speedy-utils 1.1.13__py3-none-any.whl → 1.1.15__py3-none-any.whl

llm_utils/vector_cache/core.py

@@ -4,6 +4,7 @@ import hashlib
 import os
 import sqlite3
 from pathlib import Path
+from time import time
 from typing import Any, Dict, Literal, Optional, cast
 
 import numpy as np
@@ -78,7 +79,7 @@ class VectorCache:
         self.config = {
             # OpenAI
             "api_key": api_key or os.getenv("OPENAI_API_KEY"),
-            "model_name": model_name,
+            "model_name": self._try_infer_model_name(model_name),
             # vLLM
             "vllm_gpu_memory_utilization": vllm_gpu_memory_utilization,
             "vllm_tensor_parallel_size": vllm_tensor_parallel_size,
@@ -164,7 +165,22 @@ class VectorCache:
         
         # Default to vllm for local models
         return "vllm"
-
+    def _try_infer_model_name(self, model_name: Optional[str]) -> Optional[str]:
+        """Infer model name for OpenAI backend if not explicitly provided."""
+        # if self.backend != "openai":
+            # return model_name
+        if model_name:
+            return model_name
+        if 'https://' in self.url_or_model:
+            model_name =  "text-embedding-3-small"
+        if 'http://localhost' in self.url_or_model:
+            from openai import OpenAI
+            client = OpenAI(base_url=self.url_or_model, api_key='abc')
+            model_name =  client.models.list().data[0].id
+
+        # Default model name
+        print('Infer model name:', model_name)
+        return model_name
     def _optimize_connection(self) -> None:
         """Optimize SQLite connection for bulk operations."""
         # Performance optimizations for bulk operations
@@ -366,7 +382,7 @@ class VectorCache:
         """
         if not texts:
             return np.empty((0, 0), dtype=np.float32)
-
+        t = time()
         hashes = [self._hash_text(t) for t in texts]
 
         # Helper to yield chunks
@@ -414,6 +430,9 @@ class VectorCache:
             self._bulk_insert(bulk_insert_data)
 
         # Return embeddings in the original order
+        elapsed = time() - t
+        if self.verbose:
+            print(f"Retrieved {len(texts)} embeddings in {elapsed:.2f} seconds")
         return np.vstack([hit_map[h] for h in hashes])
 
     def __call__(self, texts: list[str], cache: bool = True) -> np.ndarray:

speedy_utils/__init__.py

@@ -18,7 +18,7 @@
 # • memoize(func) -> Callable - Function result caching decorator
 # • identify(obj: Any) -> str - Generate unique object identifier
 # • identify_uuid(obj: Any) -> str - Generate UUID-based object identifier
-# • load_by_ext(fname: str | list[str]) -> Any - Auto-detect file format loader
+# • load_by_ext(fname: Union[str, list[str]]) -> Any - Auto-detect file format loader
 # • dump_json_or_pickle(obj: Any, fname: str) -> None - Smart file serializer
 # • load_json_or_pickle(fname: str) -> Any - Smart file deserializer
 # • multi_thread(func, items, **kwargs) -> list - Parallel thread execution

speedy_utils/common/utils_io.py

@@ -92,7 +92,7 @@ def load_jsonl(path):
     return [json.loads(line) for line in lines]
 
 
-def load_by_ext(fname: str | list[str], do_memoize: bool = False) -> Any:
+def load_by_ext(fname: Union[str, list[str]], do_memoize: bool = False) -> Any:
     """
     Load data based on file extension.
     """

speedy_utils/common/utils_print.py

@@ -3,7 +3,7 @@
 import copy
 import pprint
 import textwrap
-from typing import Any
+from typing import Any, Union
 
 from tabulate import tabulate
 
@@ -24,17 +24,17 @@ def flatten_dict(d, parent_key="", sep="."):
 
 def fprint(
     input_data: Any,
-    key_ignore: list[str] | None = None,
-    key_keep: list[str] | None = None,
+    key_ignore: Union[list[str], None] = None,
+    key_keep: Union[list[str], None] = None,
     max_width: int = 100,
     indent: int = 2,
-    depth: int | None = None,
+    depth: Union[int, None] = None,
     table_format: str = "grid",
     str_wrap_width: int = 80,
     grep=None,
     is_notebook=None,
     f=print,
-) -> None | str:
+) -> Union[None, str]:
     """
     Pretty print structured data.
     """

{speedy_utils-1.1.13.dist-info → speedy_utils-1.1.15.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: speedy-utils
-Version: 1.1.13
+Version: 1.1.15
 Summary: Fast and easy-to-use package for data science
 Author: AnhVTH
 Author-email: anhvth.226@gmail.com
@@ -25,6 +25,7 @@ Requires-Dist: jupyterlab
 Requires-Dist: loguru
 Requires-Dist: matplotlib
 Requires-Dist: numpy
+Requires-Dist: openai (>=1.106.0,<2.0.0)
 Requires-Dist: packaging (>=23.2,<25)
 Requires-Dist: pandas
 Requires-Dist: pydantic

{speedy_utils-1.1.13.dist-info → speedy_utils-1.1.15.dist-info}/RECORD

@@ -18,10 +18,10 @@ llm_utils/scripts/vllm_load_balancer.py,sha256=TT5Ypq7gUcl52gRFp--ORFFjzhfGlcaX2
 llm_utils/scripts/vllm_serve.py,sha256=gJ0-y4kybMfSt8qzye1pJqGMY3x9JLRi6Tu7RjJMnss,14771
 llm_utils/vector_cache/__init__.py,sha256=i1KQuC4OhPewYpFl9X6HlWFBuASCTx2qgGizhpZhmn0,862
 llm_utils/vector_cache/cli.py,sha256=DMXTj8nZ2_LRjprbYPb4uzq04qZtOfBbmblmaqDcCuM,6251
-llm_utils/vector_cache/core.py,sha256=UqAgsFFaDQtXBFBB22YnoScGpImVfv4k2P4EONQrh50,21823
+llm_utils/vector_cache/core.py,sha256=-g_y3U4hdJltHMVi8oYJTsW8p7lR973LlDqcLZ9kECk,22725
 llm_utils/vector_cache/types.py,sha256=ru8qmUZ8_lNd3_oYpjCMtpXTsqmwsSBe56Z4hTWm3xI,435
 llm_utils/vector_cache/utils.py,sha256=dwbbXlRrARrpmS4YqSlYQqrTURg0UWe8XvaAWcX05MM,1458
-speedy_utils/__init__.py,sha256=YCpiReW22zG4KkQXQe6V9BQ8bn7PtiXolOaW_iL8T4M,5734
+speedy_utils/__init__.py,sha256=nJpUb5Oa3STDbqPSiWXoI-IvKntyRYzYxkYW4GM2i_Q,5740
 speedy_utils/all.py,sha256=t-HKzDmhF1MTFnmq7xRnPs5nFG_aZaLH9Ua0RM6nQ9Y,4855
 speedy_utils/common/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 speedy_utils/common/clock.py,sha256=3n4FkCW0dz46O8By09V5Pve1DSMgpLDRbWEVRryryeQ,7423
@@ -30,16 +30,16 @@ speedy_utils/common/logger.py,sha256=a2iZx0eWyfi2-2X_H2QmfuA3tfR7_XSM7Nd0GdUnUOs
 speedy_utils/common/notebook_utils.py,sha256=-97kehJ_Gg3TzDLubsLIYJcykqX1NXhbvBO6nniZSYM,2063
 speedy_utils/common/report_manager.py,sha256=eBiw5KY6bWUhwki3B4lK5o8bFsp7L5x28X9GCI-Sd1w,3899
 speedy_utils/common/utils_cache.py,sha256=0cQJm0nnD9755pWMdAkhDn2qIbGvJMTMUl2gibkX05E,22376
-speedy_utils/common/utils_io.py,sha256=qaqbZpopfcDDwsrqNOX-pZpUw7EXRTDweXywRyV-2vo,5244
+speedy_utils/common/utils_io.py,sha256=76ZVgJwgjOznq5L_i2oyWuBnuwymjcktqSvB8VWTKsc,5250
 speedy_utils/common/utils_misc.py,sha256=cdEuBBpiB1xpuzj0UBDHDuTIerqsMIw37ENq6EXliOw,1795
-speedy_utils/common/utils_print.py,sha256=iQqnOYw2EFC8TqeSDbrcnIQAUKT7FbB8Mec8b2aGAzw,4833
+speedy_utils/common/utils_print.py,sha256=syRrnSFtguxrV-elx6DDVcSGu4Qy7D_xVNZhPwbUY4A,4864
 speedy_utils/multi_worker/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 speedy_utils/multi_worker/process.py,sha256=MJ5njqjY9nMo-Z1oXMbzkppuYVJCcCtFsLo8lbCh5zs,6849
 speedy_utils/multi_worker/thread.py,sha256=f02VjJV8nudg0eA_AcfPEX7tHY4-czesuzthKZs_Hdc,16351
 speedy_utils/scripts/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 speedy_utils/scripts/mpython.py,sha256=IvywP7Y0_V6tWfMP-4MjPvN5_KfxWF21xaLJsCIayCk,3821
 speedy_utils/scripts/openapi_client_codegen.py,sha256=f2125S_q0PILgH5dyzoKRz7pIvNEjCkzpi4Q4pPFRZE,9683
-speedy_utils-1.1.13.dist-info/METADATA,sha256=EYIm4tBWfKI94vxyTP0i8zn8--btk4BvCBCB4K3AAjk,7442
-speedy_utils-1.1.13.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-speedy_utils-1.1.13.dist-info/entry_points.txt,sha256=T1t85jwx8fK6m5msdkBGIXH5R5Kd0zSL0S6erXERPzg,237
-speedy_utils-1.1.13.dist-info/RECORD,,
+speedy_utils-1.1.15.dist-info/METADATA,sha256=GOftJglyMxP320bZFW8XX-UurB8vr_01jDNGV7ecKh8,7483
+speedy_utils-1.1.15.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+speedy_utils-1.1.15.dist-info/entry_points.txt,sha256=T1t85jwx8fK6m5msdkBGIXH5R5Kd0zSL0S6erXERPzg,237
+speedy_utils-1.1.15.dist-info/RECORD,,