mirror of
https://github.com/qdrant/landing_page.git
synced 2026-10-02 09:28:30 +02:00
created 'develop' section, re-org tutorials, formatted tables with updated css
This commit is contained in:
kanungle
@@ -0,0 +1,18 @@
|
|||||||
|
---
|
||||||
|
title: Basics
|
||||||
|
weight: 17
|
||||||
|
is_empty: false
|
||||||
|
aliases:
|
||||||
|
- how-to
|
||||||
|
- tutorials
|
||||||
|
partition: qdrant
|
||||||
|
---
|
||||||
|
|
||||||
|
# Basic Tutorials
|
||||||
|
*Get up and running with Qdrant in minutes.*
|
||||||
|
|
||||||
|
| Tutorial | Objective | Stack | Time | Level |
|
||||||
|
| :--- | :--- | :--- | :--- | :--- |
|
||||||
|
| [Local Qdrant Setup](/documentation/quickstart/) | Basic CRUD operations and local deployment. | <span class="pill">Python</span> | 10m | <span class="text-green">Beginner</span> |
|
||||||
|
| [5-Minute Semantic Search](/documentation/tutorials-basics/search-beginners/) | Build a search engine for science fiction books. | <span class="pill">Python</span> | 5m | <span class="text-green">Beginner</span> |
|
||||||
|
| [5-Minute RAG with DeepSeek](/documentation/tutorials-basics/rag-deepseek/) | Build a RAG pipeline with DeepSeek enrichment. | <span class="pill">Python</span> | 5m | <span class="text-green">Beginner</span> |
|
||||||
@@ -0,0 +1,14 @@
|
|||||||
|
---
|
||||||
|
title: Develop & Implement
|
||||||
|
weight: 21
|
||||||
|
is_empty: false
|
||||||
|
partition: qdrant
|
||||||
|
---
|
||||||
|
|
||||||
|
# Develop & Implement Tutorials
|
||||||
|
*Core tools and APIs for building with Qdrant.*
|
||||||
|
|
||||||
|
| Tutorial | Objective | Stack | Time | Level |
|
||||||
|
| :--- | :--- | :--- | :--- | :--- |
|
||||||
|
| [Bulk Data Uploads](/documentation/tutorials-develop/bulk-upload/) | High-scale ingestion tricks for power users. | <span class="pill">Python</span> | 20m | <span class="text-yellow">Intermediate</span> |
|
||||||
|
| [Python Async API](/documentation/tutorials-develop/async-api/) | Use Asynchronous programming for efficiency. | <span class="pill">Python</span> | 25m | <span class="text-yellow">Intermediate</span> |
|
||||||
@@ -1,6 +1,6 @@
|
|||||||
---
|
---
|
||||||
title: Ecosystem & Integrations
|
title: Ecosystem & Integrations
|
||||||
weight: 20
|
weight: 22
|
||||||
is_empty: false
|
is_empty: false
|
||||||
aliases:
|
aliases:
|
||||||
- how-to
|
- how-to
|
||||||
@@ -13,9 +13,9 @@ partition: qdrant
|
|||||||
|
|
||||||
| Tutorial | Objective | Stack | Time | Level |
|
| Tutorial | Objective | Stack | Time | Level |
|
||||||
| :--- | :--- | :--- | :--- | :--- |
|
| :--- | :--- | :--- | :--- | :--- |
|
||||||
| [S3 Ingestion with LangChain](/documentation/data-ingestion-beginners/) | Stream data from AWS S3 to vector store. | LangChain | 30m | Beginner |
|
| [S3 Ingestion with LangChain](/documentation/data-ingestion-beginners/) | Stream data from AWS S3 to vector store. | <span class="pill">LangChain</span> | 30m | <span class="text-green">Beginner</span> |
|
||||||
| [Hugging Face Datasets](/documentation/tutorials-ecosystem/huggingface-datasets/) | Load and search public ML datasets. | Python | 15m | Beginner |
|
| [Hugging Face Datasets](/documentation/tutorials-ecosystem/huggingface-datasets/) | Load and search public ML datasets. | <span class="pill">Python</span> | 15m | <span class="text-green">Beginner</span> |
|
||||||
| [Databricks Integration](/documentation/send-data/databricks/) | Vectorize datasets using FastEmbed on Databricks. | Databricks | 30m | Intermediate |
|
| [Databricks Integration](/documentation/send-data/databricks/) | Vectorize datasets using FastEmbed on Databricks. | <span class="pill">Databricks</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Airflow & Astronomer](/documentation/send-data/qdrant-airflow-astronomer/) | Orchestrate data engineering workflows. | Airflow | 45m | Intermediate |
|
| [Airflow & Astronomer](/documentation/send-data/qdrant-airflow-astronomer/) | Orchestrate data engineering workflows. | <span class="pill">Airflow</span> | 45m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Kafka Data Streaming](/documentation/send-data/data-streaming-kafka-qdrant/) | Setup Qdrant Sink Connector for real-time data. | Kafka | 60m | Advanced |
|
| [No-Code Automation (n8n)](/documentation/qdrant-n8n/) | Combine Qdrant with low-code n8n workflows. | <span class="pill">n8n</span> | 45m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [No-Code Automation (n8n)](/documentation/qdrant-n8n/) | Combine Qdrant with low-code n8n workflows. | n8n | 45m | Intermediate |
|
| [Kafka Data Streaming](/documentation/send-data/data-streaming-kafka-qdrant/) | Setup Qdrant Sink Connector for real-time data. | <span class="pill">Kafka</span> | 60m | <span class="text-red">Advanced</span> |
|
||||||
@@ -1,6 +1,6 @@
|
|||||||
---
|
---
|
||||||
title: Operations & Scale
|
title: Operations & Scale
|
||||||
weight: 21
|
weight: 20
|
||||||
is_empty: false
|
is_empty: false
|
||||||
aliases:
|
aliases:
|
||||||
- how-to
|
- how-to
|
||||||
@@ -13,11 +13,9 @@ partition: qdrant
|
|||||||
|
|
||||||
| Tutorial | Objective | Stack | Time | Level |
|
| Tutorial | Objective | Stack | Time | Level |
|
||||||
| :--- | :--- | :--- | :--- | :--- |
|
| :--- | :--- | :--- | :--- | :--- |
|
||||||
| [Embedding Migration](/documentation/tutorials-operations/migration/) | Move dense and sparse embeddings to Qdrant. | CLI | 30m | Intermediate |
|
| [Snapshot & Backup](/documentation/tutorials-operations/create-snapshot/) | Create and restore collection snapshots. | <span class="pill">Python</span> | 20m | <span class="text-green">Beginner</span> |
|
||||||
| [Bulk Data Uploads](/documentation/tutorials-operations/bulk-upload/) | High-scale ingestion tricks for power users. | Python | 20m | Intermediate |
|
| [Cloud Inference Search](/documentation/tutorials-and-examples/cloud-inference-hybrid-search/) | Hybrid search using Qdrant's built-in inference. | <span class="pill">Any</span> | 20m | <span class="text-green">Beginner</span> |
|
||||||
| [Snapshot & Backup](/documentation/tutorials-operations/create-snapshot/) | Create and restore collection snapshots. | Python | 20m | Beginner |
|
| [Embedding Migration](/documentation/tutorials-operations/migration/) | Move dense and sparse embeddings to Qdrant. | <span class="pill">CLI</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Billion-Scale Search](/documentation/tutorials-operations/large-scale-search/) | Cost-efficient search for LAION-400M datasets. | None | 2 days | Advanced |
|
| [Monitor Managed Cloud](/documentation/tutorials-and-examples/managed-cloud-prometheus/) | Observability with Prometheus and Grafana. | <span class="pill">Prometheus</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Python Async API](/documentation/tutorials-operations/async-api/) | Use Asynchronous programming for efficiency. | Python | 25m | Intermediate |
|
| [Monitor Private Cloud](/documentation/tutorials-and-examples/hybrid-cloud-prometheus/) | Observability for hybrid/private cloud setups. | <span class="pill">Prometheus</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Cloud Inference Search](/documentation/tutorials-and-examples/cloud-inference-hybrid-search/) | Hybrid search using Qdrant's built-in inference. | Any | 20m | Beginner |
|
| [Billion-Scale Search](/documentation/tutorials-operations/large-scale-search/) | Cost-efficient search for LAION-400M datasets. | <span class="pill">None</span> | 2 days | <span class="text-red">Advanced</span> |
|
||||||
| [Monitor Managed Cloud](/documentation/tutorials-and-examples/managed-cloud-prometheus/) | Observability with Prometheus and Grafana. | Prometheus | 30m | Intermediate |
|
|
||||||
| [Monitor Private Cloud](/documentation/tutorials-and-examples/hybrid-cloud-prometheus/) | Observability for hybrid/private cloud setups. | Prometheus | 30m | Intermediate |
|
|
||||||
@@ -1,22 +1,22 @@
|
|||||||
---
|
---
|
||||||
title: Overview
|
title: Overview
|
||||||
weight: 16
|
weight: 16
|
||||||
|
is_empty: false
|
||||||
aliases:
|
aliases:
|
||||||
- how-to
|
- how-to
|
||||||
- tutorials
|
- tutorials
|
||||||
partition: qdrant
|
partition: qdrant
|
||||||
---
|
---
|
||||||
|
# Qdrant Tutorial Repository
|
||||||
|
|
||||||
# Qdrant Tutorial Directory
|
### Basic Tutorials
|
||||||
|
|
||||||
### Quickstart
|
|
||||||
*Get up and running with Qdrant in minutes.*
|
*Get up and running with Qdrant in minutes.*
|
||||||
|
|
||||||
| Tutorial | Objective | Stack | Time | Level |
|
| Tutorial | Objective | Stack | Time | Level |
|
||||||
| :--- | :--- | :--- | :--- | :--- |
|
| :--- | :--- | :--- | :--- | :--- |
|
||||||
| [Local Qdrant Setup](/documentation/quickstart/) | Basic CRUD operations and local deployment. | Python | 10m | Beginner |
|
| [Local Qdrant Setup](/documentation/quickstart/) | Basic CRUD operations and local deployment. | <span class="pill">Python</span> | 10m | <span class="text-green">Beginner</span> |
|
||||||
| [5-Minute Semantic Search](/documentation/tutorials-quickstart/search-beginners/) | Build a search engine for science fiction books. | Python | 5m | Beginner |
|
| [5-Minute Semantic Search](/documentation/tutorials-basics/search-beginners/) | Build a search engine for science fiction books. | <span class="pill">Python</span> | 5m | <span class="text-green">Beginner</span> |
|
||||||
| [5-Minute RAG with DeepSeek](/documentation/tutorials-quickstart/rag-deepseek/) | Build a RAG pipeline with DeepSeek enrichment. | Python | 5m | Beginner |
|
| [5-Minute RAG with DeepSeek](/documentation/tutorials-basics/rag-deepseek/) | Build a RAG pipeline with DeepSeek enrichment. | <span class="pill">Python</span> | 5m | <span class="text-green">Beginner</span> |
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
@@ -25,15 +25,15 @@ partition: qdrant
|
|||||||
|
|
||||||
| Tutorial | Objective | Stack | Time | Level |
|
| Tutorial | Objective | Stack | Time | Level |
|
||||||
| :--- | :--- | :--- | :--- | :--- |
|
| :--- | :--- | :--- | :--- | :--- |
|
||||||
| [Neural Search Service](/documentation/tutorials-search-engineering/neural-search/) | Deploy a search service for company descriptions. | FastAPI | 30m | Beginner |
|
| [Hybrid Search with FastEmbed](/documentation/tutorials-search-engineering/hybrid-search-fastembed/) | Combine dense and sparse search for startups. | <span class="pill">FastAPI</span> | 20m | <span class="text-green">Beginner</span> |
|
||||||
| [Hybrid Search with FastEmbed](/documentation/tutorials-search-engineering/hybrid-search-fastembed/) | Combine dense and sparse search for startups. | FastAPI | 20m | Beginner |
|
| [Neural Search Service](/documentation/tutorials-search-engineering/neural-search/) | Deploy a search service for company descriptions. | <span class="pill">FastAPI</span> | 30m | <span class="text-green">Beginner</span> |
|
||||||
| [Movie Recommendations](/documentation/tutorials-search-engineering/collaborative-filtering/) | Collaborative filtering using sparse embeddings. | Python | 45m | Intermediate |
|
| [Movie Recommendations](/documentation/tutorials-search-engineering/collaborative-filtering/) | Collaborative filtering using sparse embeddings. | <span class="pill">Python</span> | 45m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Advanced PDF Retrieval](/documentation/tutorials-search-engineering/pdf-retrieval-at-scale/) | PDF RAG using ColPali and embedding pooling. | Python | 30m | Intermediate |
|
| [Advanced PDF Retrieval](/documentation/tutorials-search-engineering/pdf-retrieval-at-scale/) | PDF RAG using ColPali and embedding pooling. | <span class="pill">Python</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Retrieval Quality Benchmarking](/documentation/tutorials-search-engineering/retrieval-quality/) | Measure quality and tune HNSW parameters. | Python | 30m | Intermediate |
|
| [Retrieval Quality Benchmarking](/documentation/tutorials-search-engineering/retrieval-quality/) | Measure quality and tune HNSW parameters. | <span class="pill">Python</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Multivector Reranking](/documentation/search-precision/reranking-semantic-search/) | Use multivector representations for better ranking. | Python | 30m | Intermediate |
|
| [Multivector Reranking](/documentation/search-precision/reranking-semantic-search/) | Use multivector representations for better ranking. | <span class="pill">Python</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Hybrid Search Reranking](/documentation/tutorials-search-engineering/reranking-hybrid-search/) | Implement late interaction and sparse reranking. | Python | 40m | Intermediate |
|
| [Hybrid Search Reranking](/documentation/tutorials-search-engineering/reranking-hybrid-search/) | Implement late interaction and sparse reranking. | <span class="pill">Python</span> | 40m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Semantic Code Search](/documentation/tutorials-search-engineering/code-search/) | Navigate codebases using vector similarity. | Python | 45m | Intermediate |
|
| [Semantic Code Search](/documentation/tutorials-search-engineering/code-search/) | Navigate codebases using vector similarity. | <span class="pill">Python</span> | 45m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Static Embeddings Analysis](/documentation/tutorials-search-engineering/static-embeddings/) | Evaluate the renaissance of static embeddings. | Python | 20m | Intermediate |
|
| [Static Embeddings Analysis](/documentation/tutorials-search-engineering/static-embeddings/) | Evaluate the renaissance of static embeddings. | <span class="pill">Python</span> | 20m | <span class="text-yellow">Intermediate</span> |
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
@@ -42,25 +42,11 @@ partition: qdrant
|
|||||||
|
|
||||||
| Tutorial | Objective | Stack | Time | Level |
|
| Tutorial | Objective | Stack | Time | Level |
|
||||||
| :--- | :--- | :--- | :--- | :--- |
|
| :--- | :--- | :--- | :--- | :--- |
|
||||||
| [Agentic RAG with CrewAI](/documentation/agentic-rag-crewai-zoom/) | Step-by-step multi-agent RAG system. | CrewAI | 45m | Beginner |
|
| [Multimodal Search (LlamaIndex)](/documentation/multimodal-search/) | Search across image and text modalities. | <span class="pill">LlamaIndex</span> | 15m | <span class="text-green">Beginner</span> |
|
||||||
| [Agentic RAG with LangGraph](/documentation/agentic-rag-langgraph/) | Build AI agents to answer library documentation. | LangGraph | 45m | Intermediate |
|
| [Agentic RAG with CrewAI](/documentation/agentic-rag-crewai-zoom/) | Step-by-step multi-agent RAG system. | <span class="pill">CrewAI</span> | 45m | <span class="text-green">Beginner</span> |
|
||||||
| [Agentic Discord ChatBot](/documentation/agentic-rag-camelai-discord/) | Develop a functional bot with CAMEL-AI. | OpenAI | 45m | Intermediate |
|
| [Agentic RAG with LangGraph](/documentation/agentic-rag-langgraph/) | Build AI agents to answer library documentation. | <span class="pill">LangGraph</span> | 45m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Multimodal Search (LlamaIndex)](/documentation/multimodal-search/) | Search across image and text modalities. | LlamaIndex | 15m | Beginner |
|
| [Agentic Discord ChatBot](/documentation/agentic-rag-camelai-discord/) | Develop a functional bot with CAMEL-AI. | <span class="pill">OpenAI</span> | 45m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Automate Metadata Filtering](/documentation/search-precision/automate-filtering-with-llms/) | Use LLM structured output for dynamic filters. | Python | 30m | Intermediate |
|
| [Automate Metadata Filtering](/documentation/search-precision/automate-filtering-with-llms/) | Use LLM structured output for dynamic filters. | <span class="pill">Python</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
### Ecosystem & Integrations
|
|
||||||
*Connect Qdrant to cloud providers, data streams, and ETL tools.*
|
|
||||||
|
|
||||||
| Tutorial | Objective | Stack | Time | Level |
|
|
||||||
| :--- | :--- | :--- | :--- | :--- |
|
|
||||||
| [S3 Ingestion with LangChain](/documentation/data-ingestion-beginners/) | Stream data from AWS S3 to vector store. | LangChain | 30m | Beginner |
|
|
||||||
| [Hugging Face Datasets](/documentation/tutorials-ecosystem/huggingface-datasets/) | Load and search public ML datasets. | Python | 15m | Beginner |
|
|
||||||
| [Databricks Integration](/documentation/send-data/databricks/) | Vectorize datasets using FastEmbed on Databricks. | Databricks | 30m | Intermediate |
|
|
||||||
| [Airflow & Astronomer](/documentation/send-data/qdrant-airflow-astronomer/) | Orchestrate data engineering workflows. | Airflow | 45m | Intermediate |
|
|
||||||
| [Kafka Data Streaming](/documentation/send-data/data-streaming-kafka-qdrant/) | Setup Qdrant Sink Connector for real-time data. | Kafka | 60m | Advanced |
|
|
||||||
| [No-Code Automation (n8n)](/documentation/qdrant-n8n/) | Combine Qdrant with low-code n8n workflows. | n8n | 45m | Intermediate |
|
|
||||||
|
|
||||||
---
|
---
|
||||||
|
|
||||||
@@ -69,11 +55,33 @@ partition: qdrant
|
|||||||
|
|
||||||
| Tutorial | Objective | Stack | Time | Level |
|
| Tutorial | Objective | Stack | Time | Level |
|
||||||
| :--- | :--- | :--- | :--- | :--- |
|
| :--- | :--- | :--- | :--- | :--- |
|
||||||
| [Embedding Migration](/documentation/tutorials-operations/migration/) | Move dense and sparse embeddings to Qdrant. | CLI | 30m | Intermediate |
|
| [Snapshot & Backup](/documentation/tutorials-operations/create-snapshot/) | Create and restore collection snapshots. | <span class="pill">Python</span> | 20m | <span class="text-green">Beginner</span> |
|
||||||
| [Bulk Data Uploads](/documentation/tutorials-operations/bulk-upload/) | High-scale ingestion tricks for power users. | Python | 20m | Intermediate |
|
| [Cloud Inference Search](/documentation/tutorials-and-examples/cloud-inference-hybrid-search/) | Hybrid search using Qdrant's built-in inference. | <span class="pill">Any</span> | 20m | <span class="text-green">Beginner</span> |
|
||||||
| [Snapshot & Backup](/documentation/tutorials-operations/create-snapshot/) | Create and restore collection snapshots. | Python | 20m | Beginner |
|
| [Embedding Migration](/documentation/tutorials-operations/migration/) | Move dense and sparse embeddings to Qdrant. | <span class="pill">CLI</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Billion-Scale Search](/documentation/tutorials-operations/large-scale-search/) | Cost-efficient search for LAION-400M datasets. | None | 2 days | Advanced |
|
| [Monitor Managed Cloud](/documentation/tutorials-and-examples/managed-cloud-prometheus/) | Observability with Prometheus and Grafana. | <span class="pill">Prometheus</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Python Async API](/documentation/tutorials-operations/async-api/) | Use Asynchronous programming for efficiency. | Python | 25m | Intermediate |
|
| [Monitor Private Cloud](/documentation/tutorials-and-examples/hybrid-cloud-prometheus/) | Observability for hybrid/private cloud setups. | <span class="pill">Prometheus</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Cloud Inference Search](/documentation/tutorials-and-examples/cloud-inference-hybrid-search/) | Hybrid search using Qdrant's built-in inference. | Any | 20m | Beginner |
|
| [Billion-Scale Search](/documentation/tutorials-operations/large-scale-search/) | Cost-efficient search for LAION-400M datasets. | <span class="pill">None</span> | 2 days | <span class="text-red">Advanced</span> |
|
||||||
| [Monitor Managed Cloud](/documentation/tutorials-and-examples/managed-cloud-prometheus/) | Observability with Prometheus and Grafana. | Prometheus | 30m | Intermediate |
|
|
||||||
| [Monitor Private Cloud](/documentation/tutorials-and-examples/hybrid-cloud-prometheus/) | Observability for hybrid/private cloud setups. | Prometheus | 30m | Intermediate |
|
---
|
||||||
|
|
||||||
|
### Develop & Implement
|
||||||
|
*Core tools and APIs for building with Qdrant.*
|
||||||
|
|
||||||
|
| Tutorial | Objective | Stack | Time | Level |
|
||||||
|
| :--- | :--- | :--- | :--- | :--- |
|
||||||
|
| [Bulk Data Uploads](/documentation/tutorials-develop/bulk-upload/) | High-scale ingestion tricks for power users. | <span class="pill">Python</span> | 20m | <span class="text-yellow">Intermediate</span> |
|
||||||
|
| [Python Async API](/documentation/tutorials-develop/async-api/) | Use Asynchronous programming for efficiency. | <span class="pill">Python</span> | 25m | <span class="text-yellow">Intermediate</span> |
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### Ecosystem & Integrations
|
||||||
|
*Connect Qdrant to cloud providers, data streams, and ETL tools.*
|
||||||
|
|
||||||
|
| Tutorial | Objective | Stack | Time | Level |
|
||||||
|
| :--- | :--- | :--- | :--- | :--- |
|
||||||
|
| [S3 Ingestion with LangChain](/documentation/data-ingestion-beginners/) | Stream data from AWS S3 to vector store. | <span class="pill">LangChain</span> | 30m | <span class="text-green">Beginner</span> |
|
||||||
|
| [Hugging Face Datasets](/documentation/tutorials-ecosystem/huggingface-datasets/) | Load and search public ML datasets. | <span class="pill">Python</span> | 15m | <span class="text-green">Beginner</span> |
|
||||||
|
| [Databricks Integration](/documentation/send-data/databricks/) | Vectorize datasets using FastEmbed on Databricks. | <span class="pill">Databricks</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
|
| [Airflow & Astronomer](/documentation/send-data/qdrant-airflow-astronomer/) | Orchestrate data engineering workflows. | <span class="pill">Airflow</span> | 45m | <span class="text-yellow">Intermediate</span> |
|
||||||
|
| [No-Code Automation (n8n)](/documentation/qdrant-n8n/) | Combine Qdrant with low-code n8n workflows. | <span class="pill">n8n</span> | 45m | <span class="text-yellow">Intermediate</span> |
|
||||||
|
| [Kafka Data Streaming](/documentation/send-data/data-streaming-kafka-qdrant/) | Setup Qdrant Sink Connector for real-time data. | <span class="pill">Kafka</span> | 60m | <span class="text-red">Advanced</span> |
|
||||||
@@ -1,18 +0,0 @@
|
|||||||
---
|
|
||||||
title: Quickstart
|
|
||||||
weight: 17
|
|
||||||
is_empty: false
|
|
||||||
aliases:
|
|
||||||
- how-to
|
|
||||||
- tutorials
|
|
||||||
partition: qdrant
|
|
||||||
---
|
|
||||||
|
|
||||||
# Quickstart Tutorials
|
|
||||||
*Get up and running with Qdrant in minutes.*
|
|
||||||
|
|
||||||
| Tutorial | Objective | Stack | Time | Level |
|
|
||||||
| :--- | :--- | :--- | :--- | :--- |
|
|
||||||
| [Local Qdrant Setup](/documentation/quickstart/) | Basic CRUD operations and local deployment. | Python | 10m | Beginner |
|
|
||||||
| [5-Minute Semantic Search](/documentation/tutorials-quickstart/search-beginners/) | Build a search engine for science fiction books. | Python | 5m | Beginner |
|
|
||||||
| [5-Minute RAG with DeepSeek](/documentation/tutorials-quickstart/rag-deepseek/) | Build a RAG pipeline with DeepSeek enrichment. | Python | 5m | Beginner |
|
|
||||||
@@ -1,334 +0,0 @@
|
|||||||
---
|
|
||||||
title: 5 Minute RAG with Qdrant and DeepSeek
|
|
||||||
weight: 6
|
|
||||||
partition: build
|
|
||||||
social_preview_image: /documentation/examples/rag-deepseek/social_preview.png
|
|
||||||
---
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
# 5 Minute RAG with Qdrant and DeepSeek
|
|
||||||
|
|
||||||
| Time: 5 min | Level: Beginner | Output: [GitHub](https://github.com/qdrant/examples/blob/master/rag-with-qdrant-deepseek/deepseek-qdrant.ipynb) |
|
|
||||||
| --- | ----------- | ----------- |----------- |
|
|
||||||
|
|
||||||
This tutorial demonstrates how to build a **Retrieval-Augmented Generation (RAG)** pipeline using Qdrant as a vector storage solution and DeepSeek for semantic query enrichment. RAG pipelines enhance Large Language Model (LLM) responses by providing contextually relevant data.
|
|
||||||
|
|
||||||
## Overview
|
|
||||||
In this tutorial, we will:
|
|
||||||
1. Take sample text and turn it into vectors with FastEmbed.
|
|
||||||
2. Send the vectors to a Qdrant collection.
|
|
||||||
3. Connect Qdrant and DeepSeek into a minimal RAG pipeline.
|
|
||||||
4. Ask DeepSeek different questions and test answer accuracy.
|
|
||||||
5. Enrich DeepSeek prompts with content retrieved from Qdrant.
|
|
||||||
6. Evaluate answer accuracy before and after.
|
|
||||||
|
|
||||||
#### Architecture:
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
---
|
|
||||||
|
|
||||||
## Prerequisites
|
|
||||||
|
|
||||||
Ensure you have the following:
|
|
||||||
- Python environment (3.9+)
|
|
||||||
- Access to [Qdrant Cloud](https://qdrant.tech)
|
|
||||||
- A DeepSeek API key from [DeepSeek Platform](https://platform.deepseek.com/api_keys)
|
|
||||||
|
|
||||||
## Setup Qdrant
|
|
||||||
|
|
||||||
|
|
||||||
```python
|
|
||||||
pip install "qdrant-client[fastembed]>=1.14.1"
|
|
||||||
```
|
|
||||||
|
|
||||||
[Qdrant](https://qdrant.tech) will act as a knowledge base providing the context information for the prompts we'll be sending to the LLM.
|
|
||||||
|
|
||||||
You can get a free-forever Qdrant cloud instance at http://cloud.qdrant.io. Learn about setting up your instance from the [Quickstart](https://qdrant.tech/documentation/quickstart-cloud/).
|
|
||||||
|
|
||||||
|
|
||||||
```python
|
|
||||||
QDRANT_URL = "https://xyz-example.eu-central.aws.cloud.qdrant.io:6333"
|
|
||||||
QDRANT_API_KEY = "<your-api-key>"
|
|
||||||
```
|
|
||||||
|
|
||||||
### Instantiating Qdrant Client
|
|
||||||
|
|
||||||
|
|
||||||
```python
|
|
||||||
from qdrant_client import QdrantClient, models
|
|
||||||
|
|
||||||
client = QdrantClient(url=QDRANT_URL, api_key=QDRANT_API_KEY)
|
|
||||||
```
|
|
||||||
|
|
||||||
### Building the knowledge base
|
|
||||||
|
|
||||||
Qdrant will use vector embeddings of our facts to enrich the original prompt with some context. Thus, we need to store the vector embeddings and the facts used to generate them.
|
|
||||||
|
|
||||||
We'll be using the [bge-base-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) model via [FastEmbed](https://github.com/qdrant/fastembed/) - A lightweight, fast, Python library for embeddings generation.
|
|
||||||
|
|
||||||
The Qdrant client provides a handy integration with FastEmbed that makes building a knowledge base very straighforward.
|
|
||||||
|
|
||||||
First, we need to create a collection, so Qdrant would know what vectors it will be dealing with, and then, we just pass our raw documents
|
|
||||||
wrapped into `models.Document` to compute and upload the embeddings.
|
|
||||||
|
|
||||||
```python
|
|
||||||
collection_name = "knowledge_base"
|
|
||||||
model_name = "BAAI/bge-small-en-v1.5"
|
|
||||||
client.create_collection(
|
|
||||||
collection_name=collection_name,
|
|
||||||
vectors_config=models.VectorParams(size=384, distance=models.Distance.COSINE)
|
|
||||||
)
|
|
||||||
```
|
|
||||||
|
|
||||||
```python
|
|
||||||
documents = [
|
|
||||||
"Qdrant is a vector database & vector similarity search engine. It deploys as an API service providing search for the nearest high-dimensional vectors. With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more!",
|
|
||||||
"Docker helps developers build, share, and run applications anywhere — without tedious environment configuration or management.",
|
|
||||||
"PyTorch is a machine learning framework based on the Torch library, used for applications such as computer vision and natural language processing.",
|
|
||||||
"MySQL is an open-source relational database management system (RDBMS). A relational database organizes data into one or more data tables in which data may be related to each other; these relations help structure the data. SQL is a language that programmers use to create, modify and extract data from the relational database, as well as control user access to the database.",
|
|
||||||
"NGINX is a free, open-source, high-performance HTTP server and reverse proxy, as well as an IMAP/POP3 proxy server. NGINX is known for its high performance, stability, rich feature set, simple configuration, and low resource consumption.",
|
|
||||||
"FastAPI is a modern, fast (high-performance), web framework for building APIs with Python 3.7+ based on standard Python type hints.",
|
|
||||||
"SentenceTransformers is a Python framework for state-of-the-art sentence, text and image embeddings. You can use this framework to compute sentence / text embeddings for more than 100 languages. These embeddings can then be compared e.g. with cosine-similarity to find sentences with a similar meaning. This can be useful for semantic textual similar, semantic search, or paraphrase mining.",
|
|
||||||
"The cron command-line utility is a job scheduler on Unix-like operating systems. Users who set up and maintain software environments use cron to schedule jobs (commands or shell scripts), also known as cron jobs, to run periodically at fixed times, dates, or intervals.",
|
|
||||||
]
|
|
||||||
client.upsert(
|
|
||||||
collection_name=collection_name,
|
|
||||||
points=[
|
|
||||||
models.PointStruct(
|
|
||||||
id=idx,
|
|
||||||
vector=models.Document(text=document, model=model_name),
|
|
||||||
payload={"document": document},
|
|
||||||
)
|
|
||||||
for idx, document in enumerate(documents)
|
|
||||||
],
|
|
||||||
)
|
|
||||||
```
|
|
||||||
|
|
||||||
## Setup DeepSeek
|
|
||||||
|
|
||||||
RAG changes the way we interact with Large Language Models. We're converting a knowledge-oriented task, in which the model may create a counterfactual answer, into a language-oriented task. The latter expects the model to extract meaningful information and generate an answer. LLMs, when implemented correctly, are supposed to be carrying out language-oriented tasks.
|
|
||||||
|
|
||||||
The task starts with the original prompt sent by the user. The same prompt is then vectorized and used as a search query for the most relevant facts. Those facts are combined with the original prompt to build a longer prompt containing more information.
|
|
||||||
|
|
||||||
But let's start simply by asking our question directly.
|
|
||||||
|
|
||||||
|
|
||||||
```python
|
|
||||||
prompt = """
|
|
||||||
What tools should I need to use to build a web service using vector embeddings for search?
|
|
||||||
"""
|
|
||||||
```
|
|
||||||
|
|
||||||
Using the Deepseek API requires providing the API key. You can obtain it from the [DeepSeek platform](https://platform.deepseek.com/api_keys).
|
|
||||||
|
|
||||||
Now we can finally call the completion API.
|
|
||||||
|
|
||||||
|
|
||||||
```python
|
|
||||||
import requests
|
|
||||||
import json
|
|
||||||
|
|
||||||
# Fill the environmental variable with your own Deepseek API key
|
|
||||||
# See: https://platform.deepseek.com/api_keys
|
|
||||||
API_KEY = "<YOUR_DEEPSEEK_KEY>"
|
|
||||||
|
|
||||||
HEADERS = {
|
|
||||||
"Authorization": f"Bearer {API_KEY}",
|
|
||||||
"Content-Type": "application/json",
|
|
||||||
}
|
|
||||||
|
|
||||||
|
|
||||||
def query_deepseek(prompt):
|
|
||||||
data = {
|
|
||||||
"model": "deepseek-chat",
|
|
||||||
"messages": [{"role": "user", "content": prompt}],
|
|
||||||
"stream": False,
|
|
||||||
}
|
|
||||||
|
|
||||||
response = requests.post(
|
|
||||||
"https://api.deepseek.com/chat/completions", headers=HEADERS, data=json.dumps(data)
|
|
||||||
)
|
|
||||||
|
|
||||||
if response.ok:
|
|
||||||
result = response.json()
|
|
||||||
return result["choices"][0]["message"]["content"]
|
|
||||||
else:
|
|
||||||
raise Exception(f"Error {response.status_code}: {response.text}")
|
|
||||||
|
|
||||||
```
|
|
||||||
|
|
||||||
and also the query
|
|
||||||
|
|
||||||
```python
|
|
||||||
query_deepseek(prompt)
|
|
||||||
```
|
|
||||||
|
|
||||||
The response is:
|
|
||||||
|
|
||||||
```bash
|
|
||||||
"Building a web service that uses vector embeddings for search involves several components, including data processing, embedding generation, storage, search, and serving the service via an API. Below is a list of tools and technologies you can use for each step:\n\n---\n\n### 1. **Data Processing**\n - **Python**: For general data preprocessing and scripting.\n - **Pandas**: For handling tabular data.\n - **NumPy**: For numerical operations.\n - **NLTK/Spacy**: For text preprocessing (tokenization, stemming, etc.).\n - **LLM models**: For generating embeddings if you're using pre-trained models.\n\n---\n\n### 2. **Embedding Generation**\n - **Pre-trained Models**:\n - Embeddings (e.g., `text-embedding-ada-002`).\n - Hugging Face Transformers (e.g., `Sentence-BERT`, `all-MiniLM-L6-v2`).\n - Google's Universal Sentence Encoder.\n - **Custom Models**:\n - TensorFlow/PyTorch: For training custom embedding models.\n - **Libraries**:\n - `sentence-transformers`: For generating sentence embeddings.\n - `transformers`: For using Hugging Face models.\n\n---\n\n### 3. **Vector Storage**\n - **Vector Databases**:\n - Pinecone: Managed vector database for similarity search.\n - Weaviate: Open-source vector search engine.\n - Milvus: Open-source vector database.\n - FAISS (Facebook AI Similarity Search): Library for efficient similarity search.\n - Qdrant: Open-source vector search engine.\n - Redis with RedisAI: For storing and querying vectors.\n - **Traditional Databases with Vector Support**:\n - PostgreSQL with pgvector extension.\n - Elasticsearch with dense vector support.\n\n---\n\n### 4. **Search and Retrieval**\n - **Similarity Search Algorithms**:\n - Cosine similarity, Euclidean distance, or dot product for comparing vectors.\n - **Libraries**:\n - FAISS: For fast nearest-neighbor search.\n - Annoy (Approximate Nearest Neighbors Oh Yeah): For approximate nearest neighbor search.\n - **Vector Databases**: Most vector databases (e.g., Pinecone, Weaviate) come with built-in search capabilities.\n\n---\n\n### 5. **Web Service Framework**\n - **Backend Frameworks**:\n - Flask/Django/FastAPI (Python): For building RESTful APIs.\n - Node.js/Express: If you prefer JavaScript.\n - **API Documentation**:\n - Swagger/OpenAPI: For documenting your API.\n - **Authentication**:\n - OAuth2, JWT: For securing your API.\n\n---\n\n### 6. **Deployment**\n - **Containerization**:\n - Docker: For packaging your application.\n - **Orchestration**:\n - Kubernetes: For managing containers at scale.\n - **Cloud Platforms**:\n - AWS (EC2, Lambda, S3).\n - Google Cloud (Compute Engine, Cloud Functions).\n - Azure (App Service, Functions).\n - **Serverless**:\n - AWS Lambda, Google Cloud Functions, or Vercel for serverless deployment.\n\n---\n\n### 7. **Monitoring and Logging**\n - **Monitoring**:\n - Prometheus + Grafana: For monitoring performance.\n - **Logging**:\n - ELK Stack (Elasticsearch, Logstash, Kibana).\n - Fluentd.\n - **Error Tracking**:\n - Sentry.\n\n---\n\n### 8. **Frontend (Optional)**\n - **Frontend Frameworks**:\n - React, Vue.js, or Angular: For building a user interface.\n - **Libraries**:\n - Axios: For making API calls from the frontend.\n\n---\n\n### Example Workflow\n1. Preprocess your data (e.g., clean text, tokenize).\n2. Generate embeddings using a pre-trained model (e.g., Hugging Face).\n3. Store embeddings in a vector database (e.g., Pinecone or FAISS).\n4. Build a REST API using FastAPI or Flask to handle search queries.\n5. Deploy the service using Docker and Kubernetes or a serverless platform.\n6. Monitor and scale the service as needed.\n\n---\n\n### Example Tools Stack\n- **Embedding Generation**: Hugging Face `sentence-transformers`.\n- **Vector Storage**: Pinecone or FAISS.\n- **Web Framework**: FastAPI.\n- **Deployment**: Docker + AWS/GCP.\n\nBy combining these tools, you can build a scalable and efficient web service for vector embedding-based search."
|
|
||||||
```
|
|
||||||
|
|
||||||
|
|
||||||
### Extending the prompt
|
|
||||||
|
|
||||||
Even though the original answer sounds credible, it didn't answer our question correctly. Instead, it gave us a generic description of an application stack. To improve the results, enriching the original prompt with the descriptions of the tools available seems like one of the possibilities. Let's use a semantic knowledge base to augment the prompt with the descriptions of different technologies!
|
|
||||||
|
|
||||||
```python
|
|
||||||
results = client.query_points(
|
|
||||||
collection_name=collection_name,
|
|
||||||
query=models.Document(text=prompt, model=model_name),
|
|
||||||
limit=3,
|
|
||||||
)
|
|
||||||
results
|
|
||||||
```
|
|
||||||
|
|
||||||
Here is the response:
|
|
||||||
|
|
||||||
```bash
|
|
||||||
QueryResponse(points=[
|
|
||||||
ScoredPoint(id=0, version=0, score=0.67437416, payload={'document': 'Qdrant is a vector database & vector similarity search engine. It deploys as an API service providing search for the nearest high-dimensional vectors. With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more!'}, vector=None, shard_key=None, order_value=None),
|
|
||||||
ScoredPoint(id=6, version=0, score=0.63144326, payload={'document': 'SentenceTransformers is a Python framework for state-of-the-art sentence, text and image embeddings. You can use this framework to compute sentence / text embeddings for more than 100 languages. These embeddings can then be compared e.g. with cosine-similarity to find sentences with a similar meaning. This can be useful for semantic textual similar, semantic search, or paraphrase mining.'}, vector=None, shard_key=None, order_value=None),
|
|
||||||
ScoredPoint(id=5, version=0, score=0.6064749, payload={'document': 'FastAPI is a modern, fast (high-performance), web framework for building APIs with Python 3.7+ based on standard Python type hints.'}, vector=None, shard_key=None, order_value=None)
|
|
||||||
])
|
|
||||||
```
|
|
||||||
|
|
||||||
|
|
||||||
We used the original prompt to perform a semantic search over the set of tool descriptions. Now we can use these descriptions to augment the prompt and create more context.
|
|
||||||
|
|
||||||
|
|
||||||
```python
|
|
||||||
context = "\n".join(r.payload['document'] for r in results.points)
|
|
||||||
context
|
|
||||||
```
|
|
||||||
|
|
||||||
The response is:
|
|
||||||
|
|
||||||
```bash
|
|
||||||
'Qdrant is a vector database & vector similarity search engine. It deploys as an API service providing search for the nearest high-dimensional vectors. With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more!\nFastAPI is a modern, fast (high-performance), web framework for building APIs with Python 3.7+ based on standard Python type hints.\nPyTorch is a machine learning framework based on the Torch library, used for applications such as computer vision and natural language processing.'
|
|
||||||
```
|
|
||||||
|
|
||||||
|
|
||||||
Finally, let's build a metaprompt, the combination of the assumed role of the LLM, the original question, and the results from our semantic search that will force our LLM to use the provided context.
|
|
||||||
|
|
||||||
By doing this, we effectively convert the knowledge-oriented task into a language task and hopefully reduce the chances of hallucinations. It also should make the response sound more relevant.
|
|
||||||
|
|
||||||
|
|
||||||
```python
|
|
||||||
metaprompt = f"""
|
|
||||||
You are a software architect.
|
|
||||||
Answer the following question using the provided context.
|
|
||||||
If you can't find the answer, do not pretend you know it, but answer "I don't know".
|
|
||||||
|
|
||||||
Question: {prompt.strip()}
|
|
||||||
|
|
||||||
Context:
|
|
||||||
{context.strip()}
|
|
||||||
|
|
||||||
Answer:
|
|
||||||
"""
|
|
||||||
|
|
||||||
# Look at the full metaprompt
|
|
||||||
print(metaprompt)
|
|
||||||
```
|
|
||||||
|
|
||||||
**Response:**
|
|
||||||
|
|
||||||
```bash
|
|
||||||
You are a software architect.
|
|
||||||
Answer the following question using the provided context.
|
|
||||||
If you can't find the answer, do not pretend you know it, but answer "I don't know".
|
|
||||||
|
|
||||||
Question: What tools should I need to use to build a web service using vector embeddings for search?
|
|
||||||
|
|
||||||
Context:
|
|
||||||
Qdrant is a vector database & vector similarity search engine. It deploys as an API service providing search for the nearest high-dimensional vectors. With Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more!
|
|
||||||
FastAPI is a modern, fast (high-performance), web framework for building APIs with Python 3.7+ based on standard Python type hints.
|
|
||||||
PyTorch is a machine learning framework based on the Torch library, used for applications such as computer vision and natural language processing.
|
|
||||||
|
|
||||||
Answer:
|
|
||||||
```
|
|
||||||
|
|
||||||
Our current prompt is much longer, and we also used a couple of strategies to make the responses even better:
|
|
||||||
|
|
||||||
1. The LLM has the role of software architect.
|
|
||||||
2. We provide more context to answer the question.
|
|
||||||
3. If the context contains no meaningful information, the model shouldn't make up an answer.
|
|
||||||
|
|
||||||
Let's find out if that works as expected.
|
|
||||||
|
|
||||||
**Question:**
|
|
||||||
|
|
||||||
```python
|
|
||||||
query_deepseek(metaprompt)
|
|
||||||
```
|
|
||||||
**Answer:**
|
|
||||||
|
|
||||||
```bash
|
|
||||||
'To build a web service using vector embeddings for search, you can use the following tools:\n\n1. **Qdrant**: As a vector database and similarity search engine, Qdrant will handle the storage and retrieval of high-dimensional vectors. It provides an API service for searching and matching vectors, making it ideal for applications that require vector-based search functionality.\n\n2. **FastAPI**: This web framework is perfect for building the API layer of your web service. It is fast, easy to use, and based on Python type hints, which makes it a great choice for developing the backend of your service. FastAPI will allow you to expose endpoints that interact with Qdrant for vector search operations.\n\n3. **PyTorch**: If you need to generate vector embeddings from your data (e.g., text, images), PyTorch can be used to create and train neural network models that produce these embeddings. PyTorch is a powerful machine learning framework that supports a wide range of applications, including natural language processing and computer vision.\n\n### Summary:\n- **Qdrant** for vector storage and search.\n- **FastAPI** for building the web service API.\n- **PyTorch** for generating vector embeddings (if needed).\n\nThese tools together provide a robust stack for building a web service that leverages vector embeddings for search functionality.'
|
|
||||||
```
|
|
||||||
|
|
||||||
### Testing out the RAG pipeline
|
|
||||||
|
|
||||||
By leveraging the semantic context we provided our model is doing a better job answering the question. Let's enclose the RAG as a function, so we can call it more easily for different prompts.
|
|
||||||
|
|
||||||
|
|
||||||
```python
|
|
||||||
def rag(question: str, n_points: int = 3) -> str:
|
|
||||||
results = client.query_points(
|
|
||||||
collection_name=collection_name,
|
|
||||||
query=models.Document(text=question, model=model_name),
|
|
||||||
limit=n_points,
|
|
||||||
)
|
|
||||||
|
|
||||||
context = "\n".join(r.payload["document"] for r in results.points)
|
|
||||||
|
|
||||||
metaprompt = f"""
|
|
||||||
You are a software architect.
|
|
||||||
Answer the following question using the provided context.
|
|
||||||
If you can't find the answer, do not pretend you know it, but only answer "I don't know".
|
|
||||||
|
|
||||||
Question: {question.strip()}
|
|
||||||
|
|
||||||
Context:
|
|
||||||
{context.strip()}
|
|
||||||
|
|
||||||
Answer:
|
|
||||||
"""
|
|
||||||
|
|
||||||
return query_deepseek(metaprompt)
|
|
||||||
```
|
|
||||||
|
|
||||||
Now it's easier to ask a broad range of questions.
|
|
||||||
|
|
||||||
**Question:**
|
|
||||||
|
|
||||||
```python
|
|
||||||
rag("What can the stack for a web api look like?")
|
|
||||||
```
|
|
||||||
**Answer:**
|
|
||||||
|
|
||||||
```bash
|
|
||||||
'The stack for a web API can include the following components based on the provided context:\n\n1. **Web Framework**: FastAPI can be used as the web framework for building the API. It is modern, fast, and leverages Python type hints for better development and performance.\n\n2. **Reverse Proxy/Web Server**: NGINX can be used as a reverse proxy or web server to handle incoming HTTP requests, load balancing, and serving static content. It is known for its high performance and low resource consumption.\n\n3. **Containerization**: Docker can be used to containerize the application, making it easier to build, share, and run the API consistently across different environments without worrying about configuration issues.\n\nThis stack provides a robust, scalable, and efficient setup for building and deploying a web API.'
|
|
||||||
```
|
|
||||||
|
|
||||||
**Question:**
|
|
||||||
|
|
||||||
```python
|
|
||||||
rag("Where is the nearest grocery store?")
|
|
||||||
```
|
|
||||||
|
|
||||||
**Answer:**
|
|
||||||
|
|
||||||
```bash
|
|
||||||
"I don't know. The provided context does not contain any information about the location of the nearest grocery store."
|
|
||||||
```
|
|
||||||
|
|
||||||
Our model can now:
|
|
||||||
|
|
||||||
1. Take advantage of the knowledge in our vector datastore.
|
|
||||||
2. Answer, based on the provided context, that it can not provide an answer.
|
|
||||||
|
|
||||||
We have just shown a useful mechanism to mitigate the risks of hallucinations in Large Language Models.
|
|
||||||
@@ -1,245 +0,0 @@
|
|||||||
---
|
|
||||||
title: Semantic Search 101
|
|
||||||
weight: 1
|
|
||||||
aliases:
|
|
||||||
- /documentation/tutorials/mighty.md/
|
|
||||||
- /documentation/tutorials/search-beginners/
|
|
||||||
- /documentation/beginner-tutorials/search-beginners/
|
|
||||||
---
|
|
||||||
|
|
||||||
# Build Your First Semantic Search Engine in 5 Minutes
|
|
||||||
|
|
||||||
| Time: 5 - 15 min | Level: Beginner | | |
|
|
||||||
| --- | ----------- | ----------- |----------- |
|
|
||||||
|
|
||||||
<p align="center"><iframe width="560" height="315" src="https://www.youtube.com/embed/AASiqmtKo54" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe></p>
|
|
||||||
|
|
||||||
## Overview
|
|
||||||
|
|
||||||
If you are new to vector databases, this tutorial is for you. In 5 minutes you will build a semantic search engine for science fiction books. After you set it up, you will ask the engine about an impending alien threat. Your creation will recommend books as preparation for a potential space attack.
|
|
||||||
|
|
||||||
Before you begin, you need to have a [recent version of Python](https://www.python.org/downloads/) installed. If you don't know how to run this code in a virtual environment, follow Python documentation for [Creating Virtual Environments](https://docs.python.org/3/tutorial/venv.html#creating-virtual-environments) first.
|
|
||||||
|
|
||||||
This tutorial assumes you're in the bash shell. Use the Python documentation to activate a virtual environment, with commands such as:
|
|
||||||
|
|
||||||
```bash
|
|
||||||
source tutorial-env/bin/activate
|
|
||||||
```
|
|
||||||
|
|
||||||
## 1. Installation
|
|
||||||
|
|
||||||
You need to process your data so that the search engine can work with it. The [Sentence Transformers](https://www.sbert.net/) framework gives you access to common Large Language Models that turn raw data into embeddings.
|
|
||||||
|
|
||||||
```bash
|
|
||||||
pip install -U sentence-transformers
|
|
||||||
```
|
|
||||||
|
|
||||||
Once encoded, this data needs to be kept somewhere. Qdrant lets you store data as embeddings. You can also use Qdrant to run search queries against this data. This means that you can ask the engine to give you relevant answers that go way beyond keyword matching.
|
|
||||||
|
|
||||||
```bash
|
|
||||||
pip install -U qdrant-client
|
|
||||||
```
|
|
||||||
|
|
||||||
<aside role="status">
|
|
||||||
This tutorial requires qdrant-client version 1.7.1 or higher.
|
|
||||||
</aside>
|
|
||||||
|
|
||||||
### Import the models
|
|
||||||
|
|
||||||
Once the two main frameworks are defined, you need to specify the exact models this engine will use.
|
|
||||||
|
|
||||||
```python
|
|
||||||
from qdrant_client import models, QdrantClient
|
|
||||||
from sentence_transformers import SentenceTransformer
|
|
||||||
```
|
|
||||||
|
|
||||||
The [Sentence Transformers](https://www.sbert.net/index.html) framework contains many embedding models. We'll take [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) as it has a good balance between speed and embedding quality for this tutorial.
|
|
||||||
|
|
||||||
```python
|
|
||||||
encoder = SentenceTransformer("all-MiniLM-L6-v2")
|
|
||||||
```
|
|
||||||
|
|
||||||
## 2. Add the dataset
|
|
||||||
|
|
||||||
[all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2) will encode the data you provide. Here you will list all the science fiction books in your library. Each book has metadata, a name, author, publication year and a short description.
|
|
||||||
|
|
||||||
```python
|
|
||||||
documents = [
|
|
||||||
{
|
|
||||||
"name": "The Time Machine",
|
|
||||||
"description": "A man travels through time and witnesses the evolution of humanity.",
|
|
||||||
"author": "H.G. Wells",
|
|
||||||
"year": 1895,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Ender's Game",
|
|
||||||
"description": "A young boy is trained to become a military leader in a war against an alien race.",
|
|
||||||
"author": "Orson Scott Card",
|
|
||||||
"year": 1985,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Brave New World",
|
|
||||||
"description": "A dystopian society where people are genetically engineered and conditioned to conform to a strict social hierarchy.",
|
|
||||||
"author": "Aldous Huxley",
|
|
||||||
"year": 1932,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "The Hitchhiker's Guide to the Galaxy",
|
|
||||||
"description": "A comedic science fiction series following the misadventures of an unwitting human and his alien friend.",
|
|
||||||
"author": "Douglas Adams",
|
|
||||||
"year": 1979,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Dune",
|
|
||||||
"description": "A desert planet is the site of political intrigue and power struggles.",
|
|
||||||
"author": "Frank Herbert",
|
|
||||||
"year": 1965,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Foundation",
|
|
||||||
"description": "A mathematician develops a science to predict the future of humanity and works to save civilization from collapse.",
|
|
||||||
"author": "Isaac Asimov",
|
|
||||||
"year": 1951,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Snow Crash",
|
|
||||||
"description": "A futuristic world where the internet has evolved into a virtual reality metaverse.",
|
|
||||||
"author": "Neal Stephenson",
|
|
||||||
"year": 1992,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Neuromancer",
|
|
||||||
"description": "A hacker is hired to pull off a near-impossible hack and gets pulled into a web of intrigue.",
|
|
||||||
"author": "William Gibson",
|
|
||||||
"year": 1984,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "The War of the Worlds",
|
|
||||||
"description": "A Martian invasion of Earth throws humanity into chaos.",
|
|
||||||
"author": "H.G. Wells",
|
|
||||||
"year": 1898,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "The Hunger Games",
|
|
||||||
"description": "A dystopian society where teenagers are forced to fight to the death in a televised spectacle.",
|
|
||||||
"author": "Suzanne Collins",
|
|
||||||
"year": 2008,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "The Andromeda Strain",
|
|
||||||
"description": "A deadly virus from outer space threatens to wipe out humanity.",
|
|
||||||
"author": "Michael Crichton",
|
|
||||||
"year": 1969,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "The Left Hand of Darkness",
|
|
||||||
"description": "A human ambassador is sent to a planet where the inhabitants are genderless and can change gender at will.",
|
|
||||||
"author": "Ursula K. Le Guin",
|
|
||||||
"year": 1969,
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "The Three-Body Problem",
|
|
||||||
"description": "Humans encounter an alien civilization that lives in a dying system.",
|
|
||||||
"author": "Liu Cixin",
|
|
||||||
"year": 2008,
|
|
||||||
},
|
|
||||||
]
|
|
||||||
```
|
|
||||||
|
|
||||||
## 3. Define storage location
|
|
||||||
|
|
||||||
You need to tell Qdrant where to store embeddings. This is a basic demo, so your local computer will use its memory as temporary storage.
|
|
||||||
|
|
||||||
```python
|
|
||||||
client = QdrantClient(":memory:")
|
|
||||||
```
|
|
||||||
|
|
||||||
## 4. Create a collection
|
|
||||||
|
|
||||||
All data in Qdrant is organized by collections. In this case, you are storing books, so we are calling it `my_books`.
|
|
||||||
|
|
||||||
```python
|
|
||||||
client.create_collection(
|
|
||||||
collection_name="my_books",
|
|
||||||
vectors_config=models.VectorParams(
|
|
||||||
size=encoder.get_sentence_embedding_dimension(), # Vector size is defined by used model
|
|
||||||
distance=models.Distance.COSINE,
|
|
||||||
),
|
|
||||||
)
|
|
||||||
```
|
|
||||||
|
|
||||||
- The `vector_size` parameter defines the size of the vectors for a specific collection. If their size is different, it is impossible to calculate the distance between them. 384 is the encoder output dimensionality. You can also use model.get_sentence_embedding_dimension() to get the dimensionality of the model you are using.
|
|
||||||
|
|
||||||
- The `distance` parameter lets you specify the function used to measure the distance between two points.
|
|
||||||
|
|
||||||
|
|
||||||
## 5. Upload data to collection
|
|
||||||
|
|
||||||
Tell the database to upload `documents` to the `my_books` collection. This will give each record an id and a payload. The payload is just the metadata from the dataset.
|
|
||||||
|
|
||||||
```python
|
|
||||||
client.upload_points(
|
|
||||||
collection_name="my_books",
|
|
||||||
points=[
|
|
||||||
models.PointStruct(
|
|
||||||
id=idx, vector=encoder.encode(doc["description"]).tolist(), payload=doc
|
|
||||||
)
|
|
||||||
for idx, doc in enumerate(documents)
|
|
||||||
],
|
|
||||||
)
|
|
||||||
```
|
|
||||||
|
|
||||||
## 6. Ask the engine a question
|
|
||||||
|
|
||||||
Now that the data is stored in Qdrant, you can ask it questions and receive semantically relevant results.
|
|
||||||
|
|
||||||
```python
|
|
||||||
hits = client.query_points(
|
|
||||||
collection_name="my_books",
|
|
||||||
query=encoder.encode("alien invasion").tolist(),
|
|
||||||
limit=3,
|
|
||||||
).points
|
|
||||||
|
|
||||||
for hit in hits:
|
|
||||||
print(hit.payload, "score:", hit.score)
|
|
||||||
```
|
|
||||||
|
|
||||||
**Response:**
|
|
||||||
|
|
||||||
The search engine shows three of the most likely responses that have to do with the alien invasion. Each of the responses is assigned a score to show how close the response is to the original inquiry.
|
|
||||||
|
|
||||||
```text
|
|
||||||
{'name': 'The War of the Worlds', 'description': 'A Martian invasion of Earth throws humanity into chaos.', 'author': 'H.G. Wells', 'year': 1898} score: 0.570093257022374
|
|
||||||
{'name': "The Hitchhiker's Guide to the Galaxy", 'description': 'A comedic science fiction series following the misadventures of an unwitting human and his alien friend.', 'author': 'Douglas Adams', 'year': 1979} score: 0.5040468703143637
|
|
||||||
{'name': 'The Three-Body Problem', 'description': 'Humans encounter an alien civilization that lives in a dying system.', 'author': 'Liu Cixin', 'year': 2008} score: 0.45902943411768216
|
|
||||||
```
|
|
||||||
|
|
||||||
### Narrow down the query
|
|
||||||
|
|
||||||
How about the most recent book from the early 2000s?
|
|
||||||
|
|
||||||
```python
|
|
||||||
hits = client.query_points(
|
|
||||||
collection_name="my_books",
|
|
||||||
query=encoder.encode("alien invasion").tolist(),
|
|
||||||
query_filter=models.Filter(
|
|
||||||
must=[models.FieldCondition(key="year", range=models.Range(gte=2000))]
|
|
||||||
),
|
|
||||||
limit=1,
|
|
||||||
).points
|
|
||||||
|
|
||||||
for hit in hits:
|
|
||||||
print(hit.payload, "score:", hit.score)
|
|
||||||
```
|
|
||||||
|
|
||||||
**Response:**
|
|
||||||
|
|
||||||
The query has been narrowed down to one result from 2008.
|
|
||||||
|
|
||||||
```text
|
|
||||||
{'name': 'The Three-Body Problem', 'description': 'Humans encounter an alien civilization that lives in a dying system.', 'author': 'Liu Cixin', 'year': 2008} score: 0.45902943411768216
|
|
||||||
```
|
|
||||||
|
|
||||||
## Next Steps
|
|
||||||
|
|
||||||
Congratulations, you have just created your very first search engine! Trust us, the rest of Qdrant is not that complicated, either. For your next tutorial you should try building an actual [Neural Search Service with a complete API and a dataset](/documentation/tutorials/neural-search/).
|
|
||||||
@@ -13,8 +13,8 @@ partition: qdrant
|
|||||||
|
|
||||||
| Tutorial | Objective | Stack | Time | Level |
|
| Tutorial | Objective | Stack | Time | Level |
|
||||||
| :--- | :--- | :--- | :--- | :--- |
|
| :--- | :--- | :--- | :--- | :--- |
|
||||||
| [Agentic RAG with CrewAI](/documentation/agentic-rag-crewai-zoom/) | Step-by-step multi-agent RAG system. | CrewAI | 45m | Beginner |
|
| [Multimodal Search (LlamaIndex)](/documentation/multimodal-search/) | Search across image and text modalities. | <span class="pill">LlamaIndex</span> | 15m | <span class="text-green">Beginner</span> |
|
||||||
| [Agentic RAG with LangGraph](/documentation/agentic-rag-langgraph/) | Build AI agents to answer library documentation. | LangGraph | 45m | Intermediate |
|
| [Agentic RAG with CrewAI](/documentation/agentic-rag-crewai-zoom/) | Step-by-step multi-agent RAG system. | <span class="pill">CrewAI</span> | 45m | <span class="text-green">Beginner</span> |
|
||||||
| [Agentic Discord ChatBot](/documentation/agentic-rag-camelai-discord/) | Develop a functional bot with CAMEL-AI. | OpenAI | 45m | Intermediate |
|
| [Agentic RAG with LangGraph](/documentation/agentic-rag-langgraph/) | Build AI agents to answer library documentation. | <span class="pill">LangGraph</span> | 45m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Multimodal Search (LlamaIndex)](/documentation/multimodal-search/) | Search across image and text modalities. | LlamaIndex | 15m | Beginner |
|
| [Agentic Discord ChatBot](/documentation/agentic-rag-camelai-discord/) | Develop a functional bot with CAMEL-AI. | <span class="pill">OpenAI</span> | 45m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Automate Metadata Filtering](/documentation/search-precision/automate-filtering-with-llms/) | Use LLM structured output for dynamic filters. | Python | 30m | Intermediate |
|
| [Automate Metadata Filtering](/documentation/search-precision/automate-filtering-with-llms/) | Use LLM structured output for dynamic filters. | <span class="pill">Python</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
|
|||||||
@@ -13,12 +13,12 @@ partition: qdrant
|
|||||||
|
|
||||||
| Tutorial | Objective | Stack | Time | Level |
|
| Tutorial | Objective | Stack | Time | Level |
|
||||||
| :--- | :--- | :--- | :--- | :--- |
|
| :--- | :--- | :--- | :--- | :--- |
|
||||||
| [Neural Search Service](/documentation/tutorials-search-engineering/neural-search/) | Deploy a search service for company descriptions. | FastAPI | 30m | Beginner |
|
| [Hybrid Search with FastEmbed](/documentation/tutorials-search-engineering/hybrid-search-fastembed/) | Combine dense and sparse search for startups. | <span class="pill">FastAPI</span> | 20m | <span class="text-green">Beginner</span> |
|
||||||
| [Hybrid Search with FastEmbed](/documentation/tutorials-search-engineering/hybrid-search-fastembed/) | Combine dense and sparse search for startups. | FastAPI | 20m | Beginner |
|
| [Neural Search Service](/documentation/tutorials-search-engineering/neural-search/) | Deploy a search service for company descriptions. | <span class="pill">FastAPI</span> | 30m | <span class="text-green">Beginner</span> |
|
||||||
| [Movie Recommendations](/documentation/tutorials-search-engineering/collaborative-filtering/) | Collaborative filtering using sparse embeddings. | Python | 45m | Intermediate |
|
| [Movie Recommendations](/documentation/tutorials-search-engineering/collaborative-filtering/) | Collaborative filtering using sparse embeddings. | <span class="pill">Python</span> | 45m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Advanced PDF Retrieval](/documentation/tutorials-search-engineering/pdf-retrieval-at-scale/) | PDF RAG using ColPali and embedding pooling. | Python | 30m | Intermediate |
|
| [Advanced PDF Retrieval](/documentation/tutorials-search-engineering/pdf-retrieval-at-scale/) | PDF RAG using ColPali and embedding pooling. | <span class="pill">Python</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Retrieval Quality Benchmarking](/documentation/tutorials-search-engineering/retrieval-quality/) | Measure quality and tune HNSW parameters. | Python | 30m | Intermediate |
|
| [Retrieval Quality Benchmarking](/documentation/tutorials-search-engineering/retrieval-quality/) | Measure quality and tune HNSW parameters. | <span class="pill">Python</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Multivector Reranking](/documentation/search-precision/reranking-semantic-search/) | Use multivector representations for better ranking. | Python | 30m | Intermediate |
|
| [Multivector Reranking](/documentation/search-precision/reranking-semantic-search/) | Use multivector representations for better ranking. | <span class="pill">Python</span> | 30m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Hybrid Search Reranking](/documentation/tutorials-search-engineering/reranking-hybrid-search/) | Implement late interaction and sparse reranking. | Python | 40m | Intermediate |
|
| [Hybrid Search Reranking](/documentation/tutorials-search-engineering/reranking-hybrid-search/) | Implement late interaction and sparse reranking. | <span class="pill">Python</span> | 40m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Semantic Code Search](/documentation/tutorials-search-engineering/code-search/) | Navigate codebases using vector similarity. | Python | 45m | Intermediate |
|
| [Semantic Code Search](/documentation/tutorials-search-engineering/code-search/) | Navigate codebases using vector similarity. | <span class="pill">Python</span> | 45m | <span class="text-yellow">Intermediate</span> |
|
||||||
| [Static Embeddings Analysis](/documentation/tutorials-search-engineering/static-embeddings/) | Evaluate the renaissance of static embeddings. | Python | 20m | Intermediate |
|
| [Static Embeddings Analysis](/documentation/tutorials-search-engineering/static-embeddings/) | Evaluate the renaissance of static embeddings. | <span class="pill">Python</span> | 20m | <span class="text-yellow">Intermediate</span> |
|
||||||
@@ -82,7 +82,7 @@ content:
|
|||||||
description: Start with our beginner-friendly articles on vector embeddings and basic concepts.
|
description: Start with our beginner-friendly articles on vector embeddings and basic concepts.
|
||||||
link:
|
link:
|
||||||
text: Start Learning
|
text: Start Learning
|
||||||
url: /documentation/tutorials-quickstart/
|
url: /documentation/tutorials-basics/
|
||||||
- id: 2
|
- id: 2
|
||||||
icon:
|
icon:
|
||||||
src: /icons/outline/hacker-purple.svg
|
src: /icons/outline/hacker-purple.svg
|
||||||
|
|||||||
+1
-1
@@ -1,7 +1,7 @@
|
|||||||
---
|
---
|
||||||
#Delimiter files are used to separate the list of documentation pages into sections.
|
#Delimiter files are used to separate the list of documentation pages into sections.
|
||||||
type: reference
|
type: reference
|
||||||
reference: /documentation/tutorials-quickstart
|
reference: /documentation/tutorials-basics
|
||||||
weight: 311
|
weight: 311
|
||||||
sitemapExclude: True
|
sitemapExclude: True
|
||||||
_build:
|
_build:
|
||||||
@@ -0,0 +1,11 @@
|
|||||||
|
---
|
||||||
|
#Delimiter files are used to separate the list of documentation pages into sections.
|
||||||
|
type: reference
|
||||||
|
reference: /documentation/tutorials-develop
|
||||||
|
weight: 315
|
||||||
|
sitemapExclude: True
|
||||||
|
_build:
|
||||||
|
publishResources: false
|
||||||
|
render: never
|
||||||
|
partition: learn
|
||||||
|
---
|
||||||
@@ -2,7 +2,7 @@
|
|||||||
#Delimiter files are used to separate the list of documentation pages into sections.
|
#Delimiter files are used to separate the list of documentation pages into sections.
|
||||||
type: reference
|
type: reference
|
||||||
reference: /documentation/tutorials-ecosystem
|
reference: /documentation/tutorials-ecosystem
|
||||||
weight: 314
|
weight: 316
|
||||||
sitemapExclude: True
|
sitemapExclude: True
|
||||||
_build:
|
_build:
|
||||||
publishResources: false
|
publishResources: false
|
||||||
|
|||||||
@@ -2,7 +2,7 @@
|
|||||||
#Delimiter files are used to separate the list of documentation pages into sections.
|
#Delimiter files are used to separate the list of documentation pages into sections.
|
||||||
type: reference
|
type: reference
|
||||||
reference: /documentation/tutorials-operations
|
reference: /documentation/tutorials-operations
|
||||||
weight: 315
|
weight: 314
|
||||||
sitemapExclude: True
|
sitemapExclude: True
|
||||||
_build:
|
_build:
|
||||||
publishResources: false
|
publishResources: false
|
||||||
|
|||||||
@@ -14,3 +14,68 @@
|
|||||||
@import 'partials/documentation/docs-footer';
|
@import 'partials/documentation/docs-footer';
|
||||||
@import 'partials/video';
|
@import 'partials/video';
|
||||||
@import 'search/dark-theme';
|
@import 'search/dark-theme';
|
||||||
|
|
||||||
|
// Table Custom Styling
|
||||||
|
.documentation {
|
||||||
|
table {
|
||||||
|
width: 100%;
|
||||||
|
border-collapse: collapse;
|
||||||
|
margin: 1rem 0;
|
||||||
|
|
||||||
|
th {
|
||||||
|
text-align: left;
|
||||||
|
padding: 8px 10px;
|
||||||
|
}
|
||||||
|
|
||||||
|
td {
|
||||||
|
padding: 8px 10px;
|
||||||
|
vertical-align: middle;
|
||||||
|
line-height: 1.4;
|
||||||
|
|
||||||
|
// Link styling
|
||||||
|
a {
|
||||||
|
color: #DC244C;
|
||||||
|
text-decoration: none;
|
||||||
|
&:hover {
|
||||||
|
text-decoration: underline;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
tr {
|
||||||
|
// transition for the background color change
|
||||||
|
transition: background-color 0.2s ease;
|
||||||
|
|
||||||
|
&:hover {
|
||||||
|
// hover color highlight
|
||||||
|
background-color: rgba(59, 130, 246, 0.05);
|
||||||
|
|
||||||
|
// make the link slightly more prominent on hover
|
||||||
|
td a {
|
||||||
|
color: darken(#ef4444, 10%);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Ensure the header row doesn't highlight on hover
|
||||||
|
thead tr:hover {
|
||||||
|
background-color: transparent;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Stack Pill Styling
|
||||||
|
.pill {
|
||||||
|
display: inline-block;
|
||||||
|
padding: 1px 8px;
|
||||||
|
border-radius: 12px;
|
||||||
|
border: 1px solid #DC244C;
|
||||||
|
color: #DC244C;
|
||||||
|
//background-color: rgba(59, 130, 246, 0.1);
|
||||||
|
font-size: 0.85rem;
|
||||||
|
}
|
||||||
|
|
||||||
|
// Level Color-Coding
|
||||||
|
.text-green { color: #10b981 }
|
||||||
|
.text-yellow { color: #f59e0b }
|
||||||
|
.text-red { color: #ef4444 }
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user