chore: Move files (#848)

<!-- .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.

---------

Co-authored-by: Igor Ilic <igorilic03@gmail.com>

.data/code/example.txt

@@ -1,28 +0,0 @@
-'''
-	Given a string, find the length of the longest substring without repeating characters.
-
-	Examples:
-
-	Given "abcabcbb", the answer is "abc", which the length is 3.
-
-	Given "bbbbb", the answer is "b", with the length of 1.
-
-	Given "pwwkew", the answer is "wke", with the length of 3. Note that the answer must be a substring, "pwke" is a subsequence and not a substring.
-'''
-
-class Solution(object):
-    def lengthOfLongestSubstring(self, s):
-        """
-        :type s: str
-        :rtype: int
-        """
-        mapSet = {}
-        start, result = 0, 0
-
-        for end in range(len(s)):
-        	if s[end] in mapSet:
-        		start = max(mapSet[s[end]], start)
-        	result = max(result, end-start+1)
-        	mapSet[s[end]] = end+1
-
-        return result

README.md

@@ -35,11 +35,11 @@ More on [use-cases](https://docs.cognee.ai/use-cases) and [evals](https://github
   <p align="center">
   🌐 Available Languages
   :
-  <a href="community/README.pt.md">🇵🇹 Português</a>
+  <a href="assets/community/README.pt.md">🇵🇹 Português</a>
   ·
-  <a href="community/README.zh.md">🇨🇳 [中文]</a>
+  <a href="assets/community/README.zh.md">🇨🇳 [中文]</a>
   ·
-  <a href="community/README.ru.md">🇷🇺 Русский</a>
+  <a href="assets/community/README.ru.md">🇷🇺 Русский</a>
   </p>
   
 

examples/python/multimedia_example.py

@@ -21,11 +21,11 @@ async def main():
     # and description of these files
     mp3_file_path = os.path.join(
         pathlib.Path(__file__).parent.parent.parent,
-        ".data/multimedia/text_to_speech.mp3",
+        "examples/data/multimedia/text_to_speech.mp3",
     )
     png_file_path = os.path.join(
         pathlib.Path(__file__).parent.parent.parent,
-        ".data/multimedia/example.png",
+        "examples/data/multimedia/example.png",
     )
 
     # Add the files, and make it available for cognify

notebooks/cognee_multimedia_demo.ipynb

@@ -21,10 +21,10 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 23,
    "metadata": {},
+   "cell_type": "code",
    "outputs": [],
+   "execution_count": null,
    "source": [
     "import os\n",
     "import pathlib\n",
@@ -34,12 +34,12 @@
     "mp3_file_path = os.path.join(\n",
     "    os.path.abspath(\"\"),\n",
     "    \"../\",\n",
-    "    \".data/multimedia/text_to_speech.mp3\",\n",
+    "    \"examples/data/multimedia/text_to_speech.mp3\",\n",
     ")\n",
     "png_file_path = os.path.join(\n",
     "    os.path.abspath(\"\"),\n",
     "    \"../\",\n",
-    "    \".data/multimedia/example.png\",\n",
+    "    \"examples/data/multimedia/example.png\",\n",
     ")"
    ]
   },

profiling/graph_pydantic_conversion/benchmark_function.py

@@ -1,62 +0,0 @@
-import statistics
-import time
-import tracemalloc
-from typing import Any, Callable, Dict
-
-import psutil
-
-
-def benchmark_function(func: Callable, *args, num_runs: int = 5) -> Dict[str, Any]:
-    """
-    Benchmark a function for memory usage and computational performance.
-
-    Args:
-        func: Function to benchmark
-        *args: Arguments to pass to the function
-        num_runs: Number of times to run the benchmark
-
-    Returns:
-        Dictionary containing benchmark metrics
-    """
-    execution_times = []
-    peak_memory_usages = []
-    cpu_percentages = []
-
-    process = psutil.Process()
-
-    for _ in range(num_runs):
-        # Start memory tracking
-        tracemalloc.start()
-
-        # Measure execution time and CPU usage
-        start_time = time.perf_counter()
-        start_cpu_time = process.cpu_times()
-
-        end_cpu_time = process.cpu_times()
-        end_time = time.perf_counter()
-
-        # Calculate metrics
-        execution_time = end_time - start_time
-        cpu_time = (end_cpu_time.user + end_cpu_time.system) - (
-            start_cpu_time.user + start_cpu_time.system
-        )
-        current, peak = tracemalloc.get_traced_memory()
-
-        # Store results
-        execution_times.append(execution_time)
-        peak_memory_usages.append(peak / 1024 / 1024)  # Convert to MB
-        cpu_percentages.append((cpu_time / execution_time) * 100)
-
-        tracemalloc.stop()
-
-    analysis = {
-        "mean_execution_time": statistics.mean(execution_times),
-        "mean_peak_memory_mb": statistics.mean(peak_memory_usages),
-        "mean_cpu_percent": statistics.mean(cpu_percentages),
-        "num_runs": num_runs,
-    }
-
-    if num_runs > 1:
-        analysis["std_execution_time"] = statistics.stdev(execution_times)
-
-    return analysis

profiling/graph_pydantic_conversion/profile_graph_pydantic_conversion.py

@@ -1,63 +0,0 @@
-import argparse
-import asyncio
-
-from .benchmark_function import benchmark_function
-
-from cognee.modules.graph.utils import get_graph_from_model
-from cognee.tests.unit.interfaces.graph.util import (
-    PERSON_NAMES,
-    create_organization_recursive,
-)
-
-# Example usage:
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(
-        description="Benchmark graph model with configurable recursive depth"
-    )
-    parser.add_argument(
-        "--recursive-depth",
-        type=int,
-        default=3,
-        help="Recursive depth for graph generation (default: 3)",
-    )
-    parser.add_argument("--runs", type=int, default=5, help="Number of benchmark runs (default: 5)")
-    args = parser.parse_args()
-
-    society = create_organization_recursive(
-        "society", "Society", PERSON_NAMES, args.recursive_depth
-    )
-    added_nodes = {}
-    added_edges = {}
-    visited_properties = {}
-    nodes, edges = asyncio.run(
-        get_graph_from_model(
-            society,
-            added_nodes=added_nodes,
-            added_edges=added_edges,
-            visited_properties=visited_properties,
-        )
-    )
-
-    def get_graph_from_model_sync(model):
-        added_nodes = {}
-        added_edges = {}
-        visited_properties = {}
-
-        return asyncio.run(
-            get_graph_from_model(
-                model,
-                added_nodes=added_nodes,
-                added_edges=added_edges,
-                visited_properties=visited_properties,
-            )
-        )
-
-    results = benchmark_function(get_graph_from_model_sync, society, num_runs=args.runs)
-    print("\nBenchmark Results:")
-    print(f"N nodes: {len(nodes)}, N edges: {len(edges)}, Recursion depth: {args.recursive_depth}")
-    print(f"Mean Peak Memory: {results['mean_peak_memory_mb']:.2f} MB")
-    print(f"Mean CPU Usage: {results['mean_cpu_percent']:.2f}%")
-    print(f"Mean Execution Time: {results['mean_execution_time']:.4f} seconds")
-
-    if "std_execution_time" in results:
-        print(f"Execution Time Std: {results['std_execution_time']:.4f} seconds")

profiling/util/DummyEmbeddingEngine.py

@@ -1,10 +0,0 @@
-import numpy as np
-from cognee.infrastructure.databases.vector.embeddings.EmbeddingEngine import EmbeddingEngine
-
-
-class DummyEmbeddingEngine(EmbeddingEngine):
-    async def embed_text(self, text: list[str]) -> list[list[float]]:
-        return list(list(np.random.randn(3072)))
-
-    def get_vector_size(self) -> int:
-        return 3072

profiling/util/DummyLLMAdapter.py

@@ -1,59 +0,0 @@
-from typing import Type
-from uuid import uuid4
-
-import spacy
-import textacy
-from pydantic import BaseModel
-
-from cognee.infrastructure.llm.llm_interface import LLMInterface
-from cognee.shared.data_models import Edge, KnowledgeGraph, Node, SummarizedContent
-
-
-class DummyLLMAdapter(LLMInterface):
-    nlp = spacy.load("en_core_web_sm")
-
-    async def acreate_structured_output(
-        self, text_input: str, system_prompt: str, response_model: Type[BaseModel]
-    ) -> BaseModel:
-        if str(response_model) == "<class 'cognee.shared.data_models.SummarizedContent'>":
-            return dummy_summarize_content(text_input)
-        elif str(response_model) == "<class 'cognee.shared.data_models.KnowledgeGraph'>":
-            return dummy_extract_knowledge_graph(text_input, self.nlp)
-        else:
-            raise Exception(
-                "Currently dummy acreate_structured_input is only implemented for SummarizedContent and KnowledgeGraph"
-            )
-
-
-def dummy_extract_knowledge_graph(text, nlp):
-    doc = nlp(text)
-    triples = list(textacy.extract.subject_verb_object_triples(doc))
-
-    nodes = {}
-    edges = []
-    for triple in triples:
-        source = "_".join([str(e) for e in triple.subject])
-        target = "_".join([str(e) for e in triple.object])
-        nodes[source] = nodes.get(
-            source, Node(id=str(uuid4()), name=source, type="object", description="")
-        )
-        nodes[target] = nodes.get(
-            target, Node(id=str(uuid4()), name=target, type="object", description="")
-        )
-        edge_type = "_".join([str(e) for e in triple.verb])
-        edges.append(
-            Edge(
-                source_node_id=nodes[source].id,
-                target_node_id=nodes[target].id,
-                relationship_name=edge_type,
-            )
-        )
-    return KnowledgeGraph(nodes=list(nodes.values()), edges=edges)
-
-
-def dummy_summarize_content(text):
-    words = [(word, len(word)) for word in set(text.split(" "))]
-    words = sorted(words, key=lambda x: x[1], reverse=True)
-    summary = " ".join([word for word, _ in words[:50]])
-    description = " ".join([word for word, _ in words[:10]])
-    return SummarizedContent(summary=summary, description=description)