krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-09-26 14:38:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update AI getting started prompt.

Browse Source
This commit is contained in:
István Zoltán Szabó
2026-09-22 15:32:02 +02:00
parent 08f307d7ef
commit 63e11d447f
2 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/documentation/agentic-tools/_index.md
+1 -1
View File
@@ -14,7 +14,7 @@ Use them to give your agent task-specific guidance, troubleshoot existing deploy
## Start Building ## Start Building
If you're new to Qdrant, the Start building on Qdrant prompt takes your coding assistant from an empty project to a working search query. If you're new to Qdrant, the Start building on Qdrant prompt takes your coding assistant from an empty project to a working search query.
It stands up a local instance, installs the client with local embeddings, adds the [Qdrant Advisor](/documentation/agentic-tools/skills/#the-qdrant-advisor) skill, and then builds against your own use case. It stands up a local instance, installs the client with local embeddings, adds the [Qdrant Advisor](/documentation/agentic-tools/skills/#the-qdrant-advisor) skill, and then either runs a quick demo on sample data or builds against your own use case.
{{< prompt "start-building" >}} {{< prompt "start-building" >}}
qdrant-landing/content/documentation/headless/prompts/start-building.md
+5 -1
View File
@@ -28,7 +28,11 @@ Help me get started building on Qdrant.
3. Install the Qdrant Advisor agent skill: 3. Install the Qdrant Advisor agent skill:
npx skills add qdrant/skills/meta/qdrant-advisor npx skills add qdrant/skills/meta/qdrant-advisor
4. Then ask me what I'm building and what I'll search over before you write any code. Once you know, build the integration against my local instance, and get the collection right the first time: 4. Ask me whether I want a quick demo with sample data, or want to build against my own data.
5. If I want a demo: install qdrant-client[fastembed] for it even if I chose a different language above, download https://raw.githubusercontent.com/qdrant/examples/refs/heads/master/ai-getting-started/demo.py and https://raw.githubusercontent.com/qdrant/examples/refs/heads/master/ai-getting-started/menu-items.json into the same folder, and run python demo.py unmodified. Do not write your own version of this script. It creates a collection called items sized for sentence-transformers/all-MiniLM-L6-v2 (384 dimensions, cosine distance), embeds and upserts the 30 sample menu items locally, and runs three example searches. Show me the output, then ask if I want to continue by building against my own data.
6. If I want to build against my own data, or once the demo is done: ask me what I'm building and what I'll search over before you write any code. Once you know, build the integration against my local instance, and get the collection right the first time:
- Derive the vector size from the embedding model itself. Never hardcode a dimension. - Derive the vector size from the embedding model itself. Never hardcode a dimension.
- Choose the distance metric the model was trained for, and say which one you picked and why. - Choose the distance metric the model was trained for, and say which one you picked and why.
- Create a payload index for every field I'll filter on, before I load data rather than after. - Create a payload index for every field I'll filter on, before I load data rather than after.