:
        print(f"Title: {article['title']}, Author: {article['author']}")
except Exception as e:
    print(f"Error during query: {e}")

Retrieving Vector Embeddings

Weaviate stores a vector embedding for each object, representing its semantic meaning. You can retrieve this vector directly as part of your GraphQL query.

To do this, you use the _additional { vector } clause. This is useful for debugging, understanding your data, or performing custom operations outside Weaviate.

Get Vector Embedding

Here's how to fetch the vector embedding along with other properties. We'll get the title and the vector for the first article found.

import weaviate

client = weaviate.Client(url="http://localhost:8080")

# Query for a title and its vector
try:
    response = client.query.get("Article", ["title"])
                          .with_additional("vector")
                          .with_limit(1).do()
    print("--- Article Title and Vector ---")
    if response["data"]["Get"]["Article"]:
        article = response["data"]["Get"]["Article"][0]
        print(f"Title: {article['title']}")
        print(f"Vector (first 5 elements): {article['_additional']['vector'][:5]}...")
    else:
        print("No articles found.")
except Exception as e:
    print(f"Error during query: {e}")

Powerful Semantic Search

One of Weaviate's core strengths is semantic search. Instead of keyword matching, it finds data objects based on their meaning, even if the exact words aren't present.

This is achieved using the nearText operator. You provide 'concepts' (text) and Weaviate uses them to find the most semantically similar objects in your database.

Find Similar Articles

Let's perform a semantic search to find articles related to 'machine learning applications'. Notice how we use with_near_text and provide our query concepts.

import weaviate

client = weaviate.Client(url="http://localhost:8080")

# Define the concepts for semantic search
concepts = ["machine learning applications"]

# Perform a nearText query
try:
    response = client.query.get("Article", ["title", "content"])
                          .with_near_text({"concepts": concepts})
                          .with_limit(3).do()
    print("--- Articles similar to 'machine learning applications' ---")
    for article in response["data"]["Get"]["Article"]:
        print(f"Title: {article['title']}")
except Exception as e:
    print(f"Error during query: {e}")

GraphQL Query Challenge

You've learned about various ways to query data in Weaviate using GraphQL.

Which of the following GraphQL query operations is specifically used to find data objects that are semantically similar to a given text concept?

Weaviate Queries Recap

Great job! You've mastered the essentials of Weaviate's powerful GraphQL API:

  • The Get operation retrieves data objects and their properties.
  • The where filter allows you to apply precise conditions to your searches.
  • You can explicitly fetch an object's vector embedding using _additional { vector }.
  • The nearText operator powers semantic search, finding items based on meaning.

These tools enable you to efficiently retrieve and explore your vector data in Weaviate!

Questions Fréquemment Posées

La leçon « Requêtes GraphQL dans Weaviate » est-elle gratuite ?

Oui — le texte complet de « Requêtes GraphQL dans Weaviate » est gratuit à lire ici sur le web. Pour la pratiquer de manière interactive (un éditeur de code intégré et un tuteur IA 24/7) et déverrouiller le reste du cours Vector Databases: Pinecone, Weaviate & pgvector, passe à CoddyKit PRO. Le cours Vector Databases: Pinecone, Weaviate & pgvector comprend 4 leçons au total.

Qu'est-ce que j'apprendrai dans « Requêtes GraphQL dans Weaviate » ?

Maîtrisez l’interrogation de vos données Weaviate à l’aide de sa puissante API GraphQL pour la recherche sémantique et la récupération de données. Tu pratiques Vector Databases: Pinecone, Weaviate & pgvector avec du code pratique que tu exécutes directement dans le navigateur, et un tuteur IA 24/7 répond à tes questions au fur et à mesure que tu avances dans la leçon.

Dois-je avoir de l'expérience pour commencer Vector Databases: Pinecone, Weaviate & pgvector ?

Aucune expérience préalable n'est requise. Vector Databases: Pinecone, Weaviate & pgvector sur CoddyKit est structuré pour les débutants jusqu'aux apprenants avancés, donc tu peux commencer ici ou depuis le début et avancer à ton rythme. Ceci est la leçon 3 sur 4.

Combien de temps prend la leçon « Requêtes GraphQL dans Weaviate » ?

La plupart des leçons CoddyKit prennent environ 5–10 minutes. Chacune est courte et interactive, tu progresses régulièrement et tu repiques exactement où tu t'es arrêté sur le web et l'app.

Peux-tu écrire et exécuter du code dans cette leçon Vector Databases: Pinecone, Weaviate & pgvector ?

Oui. Chaque leçon Vector Databases: Pinecone, Weaviate & pgvector inclut un éditeur de code intégré, tu écris et exécutes du vrai code directement dans ton navigateur et tu reçois des retours IA instantanés — aucune configuration locale requise.

Toutes les leçons de ce cours

  1. Définir un schéma Weaviate
  2. Importer des objets de données
  3. Requêtes GraphQL dans Weaviate
  4. Modules de vectorisation et génération automatique d’embeddings
← Retour à Vector Databases: Pinecone, Weaviate & pgvector