Docs: Run with uv

Author: ashvardanian

bench_find.py

@@ -16,9 +16,9 @@
 - STRINGWARS_TOKENS: Tokenization mode ('lines', 'words', 'file')
 
 Examples:
-  python bench_find.py --dataset README.md --tokens lines
-  python bench_find.py --dataset xlsum.csv --tokens words -k "str.find"
-  STRINGWARS_DATASET=data.txt STRINGWARS_TOKENS=lines python bench_find.py
+  uv run bench_find.py --dataset README.md --tokens lines
+  uv run bench_find.py --dataset xlsum.csv --tokens words -k "str.find"
+  STRINGWARS_DATASET=data.txt STRINGWARS_TOKENS=lines uv run bench_find.py
 
 Timing via time.monotonic_ns.; throughput in decimal GB/s. Filter with -k/--filter.
 """

bench_fingerprints.py

@@ -18,9 +18,9 @@
 - STRINGWARS_TOKENS: Tokenization mode ('lines', 'words', 'file')
 
 Examples:
-  python bench_fingerprints.py --dataset README.md --tokens lines
-  python bench_fingerprints.py --dataset xlsum.csv --tokens words -k "datasketch"
-  STRINGWARS_DATASET=data.txt STRINGWARS_TOKENS=lines python bench_fingerprints.py
+  uv run --with stringzillas-cpus bench_fingerprints.py --dataset README.md --tokens lines
+  uv run --with stringzillas-cpus bench_fingerprints.py --dataset xlsum.csv --tokens words -k "datasketch"
+  STRINGWARS_DATASET=data.txt STRINGWARS_TOKENS=lines uv run --with stringzillas-cpus bench_fingerprints.py
 """
 
 import os

bench_hash.py

@@ -30,9 +30,9 @@
 - STRINGWARS_TOKENS: Tokenization mode ('lines', 'words', 'file')
 
 Examples:
-  python bench_hash.py --dataset README.md --tokens lines
-  python bench_hash.py --dataset xlsum.csv --tokens words -k "xxhash"
-  STRINGWARS_DATASET=data.txt STRINGWARS_TOKENS=lines python bench_hash.py
+  uv run bench_hash.py --dataset README.md --tokens lines
+  uv run bench_hash.py --dataset xlsum.csv --tokens words -k "xxhash"
+  STRINGWARS_DATASET=data.txt STRINGWARS_TOKENS=lines uv run bench_hash.py
 """
 
 import argparse

bench_memory.py

@@ -14,8 +14,8 @@
 - Random byte generation: NumPy PCG64, NumPy Philox, and PyCryptodome AES-CTR
 
 Examples:
-  python bench_memory.py --dataset README.md --tokens lines
-  python bench_memory.py --dataset README.md --tokens words -k "translate|LUT|AES-CTR|PCG64|Philox"
+  uv run bench_memory.py --dataset README.md --tokens lines
+  uv run bench_memory.py --dataset README.md --tokens words -k "translate|LUT|AES-CTR|PCG64|Philox"
 """
 
 from __future__ import annotations

bench_sequence.py

@@ -17,9 +17,9 @@
 - STRINGWARS_TOKENS: Tokenization mode ('lines', 'words', 'file')
 
 Examples:
-  python bench_sequence.py --dataset README.md --tokens lines
-  python bench_sequence.py --dataset xlsum.csv --tokens words -k "list.sort"
-  STRINGWARS_DATASET=data.txt STRINGWARS_TOKENS=lines python bench_sequence.py
+  uv run bench_sequence.py --dataset README.md --tokens lines
+  uv run bench_sequence.py --dataset xlsum.csv --tokens words -k "list.sort"
+  STRINGWARS_DATASET=data.txt STRINGWARS_TOKENS=lines uv run bench_sequence.py
 """
 import os
 

bench_similarities.py

@@ -29,9 +29,9 @@
 - STRINGWARS_TOKENS: Tokenization mode ('lines', 'words', 'file')
 
 Examples:
-  python bench_similarities.py --dataset README.md --max-pairs 1000
-  python bench_similarities.py --dataset xlsum.csv --bio -k "biopython"
-  STRINGWARS_DATASET=data.txt STRINGWARS_TOKENS=lines python bench_similarities.py
+  uv run --with stringzillas-cpus bench_similarities.py --dataset README.md --max-pairs 1000
+  uv run --with stringzillas-cpus bench_similarities.py --dataset xlsum.csv --bio -k "biopython"
+  STRINGWARS_DATASET=data.txt STRINGWARS_TOKENS=lines uv run --with stringzillas-cpus bench_similarities.py
 """
 
 import os