Update debugging docs for heaptrack

next.config.mjs

@@ -3405,7 +3405,36 @@ export default withNextra({
         destination: '/ai-ecosystem#graphchat',
         permanent: true
       },
-
+      {
+        source: '/getting-started/build-memgraph-from-source#obtaining-the-source-code',
+        destination: '/getting-started/build-memgraph-from-source#obtain-the-source-code',
+        permanent: true
+      },
+      {
+        source: '/getting-started/build-memgraph-from-source#downloading-the-dependencies',
+        destination: '/getting-started/build-memgraph-from-source#download-dependencies-required-for-methods-1--2',
+        permanent: true
+      },
+      {
+        source: '/getting-started/build-memgraph-from-source#compiling',
+        destination: '/getting-started/build-memgraph-from-source#toolchain-installation-required-for-methods-1--2',
+        permanent: true
+      },
+      {
+        source: '/getting-started/build-memgraph-from-source#toolchain-installation-procedure',
+        destination: '/getting-started/build-memgraph-from-source#toolchain-installation-required-for-methods-1--2',
+        permanent: true
+      },
+      {
+        source: '/getting-started/build-memgraph-from-source#installing-memgraph-dependencies',
+        destination: '/getting-started/build-memgraph-from-source#download-dependencies-required-for-methods-1--2',
+        permanent: true
+      },
+      {
+        source: '/getting-started/build-memgraph-from-source#running-memgraph',
+        destination: '/getting-started/build-memgraph-from-source#run-memgraph',
+        permanent: true
+      },
 
 
       // END: NEW MEMGRAPH LAB REDIRECTS

pages/advanced-algorithms/available-algorithms/_meta.ts

@@ -19,6 +19,7 @@ export default {
   "degree_centrality": "degree_centrality",
   "distance_calculator": "distance_calculator",
   "elasticsearch_synchronization": "elasticsearch_synchronization",
+  "embeddings": "embeddings",
   "export_util": "export_util",
   "gnn_link_prediction": "gnn_link_prediction",
   "gnn_node_classification": "gnn_node_classification",

pages/advanced-algorithms/available-algorithms/embeddings.mdx

@@ -0,0 +1,135 @@
+---
+title: embeddings
+description: Calculate sentence embeddings on node strings using pytorch.
+---
+
+# embeddings
+
+import { Cards } from 'nextra/components'
+import GitHub from '/components/icons/GitHub'
+
+The embeddings module provides tools for calculating sentence embeddings on node strings using pytorch.
+
+<Cards>
+  <Cards.Card
+    icon={<GitHub />}
+    title="Source code"
+    href="https://github.com/memgraph/mage/blob/main/python/embeddings.py"
+  />
+</Cards>
+
+| Trait               | Value               |
+| ------------------- | ------------------- |
+| **Module type**     | algorithm           |
+| **Implementation**  | Python              |
+| **Parallelism**     | parallel            |
+
+
+## Procedures
+
+### `compute()`
+
+The procedure computes the sentence embeddings on the string properties of nodes. Embeddings are 
+created as a property of the nodes in the graph.
+
+{<h4 className="custom-header"> Input: </h4>}
+
+- `input_nodes: List[Vertex]` (**OPTIONAL**) ➡ The list of nodes to compute the embeddings for. If not provided, the embeddings are computed for all nodes in the graph.
+- `embedding_property: string` ➡ The name of the property to store the embeddings in. This property is `embedding` by default.
+- `excluded_properties: List[string]` ➡ The list of properties to exclude from the embeddings computation. This list is empty by default.
+- `model_name: string` ➡ The name of the model to use for the embeddings computation, buy default this module uses the `all-MiniLM-L6-v2` model provided by the `sentence-transformers` library.
+- `batch_size: int` ➡ The batch size to use for the embeddings computation. This is set to `2000` by default.
+- `chunk_size: int` ➡ The number of batches per "chunk". This is used when computing embeddings across multiple GPUs, as this has to be done by spawning multiple processes. Each spawned process computes the embeddings for a single chunk. This is set to 48 by default.
+- `device: string|int|List[string|int]` ➡ The device to use for the embeddings computation. This can be any of the following:
+    - `"cpu"` - Use CPU for computation.
+    - `"cuda"` or `"all"` - Use all available CUDA devices for computation.
+    - `"cuda:id"` - Use a specific CUDA device for computation.
+    - `id` - Use a specific device for computation.
+    - `[id1, id2, ...]` - Use a list of device ids for computation.
+    - `["cuda:id1", "cuda:id2", ...]` - Use a list of CUDA devices for computation.
+by default, the first device (`0`) is used.
+
+{<h4 className="custom-header"> Output: </h4>}
+
+- `success: bool` ➡ Whether the embeddings computation was successful.
+
+{<h4 className="custom-header"> Usage: </h4>}
+
+To compute the embeddings across the entire graph with the default parameters, use the following query: 
+
+```cypher
+CALL embeddings.compute()
+YIELD success;
+```
+
+To compute the embeddings for a specific list of nodes, use the following query:
+
+
+```cypher
+MATCH (n)
+WITH n ORDER BY id(n)
+LIMIT 5
+WITH collect(n) AS subset
+CALL embeddings.compute(subset)
+YIELD success;
+```
+
+To run the computation on specific device(s), use the following query:
+
+```cypher
+CALL embeddings.compute(
+    NULL,
+    "embedding",
+    NULL,
+    "all-MiniLM-L6-v2",
+    2000,
+    48,
+    "cuda:1"
+)
+YIELD success;
+```
+
+
+## Example
+
+Create the following graph:
+
+```cypher
+CREATE (n:Node {id: 1, Title: "Stilton", Description: "A stinky cheese from the UK"}),
+(n:Node {id: 2, Title: "Roquefort", Description: "A blue cheese from France"}),
+(n:Node {id: 3, Title: "Cheddar", Description: "A yellow cheese from the UK"}),
+(n:Node {id: 4, Title: "Gouda", Description: "A Dutch cheese"}),
+(n:Node {id: 5, Title: "Parmesan", Description: "An Italian cheese"}),
+(n:Node {id: 6, Title: "Red Leicester", Description: "The best cheese in the world"});
+```
+
+Run the following query to compute the embeddings:
+
+```cypher
+CALL embeddings.compute()
+YIELD success;
+
+MATCH (n) 
+WHERE n.embedding IS NOT NULL 
+RETURN n.Title, n.embedding;
+```
+
+Results:
+
+```plaintext
++---------+
+| success |
++---------+
+| true    |
++---------+
++----------------------------------------------------------------------+----------------------------------------------------------------------+
+| n.Title                                                              | n.embedding                                                          |
++----------------------------------------------------------------------+----------------------------------------------------------------------+
+| "Stilton"                                                            | [-0.0485366, -0.021823, 0.0159757, 0.0376443, 0.00594089, -0.0044... |
+| "Roquefort"                                                          | [-0.0252884, 0.0250485, -0.0249728, 0.0571037, 0.0386177, 0.03863... |
+| "Cheddar"                                                            | [-0.0129724, -0.00756301, -0.00379329, 0.0037531, -0.0134941, 0.0... |
+| "Gouda"                                                              | [0.0128716, 0.025435, -0.0288951, 0.0177759, -0.0624398, 0.043577... |
+| "Parmesan"                                                           | [-0.0755439, 0.00906182, -0.010977, 0.0208911, -0.0527448, 0.0085... |
+| "Red Leicester"                                                      | [-0.0244318, -0.0280038, -0.0373183, 0.0284436, -0.0277753, 0.066... |
++----------------------------------------------------------------------+----------------------------------------------------------------------+
+```

pages/advanced-algorithms/available-algorithms/map.mdx

@@ -171,16 +171,18 @@ RETURN map.from_pairs([["b", 3], ["c", "c"]]) AS map;
 ### `merge()`
 
 The procedure merges two maps into one. If the same key occurs twice, the later
-value will overwrite the previous one.
+value will overwrite the previous one. 
+
+If null is provided as an argument, it will resolve to an empty map.
 
 <Callout type="info">
 This function is equivalent to **apoc.map.merge**.
 </Callout>
 
 {<h4 className="custom-header"> Input: </h4>}
 
-- `first: Map` ➡ A map containing key-value pairs that need to be merged with another map.
-- `second: Map` ➡ The second map containing key-value pairs that need to be merged with the key-values from the first map.
+- `first: mgp.Nullable[Map]` ➡ A map containing key-value pairs that need to be merged with another map.
+- `second: mgp.Nullable[Map]` ➡ The second map containing key-value pairs that need to be merged with the key-values from the first map.
 
 {<h4 className="custom-header"> Output: </h4>}
 

pages/advanced-algorithms/install-mage.mdx

@@ -33,6 +33,9 @@ The following tags are available on Docker Hub:
 - `x.y` - production MAGE image
 - `x.y-relwithdebinfo` - contains debugging symbols and `gdb`
 - `x.y-malloc` - Memgraph compiled with `malloc`instead of `jemalloc` (x86_64 only)
+- `x.y-relwithdebinfo-cuda` - Memgraph built with CUDA support* - available since version `3.6.1`.
+
+*To run GPU-accelerated algorithms, you need to launch the container with the `--gpus all` flag.
 
 For versions prior to `3.2`, MAGE image tags included both MAGE and Memgraph versions, e.g.
 
@@ -90,7 +93,7 @@ sudo apt-get update && sudo apt-get install -y \
     git \
     pkg-config \
     uuid-dev \
-    libxmlsec1-dev xmlsec1 \
+    xmlsec1 \
     --no-install-recommends 
 ```
 
@@ -106,7 +109,7 @@ git clone --recurse-submodules https://github.com/memgraph/mage.git && cd mage
 
 Download and install the [Memgraph Toolchain](https://memgraph.com/docs/getting-started/build-memgraph-from-source#toolchain-installation-procedure):
 ```bash
-curl -L https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v6/toolchain-v6-binaries-ubuntu-24.04-amd64.tar.gz -o toolchain.tar.gz
+curl -L https://s3-eu-west-1.amazonaws.com/deps.memgraph.io/toolchain-v7/toolchain-v7-binaries-ubuntu-24.04-amd64.tar.gz -o toolchain.tar.gz
 sudo tar xzvfm toolchain.tar.gz -C /opt
 ```
 
@@ -125,16 +128,25 @@ curl https://sh.rustup.rs -sSf | sh -s -- -y
 export PATH="/root/.cargo/bin:${PATH}" 
 python3 -m pip install -r python/requirements.txt 
 python3 -m pip install -r cpp/memgraph/src/auth/reference_modules/requirements.txt
-python3 -m pip install torch-sparse torch-cluster torch-spline-conv torch-geometric torch-scatter -f https://data.pyg.org/whl/torch-2.3.0+cpu.html
-python3 -m pip install dgl -f https://data.dgl.ai/wheels/torch-2.3/repo.html
+python3 -m pip install torch-sparse torch-cluster torch-spline-conv torch-geometric torch-scatter -f https://data.pyg.org/whl/torch-2.6.0+cpu.html
+python3 -m pip install dgl -f https://data.dgl.ai/wheels/torch-2.6/repo.html
+```
+
+<Callout type="info">
+
+To install the dependencies for GPU-accelerated algorithms, you need to use the GPU-specific requirements file:
+
+```shell
+python3 -m pip install -r python/requirements-gpu.txt
 ```
+</Callout>
 
 {<h3 className="custom-header">Run the `setup` script</h3>}
 
 Run the following command: 
 
 ```shell
-source /opt/toolchain-v6/activate
+source /opt/toolchain-v7/activate
 python3 setup build
 sudo cp -r dist/* /usr/lib/memgraph/query_modules
 ```

pages/custom-query-modules/python.mdx

@@ -55,7 +55,7 @@ inside a Docker container, run the following command in the terminal:
 
 
 ```
-docker exec -i -u root <container_id> bash -c "apt install -y python3-pip &&
+docker exec -i -u memgraph <container_id> bash -c "apt install -y python3-pip &&
 pip install pandas"
 ```
 
@@ -69,16 +69,16 @@ commands in the Dockerfile:
 ```
 FROM memgraph/memgraph:latest
 
-USER root
+USER memgraph
 
 RUN apt install -y python3-pip
 RUN pip install pandas
 
-USER memgraph
 ```
 
-It is important that you install Python library as a `root` user, rather than
-the default `memgraph` user.
+Python libraries should now be installed as the `memgraph` user, which is the
+default user inside the Memgraph container. You no longer need to switch to the
+`root` user to perform installations.
 
 ## Example