From 8a3a40c55b538cc62503cb0ae942949b31dd94a3 Mon Sep 17 00:00:00 2001 From: Maddie Duhon Date: Fri, 6 Jun 2025 13:08:03 -0400 Subject: [PATCH 01/15] Blog-create-n8n-node-blog --- qdrant-landing/content/blog/n8n-node.md | 129 ++++++++++++++++++++++++ 1 file changed, 129 insertions(+) create mode 100644 qdrant-landing/content/blog/n8n-node.md diff --git a/qdrant-landing/content/blog/n8n-node.md b/qdrant-landing/content/blog/n8n-node.md new file mode 100644 index 000000000..b53f1cbe5 --- /dev/null +++ b/qdrant-landing/content/blog/n8n-node.md @@ -0,0 +1,129 @@ +--- +title: "​​Introducing the Official Qdrant Node for n8n: Native, Powerful, and Ready for Hybrid Search" +draft: false +slug: n8n-node +short_description: Qdrant now has an official, team-supported node for n8n +description: Qdrant now has an official, team-supported node for n8n +preview_image: /case-studies/iris/irisagent-qdrant.png + +date: 2025-06-06 +author: Evgeniya (Jenny) Sukhodolskaya +featured: false +tags: + - news + - blog + - n8n + +--- + +## ​​Introducing the Official Qdrant Node for n8n: Native, Powerful, and Ready for Hybrid Search +Amazing news for n8n builders working with semantic search: Qdrant now has an official, team-supported node for n8n, available as a verified community note\! +This new integration brings the full power of Qdrant’s vector database directly into your n8n workflows: no more wrestling with HTTP nodes or manual API calls. +Whether you’re building RAG systems, intelligent agents, or advanced unstructured data analysis tools, this node is designed to make your life easier and your solutions more robust. + +## **Why This Matters** + +Previously, integrating Qdrant with n8n meant manually configuring HTTP requests for every operation, limiting access to advanced features like batch upserts, custom embeddings, and hybrid search. + +The new Qdrant node changes that. + +It supports everything Qdrant can do, including hybrid search, reranking with multivectors, batch upserts and updates, sophisticated filtering, and compatibility with the latest [Qdrant 1.14.0](https://qdrant.tech/blog/qdrant-1.14.x/) release. + +The Qdrant node is not just a wrapper; it’s a fully-featured, officially maintained integration. + +**Getting Started: Installation Is a Click Away** + +The Qdrant node is available for both cloud and self-hosted n8n instances, starting from version 1.94.0. Installing it is as simple as searching for “Qdrant” in the n8n integrations panel and clicking “Install.” You’ll be up and running in seconds. +**Unlocking Hybrid Search: A Step-by-Step Guide** + +One of the most exciting features of the new node is seamless hybrid search: combining the precision of keyword-based (sparse) search with the semantic power of dense embeddings. This is especially valuable in domains like legal or medical search, where both exact matches and contextual understanding are crucial. + +\ Here’s a quick walkthrough: 1\. Create a Hybrid Collection From b509a71e458f3c82f1d6c8867d28181eeaedf01c Mon Sep 17 00:00:00 2001 From: Maddie Duhon Date: Fri, 6 Jun 2025 14:22:52 -0400 Subject: [PATCH 05/15] header --- qdrant-landing/content/blog/n8n-node.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/qdrant-landing/content/blog/n8n-node.md b/qdrant-landing/content/blog/n8n-node.md index b6a466350..60da4eeae 100644 --- a/qdrant-landing/content/blog/n8n-node.md +++ b/qdrant-landing/content/blog/n8n-node.md @@ -116,7 +116,7 @@ The Qdrant node for n8n is just the beginning. You can now build advanced RAG ch We welcome your feedback, suggestions, and contributions on GitHub\! Don’t forget to star the repo and join our Discord community if you have questions or want to connect with other users. -##Resources: +## Resources: * [Qdrant n8n Node on npm](https://www.npmjs.com/package/n8n-nodes-qdrant) * [GitHub Repo](https://github.com/qdrant/n8n-nodes-qdrant) From f682cbed01609acbf040a77334784580e9df8b76 Mon Sep 17 00:00:00 2001 From: Anush Date: Fri, 6 Jun 2025 23:58:23 +0530 Subject: [PATCH 06/15] Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --- qdrant-landing/content/blog/n8n-node.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/qdrant-landing/content/blog/n8n-node.md b/qdrant-landing/content/blog/n8n-node.md index 60da4eeae..379c7c8dc 100644 --- a/qdrant-landing/content/blog/n8n-node.md +++ b/qdrant-landing/content/blog/n8n-node.md @@ -54,7 +54,7 @@ json "lexical": {} } -Dense vectors are for semantic search; sparse vectors handle keyword searches. The sparse vector configuration is simple—just specify the name, as the size is dynamic1. +Dense vectors are for semantic search; sparse vectors handle keyword searches. The sparse vector configuration is simple—just specify the name, as the size is dynamic. 2\. Insert Data Points @@ -80,7 +80,7 @@ json } \] -Batch upserts are now supported natively, making large-scale data ingestion fast and simple1. +Batch upserts are now supported natively, making large-scale data ingestion fast and simple. 3\. Run a Hybrid Search @@ -112,7 +112,7 @@ This approach retrieves top results from both semantic and lexical searches and ## Explore More and Get Involved -The Qdrant node for n8n is just the beginning. You can now build advanced RAG chatbots, agents for unstructured big data analysis, and much more, all natively within n8n1. If you want to see more tutorials or have specific use cases in mind, let us know in the comments or join our community discussions. +The Qdrant node for n8n is just the beginning. You can now build advanced RAG chatbots, agents for unstructured big data analysis, and much more, all natively within n8n. If you want to see more tutorials or have specific use cases in mind, let us know in the comments or join our community discussions. We welcome your feedback, suggestions, and contributions on GitHub\! Don’t forget to star the repo and join our Discord community if you have questions or want to connect with other users. From 8127784ffecaf54c97965f20b535701dd9ac3492 Mon Sep 17 00:00:00 2001 From: Anush Date: Fri, 6 Jun 2025 23:59:01 +0530 Subject: [PATCH 07/15] Update qdrant-landing/content/blog/n8n-node.md --- qdrant-landing/content/blog/n8n-node.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/qdrant-landing/content/blog/n8n-node.md b/qdrant-landing/content/blog/n8n-node.md index 379c7c8dc..91eb8862d 100644 --- a/qdrant-landing/content/blog/n8n-node.md +++ b/qdrant-landing/content/blog/n8n-node.md @@ -114,7 +114,7 @@ This approach retrieves top results from both semantic and lexical searches and The Qdrant node for n8n is just the beginning. You can now build advanced RAG chatbots, agents for unstructured big data analysis, and much more, all natively within n8n. If you want to see more tutorials or have specific use cases in mind, let us know in the comments or join our community discussions. -We welcome your feedback, suggestions, and contributions on GitHub\! Don’t forget to star the repo and join our Discord community if you have questions or want to connect with other users. +We welcome your feedback, suggestions, and contributions on GitHub! Don’t forget to star the repo and join our Discord community if you have questions or want to connect with other users. ## Resources: From 9f98a1ee89a308f4d763212f2fc8ec6740ba28d8 Mon Sep 17 00:00:00 2001 From: Anush008 Date: Sat, 7 Jun 2025 00:03:39 +0530 Subject: [PATCH 08/15] chore: Formatting Signed-off-by: Anush008 --- qdrant-landing/content/blog/n8n-node.md | 61 +++++++++++++------------ 1 file changed, 33 insertions(+), 28 deletions(-) diff --git a/qdrant-landing/content/blog/n8n-node.md b/qdrant-landing/content/blog/n8n-node.md index 91eb8862d..8b14da0c4 100644 --- a/qdrant-landing/content/blog/n8n-node.md +++ b/qdrant-landing/content/blog/n8n-node.md @@ -15,37 +15,38 @@ tags: --- -## ​​Introducing the Official Qdrant Node for n8n: Native, Powerful, and Ready for Hybrid Search +## ​​Introducing the Official Qdrant Node for n8n: Native, Powerful, and Ready for Hybrid Search -Amazing news for n8n builders working with semantic search: Qdrant now has an official, team-supported node for n8n, available as a verified community note! -This new integration brings the full power of Qdrant’s vector database directly into your n8n workflows: no more wrestling with HTTP nodes or manual API calls. +Amazing news for n8n builders working with semantic search: Qdrant now has an official, team-supported node for n8n, available as a verified community note! +This new integration brings the full power of Qdrant’s vector database directly into your n8n workflows: no more wrestling with HTTP nodes or manual API calls. Whether you’re building RAG systems, intelligent agents, or advanced unstructured data analysis tools, this node is designed to make your life easier and your solutions more robust. ## Why This Matters -Previously, integrating Qdrant with n8n meant manually configuring HTTP requests for every operation, limiting access to advanced features like batch upserts, custom embeddings, and hybrid search. +Previously, integrating Qdrant with n8n meant manually configuring HTTP requests for every operation, limiting access to advanced features like batch upserts, custom embeddings, and hybrid search. -The new Qdrant node changes that. +The new Qdrant node changes that. It supports everything Qdrant can do, including hybrid search, reranking with multivectors, batch upserts and updates, sophisticated filtering, and compatibility with the latest [Qdrant 1.14.0](https://qdrant.tech/blog/qdrant-1.14.x/) release. -The Qdrant node is not just a wrapper; it’s a fully-featured, officially maintained integration. +The Qdrant node is not just a wrapper; it’s a fully-featured, officially maintained integration. The Qdrant node is available for both cloud and self-hosted n8n instances, starting from version 1.94.0. Installing it is as simple as searching for “Qdrant” in the n8n integrations panel and clicking “Install.” You’ll be up and running in seconds. -## Unlocking Hybrid Search: A Step-by-Step Guide +## Unlocking Hybrid Search: A Step-by-Step Guide One of the most exciting features of the new node is seamless hybrid search: combining the precision of keyword-based (sparse) search with the semantic power of dense embeddings. This is especially valuable in domains like legal or medical search, where both exact matches and contextual understanding are crucial. Here’s a quick walkthrough: -1\. Create a Hybrid Collection + +1. Create a Hybrid Collection * Use Qdrant Cloud’s free tier for experimentation. * Create a collection that supports both dense (semantic) and sparse (lexical) vectors. For example: -json +```json { "semantic": { "size": 4, @@ -53,60 +54,64 @@ json }, "lexical": {} } +``` Dense vectors are for semantic search; sparse vectors handle keyword searches. The sparse vector configuration is simple—just specify the name, as the size is dynamic. -2\. Insert Data Points +2. Insert Data Points * Insert points with both dense and sparse vectors. Here’s a sample payload: -json -\[ +```json +[ { "id": "209ed309-bb5e-47fd-8af6-a54eea28e0e7", "payload": {}, "vector": { - "semantic": \[0.3, 0.1, 0.4, 0.2\], - "lexical": {"indices":\[1, 2\], "values": \[0.2, \-0.5\]} + "semantic": [0.3, 0.1, 0.4, 0.2], + "lexical": {"indices":[1, 2], "values": [0.2, -0.5]} } }, { "id": "f7e8316e-91da-4b97-9ae9-7503e6cdbd7b", "payload": {}, "vector": { - "semantic": \[0.4, 0.0, \-0.4, 0.2\], - "lexical": {"indices":\[54\], "values": \[\-0.9\]} + "semantic": [0.4, 0.0, -0.4, 0.2], + "lexical": {"indices":[54], "values": \[-0.9]} } } -\] +] +``` Batch upserts are now supported natively, making large-scale data ingestion fast and simple. -3\. Run a Hybrid Search +3. Run a Hybrid Search -* Use the query\_points operation to perform hybrid searches. For example: +* Use the query_points operation to perform hybrid searches. For example: -json -\[ +```json +[ { - "query": \[0.0, 0.6, 0.7, 0.9\], + "query": [0.0, 0.6, 0.7, 0.9], "using": "semantic", "limit": 2 }, { "query": { - "indices": \[55, 2\], - "values": \[0.6, 0.7\] + "indices": [55, 2], + "values": [0.6, 0.7] }, "using": "lexical", "limit": 2 } -\] +] +``` * Merge results using reciprocal rank fusion (RRF): -json +```json {"fusion": "rrf"} +``` This approach retrieves top results from both semantic and lexical searches and fuses them, delivering more relevant outcomes,especially for complex, domain-specific queries. @@ -116,11 +121,11 @@ The Qdrant node for n8n is just the beginning. You can now build advanced RAG ch We welcome your feedback, suggestions, and contributions on GitHub! Don’t forget to star the repo and join our Discord community if you have questions or want to connect with other users. -## Resources: +## Resources * [Qdrant n8n Node on npm](https://www.npmjs.com/package/n8n-nodes-qdrant) * [GitHub Repo](https://github.com/qdrant/n8n-nodes-qdrant) * [Video: Connecting Qdrant to n8n](https://youtu.be/fYMGpXyAsfQ?feature=shared&t=194) * [Video: Introducing Qdrant's Official n8n Node: Hybrid Search Example](https://www.youtube.com/watch?v=sYP_kHWptHY) * [Hybrid Search Concepts](https://qdrant.tech/documentation/concepts/search/) -* [Qdrant's n8n User Docs](https://qdrant.tech/documentation/platforms/n8n/) \ No newline at end of file +* [Qdrant's n8n User Docs](https://qdrant.tech/documentation/platforms/n8n/) From 59e9d2e1317216de6090bae1f61ecbab333dda51 Mon Sep 17 00:00:00 2001 From: Maddie Duhon Date: Mon, 9 Jun 2025 07:36:03 -0400 Subject: [PATCH 09/15] Jenny-edits --- qdrant-landing/content/blog/n8n-node.md | 16 +++++++--------- 1 file changed, 7 insertions(+), 9 deletions(-) diff --git a/qdrant-landing/content/blog/n8n-node.md b/qdrant-landing/content/blog/n8n-node.md index 8b14da0c4..8ec7d1b58 100644 --- a/qdrant-landing/content/blog/n8n-node.md +++ b/qdrant-landing/content/blog/n8n-node.md @@ -1,11 +1,11 @@ --- -title: "​​Introducing the Official Qdrant Node for n8n: Native, Powerful, and Ready for Hybrid Search" +title: "​​Introducing the Official Qdrant Node for n8n" draft: false slug: n8n-node short_description: Qdrant now has an official, team-supported node for n8n. description: Qdrant now has an official, team-supported node for n8n. preview_image: /blog/n8n-node/n8n-node-blog-hero.jpg -date: 2025-06-07 +date: 2025-06-09 author: Evgeniya (Jenny) Sukhodolskaya featured: false tags: @@ -15,10 +15,10 @@ tags: --- -## ​​Introducing the Official Qdrant Node for n8n: Native, Powerful, and Ready for Hybrid Search +## ​​Introducing the Official Qdrant Node for n8n Amazing news for n8n builders working with semantic search: Qdrant now has an official, team-supported node for n8n, available as a verified community note! -This new integration brings the full power of Qdrant’s vector database directly into your n8n workflows: no more wrestling with HTTP nodes or manual API calls. +This new integration brings the full power of Qdrant’s vector database directly into your n8n workflows: no more wrestling with HTTP nodes. Whether you’re building RAG systems, intelligent agents, or advanced unstructured data analysis tools, this node is designed to make your life easier and your solutions more robust. ## Why This Matters @@ -29,13 +29,11 @@ The new Qdrant node changes that. It supports everything Qdrant can do, including hybrid search, reranking with multivectors, batch upserts and updates, sophisticated filtering, and compatibility with the latest [Qdrant 1.14.0](https://qdrant.tech/blog/qdrant-1.14.x/) release. -The Qdrant node is not just a wrapper; it’s a fully-featured, officially maintained integration. - The Qdrant node is available for both cloud and self-hosted n8n instances, starting from version 1.94.0. Installing it is as simple as searching for “Qdrant” in the n8n integrations panel and clicking “Install.” You’ll be up and running in seconds. -## Unlocking Hybrid Search: A Step-by-Step Guide +## Step-by-Step Example of Hybrid Search -One of the most exciting features of the new node is seamless hybrid search: combining the precision of keyword-based (sparse) search with the semantic power of dense embeddings. This is especially valuable in domains like legal or medical search, where both exact matches and contextual understanding are crucial. +One exciting feature of the new node is seamless hybrid search: combining the precision of keyword-based (sparse) search with the semantic power of dense embeddings. This is especially valuable in domains like legal or medical search, where both exact matches and contextual understanding are crucial. @@ -113,7 +111,7 @@ Batch upserts are now supported natively, making large-scale data ingestion fast {"fusion": "rrf"} ``` -This approach retrieves top results from both semantic and lexical searches and fuses them, delivering more relevant outcomes,especially for complex, domain-specific queries. +This approach retrieves top results from both semantic and lexical searches and fuses them, delivering more relevant outcomes, especially for complex, domain-specific queries. ## Explore More and Get Involved From 8f91a6f3c7555d5b450385530935e548b5ca8564 Mon Sep 17 00:00:00 2001 From: Maddie Duhon Date: Mon, 9 Jun 2025 09:12:07 -0400 Subject: [PATCH 10/15] Deleted-code --- qdrant-landing/content/blog/n8n-node.md | 78 +------------------------ 1 file changed, 2 insertions(+), 76 deletions(-) diff --git a/qdrant-landing/content/blog/n8n-node.md b/qdrant-landing/content/blog/n8n-node.md index 8ec7d1b58..7ba42f7d4 100644 --- a/qdrant-landing/content/blog/n8n-node.md +++ b/qdrant-landing/content/blog/n8n-node.md @@ -35,84 +35,10 @@ The Qdrant node is available for both cloud and self-hosted n8n instances, start One exciting feature of the new node is seamless hybrid search: combining the precision of keyword-based (sparse) search with the semantic power of dense embeddings. This is especially valuable in domains like legal or medical search, where both exact matches and contextual understanding are crucial. +## Video example: How to install & use the node for hybrid search + -Here’s a quick walkthrough: - -1. Create a Hybrid Collection - -* Use Qdrant Cloud’s free tier for experimentation. -* Create a collection that supports both dense (semantic) and sparse (lexical) vectors. For example: - -```json -{ - "semantic": { - "size": 4, - "distance": "Cosine" - }, - "lexical": {} -} -``` - -Dense vectors are for semantic search; sparse vectors handle keyword searches. The sparse vector configuration is simple—just specify the name, as the size is dynamic. - -2. Insert Data Points - -* Insert points with both dense and sparse vectors. Here’s a sample payload: - -```json -[ - { - "id": "209ed309-bb5e-47fd-8af6-a54eea28e0e7", - "payload": {}, - "vector": { - "semantic": [0.3, 0.1, 0.4, 0.2], - "lexical": {"indices":[1, 2], "values": [0.2, -0.5]} - } - }, - { - "id": "f7e8316e-91da-4b97-9ae9-7503e6cdbd7b", - "payload": {}, - "vector": { - "semantic": [0.4, 0.0, -0.4, 0.2], - "lexical": {"indices":[54], "values": \[-0.9]} - } - } -] -``` - -Batch upserts are now supported natively, making large-scale data ingestion fast and simple. - -3. Run a Hybrid Search - -* Use the query_points operation to perform hybrid searches. For example: - -```json -[ - { - "query": [0.0, 0.6, 0.7, 0.9], - "using": "semantic", - "limit": 2 - }, - { - "query": { - "indices": [55, 2], - "values": [0.6, 0.7] - }, - "using": "lexical", - "limit": 2 - } -] -``` - -* Merge results using reciprocal rank fusion (RRF): - -```json -{"fusion": "rrf"} -``` - -This approach retrieves top results from both semantic and lexical searches and fuses them, delivering more relevant outcomes, especially for complex, domain-specific queries. - ## Explore More and Get Involved The Qdrant node for n8n is just the beginning. You can now build advanced RAG chatbots, agents for unstructured big data analysis, and much more, all natively within n8n. If you want to see more tutorials or have specific use cases in mind, let us know in the comments or join our community discussions. From dea6c6323e8d55a1f8a7ff95fd309c71a9b7b062 Mon Sep 17 00:00:00 2001 From: Maddie Duhon Date: Mon, 9 Jun 2025 09:23:13 -0400 Subject: [PATCH 11/15] updated-header --- qdrant-landing/content/blog/n8n-node.md | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/qdrant-landing/content/blog/n8n-node.md b/qdrant-landing/content/blog/n8n-node.md index 7ba42f7d4..267e05f95 100644 --- a/qdrant-landing/content/blog/n8n-node.md +++ b/qdrant-landing/content/blog/n8n-node.md @@ -31,11 +31,9 @@ It supports everything Qdrant can do, including hybrid search, reranking with mu The Qdrant node is available for both cloud and self-hosted n8n instances, starting from version 1.94.0. Installing it is as simple as searching for “Qdrant” in the n8n integrations panel and clicking “Install.” You’ll be up and running in seconds. -## Step-by-Step Example of Hybrid Search +## Video example: How to install & use the node for hybrid search -One exciting feature of the new node is seamless hybrid search: combining the precision of keyword-based (sparse) search with the semantic power of dense embeddings. This is especially valuable in domains like legal or medical search, where both exact matches and contextual understanding are crucial. - -## Video example: How to install & use the node for hybrid search +One exciting feature of the new node is seamless hybrid search: combining the precision of keyword-based (sparse) search with the semantic power of dense embeddings. This is especially valuable in domains like legal or medical search, where both exact matches and contextual understanding are crucial. Watch this video for a walkthrough. From a6b585e646d8d06a575721589f26a0899f736a4c Mon Sep 17 00:00:00 2001 From: Anush Date: Mon, 9 Jun 2025 18:55:09 +0530 Subject: [PATCH 12/15] Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> --- qdrant-landing/content/blog/n8n-node.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/qdrant-landing/content/blog/n8n-node.md b/qdrant-landing/content/blog/n8n-node.md index 267e05f95..6690c7cc7 100644 --- a/qdrant-landing/content/blog/n8n-node.md +++ b/qdrant-landing/content/blog/n8n-node.md @@ -17,7 +17,7 @@ tags: ## ​​Introducing the Official Qdrant Node for n8n -Amazing news for n8n builders working with semantic search: Qdrant now has an official, team-supported node for n8n, available as a verified community note! +Amazing news for n8n builders working with semantic search: Qdrant now has an official, team-supported node for n8n, available as a verified community node! This new integration brings the full power of Qdrant’s vector database directly into your n8n workflows: no more wrestling with HTTP nodes. Whether you’re building RAG systems, intelligent agents, or advanced unstructured data analysis tools, this node is designed to make your life easier and your solutions more robust. @@ -35,7 +35,7 @@ The Qdrant node is available for both cloud and self-hosted n8n instances, start One exciting feature of the new node is seamless hybrid search: combining the precision of keyword-based (sparse) search with the semantic power of dense embeddings. This is especially valuable in domains like legal or medical search, where both exact matches and contextual understanding are crucial. Watch this video for a walkthrough. - + ## Explore More and Get Involved From d56984320fa00f4ad1d3c92561cd6355023c95dc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=D0=95=D0=B2=D0=B3=D0=B5=D0=BD=D0=B8=D1=8F=20=D0=A1=D1=83?= =?UTF-8?q?=D1=85=D0=BE=D0=B4=D0=BE=D0=BB=D1=8C=D1=81=D0=BA=D0=B0=D1=8F?= Date: Mon, 9 Jun 2025 15:32:00 +0200 Subject: [PATCH 13/15] on terminology --- qdrant-landing/content/blog/n8n-node.md | 32 ++++++++++++++----------- 1 file changed, 18 insertions(+), 14 deletions(-) diff --git a/qdrant-landing/content/blog/n8n-node.md b/qdrant-landing/content/blog/n8n-node.md index 6690c7cc7..11c51e697 100644 --- a/qdrant-landing/content/blog/n8n-node.md +++ b/qdrant-landing/content/blog/n8n-node.md @@ -6,7 +6,7 @@ short_description: Qdrant now has an official, team-supported node for n8n. description: Qdrant now has an official, team-supported node for n8n. preview_image: /blog/n8n-node/n8n-node-blog-hero.jpg date: 2025-06-09 -author: Evgeniya (Jenny) Sukhodolskaya +author: Maddie Duhon & Evgeniya Sukhodolskaya featured: false tags: - news @@ -17,37 +17,41 @@ tags: ## ​​Introducing the Official Qdrant Node for n8n -Amazing news for n8n builders working with semantic search: Qdrant now has an official, team-supported node for n8n, available as a verified community node! -This new integration brings the full power of Qdrant’s vector database directly into your n8n workflows: no more wrestling with HTTP nodes. -Whether you’re building RAG systems, intelligent agents, or advanced unstructured data analysis tools, this node is designed to make your life easier and your solutions more robust. +Amazing news for n8n builders working with semantic search: Qdrant now has an [official, team-supported node for n8n](https://www.npmjs.com/package/n8n-nodes-qdrant), an early adopter of n8n's new [verified community nodes](https://docs.n8n.io/integrations/creating-nodes/deploy/submit-community-nodes/#submit-your-node-for-verification-by-n8n) feature! + +This new integration brings the full power of Qdrant directly into your n8n workflows: no more wrestling with HTTP nodes ever again! +Whether you’re building RAG systems, agentic pipelines, or advanced data analysis tools, this node is designed to make your life easier and your solutions more robust. ## Why This Matters -Previously, integrating Qdrant with n8n meant manually configuring HTTP requests for every operation, limiting access to advanced features like batch upserts, custom embeddings, and hybrid search. +Previously, using Qdrant in n8n frequently meant configuring HTTP request nodes due to limited access to advanced Qdrant features like batch upserts and updates, hybrid search and recommendations, discovery search and distance matrix API, and many, many more. The new Qdrant node changes that. -It supports everything Qdrant can do, including hybrid search, reranking with multivectors, batch upserts and updates, sophisticated filtering, and compatibility with the latest [Qdrant 1.14.0](https://qdrant.tech/blog/qdrant-1.14.x/) release. +It supports everything Qdrant can do, including hybrid queries, reranking with multivectors, sophisticated filtering, and all that the latest [Qdrant 1.14.0](https://qdrant.tech/blog/qdrant-1.14.x/) release provides. -The Qdrant node is available for both cloud and self-hosted n8n instances, starting from version 1.94.0. Installing it is as simple as searching for “Qdrant” in the n8n integrations panel and clicking “Install.” You’ll be up and running in seconds. +The Qdrant node is available for **both cloud and self-hosted n8n instances**, starting from version **1.94.0**. Installing it is as simple as clicking “Install” button, you’ll be up and running in seconds. -## Video example: How to install & use the node for hybrid search +## Start Using it Now: How to Install & Use the Node for Hybrid Search -One exciting feature of the new node is seamless hybrid search: combining the precision of keyword-based (sparse) search with the semantic power of dense embeddings. This is especially valuable in domains like legal or medical search, where both exact matches and contextual understanding are crucial. Watch this video for a walkthrough. +We filmed a short demo for you on how to use this new node for **hybrid search** in Qdrant, as we thought it would be super handy for you to know how to combine the precision of keyword-based (sparse) search with the semantic power of dense embeddings in your n8n solutions. +It's especially valuable in domains like legal or medical, where both exact matches and contextual understanding are crucial, so we love that you now have access to a method that delivers relevant results for complex, domain-specific queries! + +This toy example walks you through fusing dense and lexical hybrid search results using Reciprocal Rank Fusion (RRF). +Naturally, you don't have to stop at a simple example! Everything we suggested in our [Hybrid Search article](https://qdrant.tech/articles/hybrid-search/) is now possible to use natively, even our latest [Score-Boosting Reranker](https://qdrant.tech/blog/qdrant-1.14.x/#score-boosting-reranker), which allows for complete customization of the rescoring formula. + ## Explore More and Get Involved -The Qdrant node for n8n is just the beginning. You can now build advanced RAG chatbots, agents for unstructured big data analysis, and much more, all natively within n8n. If you want to see more tutorials or have specific use cases in mind, let us know in the comments or join our community discussions. +This example is just the beginning. You can now build Qdrant-based solutions, from advanced RAG to complicated agentic systems, all natively within n8n. If you want to see more tutorials or have specific use cases in mind, let us know in the comments on the video or join our community discussions. -We welcome your feedback, suggestions, and contributions on GitHub! Don’t forget to star the repo and join our Discord community if you have questions or want to connect with other users. +We welcome your feedback, suggestions, and contributions on GitHub! Don’t forget to star the [new node's repo]((https://github.com/qdrant/n8n-nodes-qdrant) and join our [Discord community]((https://discord.gg/njJFNKXj)) if you have questions or want to connect with other users. ## Resources * [Qdrant n8n Node on npm](https://www.npmjs.com/package/n8n-nodes-qdrant) * [GitHub Repo](https://github.com/qdrant/n8n-nodes-qdrant) * [Video: Connecting Qdrant to n8n](https://youtu.be/fYMGpXyAsfQ?feature=shared&t=194) -* [Video: Introducing Qdrant's Official n8n Node: Hybrid Search Example](https://www.youtube.com/watch?v=sYP_kHWptHY) -* [Hybrid Search Concepts](https://qdrant.tech/documentation/concepts/search/) -* [Qdrant's n8n User Docs](https://qdrant.tech/documentation/platforms/n8n/) +* [Qdrant's n8n User Docs](https://qdrant.tech/documentation/platforms/n8n/) \ No newline at end of file From 30bb9621dc36d2cff4d14ac791db1fba5a883e2f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=D0=95=D0=B2=D0=B3=D0=B5=D0=BD=D0=B8=D1=8F=20=D0=A1=D1=83?= =?UTF-8?q?=D1=85=D0=BE=D0=B4=D0=BE=D0=BB=D1=8C=D1=81=D0=BA=D0=B0=D1=8F?= Date: Mon, 9 Jun 2025 15:33:23 +0200 Subject: [PATCH 14/15] typos --- qdrant-landing/content/blog/n8n-node.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/qdrant-landing/content/blog/n8n-node.md b/qdrant-landing/content/blog/n8n-node.md index 11c51e697..17f039883 100644 --- a/qdrant-landing/content/blog/n8n-node.md +++ b/qdrant-landing/content/blog/n8n-node.md @@ -47,7 +47,7 @@ Naturally, you don't have to stop at a simple example! Everything we suggested i This example is just the beginning. You can now build Qdrant-based solutions, from advanced RAG to complicated agentic systems, all natively within n8n. If you want to see more tutorials or have specific use cases in mind, let us know in the comments on the video or join our community discussions. -We welcome your feedback, suggestions, and contributions on GitHub! Don’t forget to star the [new node's repo]((https://github.com/qdrant/n8n-nodes-qdrant) and join our [Discord community]((https://discord.gg/njJFNKXj)) if you have questions or want to connect with other users. +We welcome your feedback, suggestions, and contributions on GitHub! Don’t forget to star the [new node's repo](https://github.com/qdrant/n8n-nodes-qdrant) and join our [Discord community](https://discord.gg/njJFNKXj) if you have questions or want to connect with other users. ## Resources From 13bd83f1903155bed19c8bc1b463e667e0f4ec52 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=D0=95=D0=B2=D0=B3=D0=B5=D0=BD=D0=B8=D1=8F=20=D0=A1=D1=83?= =?UTF-8?q?=D1=85=D0=BE=D0=B4=D0=BE=D0=BB=D1=8C=D1=81=D0=BA=D0=B0=D1=8F?= Date: Mon, 9 Jun 2025 15:38:39 +0200 Subject: [PATCH 15/15] featured --- qdrant-landing/content/blog/n8n-node.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/qdrant-landing/content/blog/n8n-node.md b/qdrant-landing/content/blog/n8n-node.md index 17f039883..9a536514c 100644 --- a/qdrant-landing/content/blog/n8n-node.md +++ b/qdrant-landing/content/blog/n8n-node.md @@ -7,7 +7,7 @@ description: Qdrant now has an official, team-supported node for n8n. preview_image: /blog/n8n-node/n8n-node-blog-hero.jpg date: 2025-06-09 author: Maddie Duhon & Evgeniya Sukhodolskaya -featured: false +featured: true tags: - news - blog @@ -35,6 +35,7 @@ The Qdrant node is available for **both cloud and self-hosted n8n instances**, s ## Start Using it Now: How to Install & Use the Node for Hybrid Search We filmed a short demo for you on how to use this new node for **hybrid search** in Qdrant, as we thought it would be super handy for you to know how to combine the precision of keyword-based (sparse) search with the semantic power of dense embeddings in your n8n solutions. + It's especially valuable in domains like legal or medical, where both exact matches and contextual understanding are crucial, so we love that you now have access to a method that delivers relevant results for complex, domain-specific queries! This toy example walks you through fusing dense and lexical hybrid search results using Reciprocal Rank Fusion (RRF).