VL Chat

Explore and search your visual datasets using natural language queries with VL Chat’s conversational interface.

VL Chat enables you to explore visual datasets through natural language. Instead of navigating filters and dropdown menus, ask questions directly — find images by quality issue, label, tag, custom metadata, or cluster. The system interprets your intent and returns results with explanations of what it found.

Common Use Cases

VL Chat supports a range of workflows across dataset exploration and curation:

Use Case	Description	Examples
Quality Assurance	Quickly identify and review quality issues.	”Show me all blur issues from today’s production run” “Find outlier images in batch 12345” “Display mislabeled images above 90% confidence”
Dataset Curation	Organize and filter datasets for training.	”Show me the most unique images from each cluster” “Find images labeled as cats that don’t have the reviewed tag” “Display images with low uniqueness scores”
Research and Analysis	Explore dataset composition and patterns.	”Show me the largest clusters” “Find images with the most labels” “Display images that appear in multiple clusters”

How to Use VL Chat

To access VL Chat, open any dataset in Visual Layer and click in the top navigation bar. The chat interface appears as a panel on the right side of your screen, allowing you to explore while viewing your dataset.

Each dataset maintains its own conversation thread, which persists across sessions. To start a fresh conversation, click New Thread in the chat panel.

Asking Questions

Type your question in natural language into the chat input field and press Enter. VL Chat processes your query and returns results along with an explanation of what it understood and what it found.

Query capabilities depend on the dataset configuration. VL Chat can only search fields that exist in your data: datasets without annotations cannot filter by labels, and cluster-based queries require Similarity Clusters to be generated first. If you reference a field that isn’t configured, the system explains this and applies the filters it can.

Example queries:

• “Show me images with blur issues”
• “Find all images tagged as defective”
• “Display images from cluster 5”
• “Show me images with high uniqueness scores”
• “Find images labeled as cats”

Types of Queries You Can Ask

VL Chat understands queries about different aspects of your dataset:

Type	Description	Examples
Filter by Issues	Find images with specific quality issues detected by Visual Layer.	”Show me blurry images” “Find all images with duplicates” “Display images that have outlier issues” “Show me images with mislabel issues above 80% confidence”
Filter by Labels	Search for specific labels or annotations in your dataset.	”Show me images labeled as cats” “Find all images with car labels” “Display images labeled as defective”
Filter by Tags	Query images based on user-assigned tags.	”Show me images tagged as urgent” “Find all images with the reviewed tag” “Display images tagged for training”
Filter by Custom Metadata	Query Custom Metadata fields directly if your dataset includes them.	”Show me images with temperature above 30” “Find images from Station A” “Display images where batch number is 12345”
Navigate Clusters	Explore Similarity Clusters in your dataset.	”Show me cluster 5” “Display the largest cluster” “Find clusters with more than 100 images”
Combine Multiple Criteria	Build complex queries by combining different filter types.	”Show me blurry images from cluster 3” “Find images labeled as cats with high uniqueness scores” “Display images tagged as urgent that also have blur issues”

Tips for Effective Queries

Use these guidelines to get accurate, relevant results from VL Chat:

Rule	Explanation	Good	Less Clear
Be Specific About Filter Types	When referencing labels, tags, or custom fields, use clear terminology.	”Show me images labeled as defective"	"Show me defective images” (could refer to labels, tags, or quality issues)
Use Exact Field Names	For custom metadata, use the exact field name as it appears in your dataset.	”Show me images where Station equals A"	"Show me images from station A” (if the field is named “StationID”)
Specify Thresholds Explicitly	When filtering by numeric values or confidence scores, include specific thresholds.	”Show me blur issues above 85% confidence"	"Show me images with high blur” (what threshold defines “high”?)
Build Complex Queries Iteratively	Start with a simple query and refine it through follow-up questions.	”Show me images with blur” “Now filter to cluster 5” “Show only the ones tagged as urgent"	"Show me blurry images from cluster 5 tagged as urgent”

Understanding Responses

When you ask a question, VL Chat provides:

• Interpretation summary: A clear statement of what the system understood from your query.
• Validation feedback: Information about which parts of your query were applied successfully and which weren’t available.
• Visual results: The actual images or objects matching your criteria.
• Alternative interpretations: Suggestions if your query was ambiguous or if certain fields aren’t available.

Each response includes a confidence score. Lower scores (below 0.5) indicate ambiguity. If results don’t match your expectations, review the alternative interpretations provided — these often reveal where the system interpretation differed from your intent. For complex criteria, break queries into multiple steps rather than a single nested question.

Example response:

Understood query with confidence 0.85. Applied blur filter successfully and
filtered to cluster 5. Showing 47 images that match your criteria.

If part of your query can’t be processed, the system explains why:

I found 23 blurry images in your dataset. Note: This dataset doesn't have a
'Temperature' custom metadata field configured, so I could only search for blur.

Multi-Turn Conversations

VL Chat maintains context across multiple messages, allowing you to refine your queries progressively:

You: “Show me images with blur” VL Chat: Returns 156 blurry images

You: “Now show only the ones from last week” VL Chat: Filters the previous results to show 23 images from last week

You: “Which cluster has the most of these?” VL Chat: Analyzes the filtered results and highlights cluster 12

Each follow-up question builds on the previous context, making exploration feel natural and conversational.

Related Resources

Exploring Datasets

Learn about all dataset exploration features

Using Search & Filter

Manual filtering and search options

Understanding Clusters

How similarity clustering works

Custom Metadata

Adding custom metadata fields to your datasets