<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
---------
Signed-off-by: Andrew Carbonetto <andrew.carbonetto@improving.com>
Signed-off-by: Andy Kwok <andy.kwok@improving.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
Co-authored-by: vasilije <vas.markovic@gmail.com>
Co-authored-by: Andrew Carbonetto <andrew.carbonetto@improving.com>
Co-authored-by: Andy Kwok <andy.kwok@improving.com>
<!-- .github/pull_request_template.md -->
## Description
Adds a Neptune Analytics 'hybrid' integration layer to the Cognee.ai
memory storage layer. The following configuration will use Amazon
Neptune Analytics to store all nodes, edges, and vector embeddings for
the Cognee.ai memory conversation.
```
cognee.config.set_graph_db_config(
{
"graph_database_provider": "neptune_analytics", # Specify Neptune Analytics as provider
"graph_database_url": graph_endpoint_url, # Neptune Analytics endpoint with the format neptune-graph://<GRAPH_ID>
}
)
cognee.config.set_vector_db_config(
{
"vector_db_provider": "neptune_analytics", # Specify Neptune Analytics as provider
"vector_db_url": graph_endpoint_url, # Neptune Analytics endpoint with the format neptune-graph://<GRAPH_ID>
}
)
```
For example, see
[neptune_analytics_example.py](08a3a1d2a8/examples/database_examples/neptune_analytics_example.py)
Related: https://github.com/topoteretes/cognee-starter/pull/11
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
---------
Signed-off-by: Andrew Carbonetto <andrew.carbonetto@improving.com>
Signed-off-by: Andy Kwok <andy.kwok@improving.com>
Co-authored-by: Andy Kwok <andy.kwok@improving.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
<!-- .github/pull_request_template.md -->
## Description
Fix Cognee mcp issues
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
Resolve issues with Cognee MCP docker use
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
This PR implements the 'FEELING_LUCKY' search type, which intelligently
routes user queries to the most appropriate search retriever, addressing
[#1162](https://github.com/topoteretes/cognee/issues/1162).
- implement new search type FEELING_LUCKY
- Add the select_search_type function to analyze queries and choose the
proper search type
- Integrate with an LLM for intelligent search type determination
- Add logging for the search type selection process
- Support fallback to RAG_COMPLETION when the LLM selection fails
- Add tests for the new search type
## How it works
When a user selects the 'FEELING_LUCKY' search type, the system first
sends their natural language query to an LLM-based classifier. This
classifier analyzes the query's intent (e.g., is it asking for a
relationship, a summary, or a factual answer?) and selects the optimal
SearchType, such as 'INSIGHTS' or 'GRAPH_COMPLETION'. The main search
function then proceeds using this dynamically selected type. If the
classification process fails, it gracefully falls back to the default
'RAG_COMPLETION' type.
## Testing
Tests can be run with:
```bash
python -m pytest cognee/tests/unit/modules/search/search_methods_test.py -k "feeling_lucky" -v
```
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
Signed-off-by: EricXiao <taoiaox@gmail.com>
<!-- .github/pull_request_template.md -->
## Description
Add default tokenizer for custom models not available on HuggingFace
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
Add async lock for dynamic table creation
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
## Description
This PR adds **responsive resizing** to the graph container. The
`ForceGraph` component now dynamically adjusts its width and height when
the browser window is resized, improving the user experience by removing
the need to manually click the "Fit Into View" button. solver issue
#1164
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
---
## ✅ Changes Made (Minimal, Additive Only)
### 1. **Added necessary imports**
```typescript
import { MutableRefObject, useEffect, useImperativeHandle, useRef, useState, useCallback } from "react";
// Added useCallback to existing imports
```
### 2. **Added responsive sizing state and refs**
```typescript
// State for tracking container dimensions
const [dimensions, setDimensions] = useState({ width: 0, height: 0 });
const containerRef = useRef<HTMLDivElement>(null);
```
### 3. **Added resize handling logic**
```typescript
// Handle window resize
const handleResize = useCallback(() => {
if (containerRef.current) {
const { clientWidth, clientHeight } = containerRef.current;
setDimensions({ width: clientWidth, height: clientHeight });
// Trigger graph refresh after resize
if (graphRef.current) {
// Small delay to ensure DOM has updated
setTimeout(() => {
graphRef.current?.refresh();
}, 100);
}
}
}, []);
// Set up resize observer
useEffect(() => {
// Initial size calculation
handleResize();
// ResizeObserver for more precise container size tracking
const resizeObserver = new ResizeObserver(() => {
handleResize();
});
if (containerRef.current) {
resizeObserver.observe(containerRef.current);
}
return () => {
resizeObserver.disconnect();
};
}, [handleResize]);
```
### 4. **Added container ref to wrapping div**
```tsx
<div ref={containerRef} className="w-full h-full" id="graph-container">
{/* Graph component rendered here */}
</div>
```
### 5. **Passed dynamic width/height to ForceGraph**
```tsx
<ForceGraph
ref={graphRef}
width={dimensions.width}
height={dimensions.height}
dagMode={graphShape as unknown as undefined}
// ... rest of props unchanged
/>
```
---
you can check this video out:
https://github.com/user-attachments/assets/e8e42c99-23e9-4acd-a51b-c59e8bee7094
<!-- .github/pull_request_template.md -->
## Description
Attempt at making incremental loading run async
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
<!-- .github/pull_request_template.md -->
## Description
feature: solve edge embedding duplicates in edge collection + retriever
optimization
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
---------
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
<!-- .github/pull_request_template.md -->
## Description
<!-- Provide a clear description of the changes in this PR -->
## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
