vectoriz 0.0.4__py3-none-any.whl → 0.1.0b0__py3-none-any.whl

vectoriz/files.py

@@ -2,6 +2,7 @@ import os
 import docx
 import numpy as np
 from typing import Optional
+
 from vectoriz.token_transformer import TokenTransformer
 
 class FileArgument:

vectoriz/token_transformer.py

@@ -73,15 +73,16 @@ class TokenTransformer:
     def search(
         self,
         query: str,
-        data: TokenData,
+        index: faiss.IndexFlatL2,
+        texts: list[str],
         context_amount: int = 1,
     ) -> str:
         query_embedding = self._query_to_embeddings(query)
-        _, I = data.index.search(query_embedding, k=context_amount)
+        _, I = index.search(query_embedding, k=context_amount)
         context = ""
 
         for i in I[0]:
-            context += data.texts[i] + "\n"
+            context += texts[i] + "\n"
 
         return context.strip()
 

vectoriz/vector_db.py

@@ -54,15 +54,6 @@ class VectorDBClient:
 
 class VectorDB:
 
-    def __init__(self):
-        """
-        Constructor for the class.
-
-        Initializes the following attributes:
-        - transformer: A TokenTransformer instance for text transformation.
-        """
-        self.transformer = TokenTransformer()
-
     def load_saved_data(
         self, faiss_db_path: str, np_db_path: str
     ) -> Optional[VectorDBClient]:
@@ -158,13 +149,14 @@ class VectorDB:
             - 'chunk_names': The chunk names
             - 'texts': The text content
         """
+        transformer = TokenTransformer()
         np_db_path = np_db_path if np_db_path.endswith(".npz") else np_db_path + ".npz"
 
         embeddings_np: np.ndarray = None
         if argument.ndarray_data is not None:
             embeddings_np = argument.ndarray_data
         else:
-            embeddings_np = self.transformer.get_np_vectors(argument.embeddings)
+            embeddings_np = transformer.get_np_vectors(argument.embeddings)
 
         np.savez(
             np_db_path,

{vectoriz-0.0.4.dist-info → vectoriz-0.1.0b0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: vectoriz
-Version: 0.0.4
+Version: 0.1.0b0
 Summary: Python library for creating vectorized data from text or files.
 Home-page: https://github.com/PedroHenriqueDevBR/vectoriz
 Author: PedroHenriqueDevBR
@@ -25,6 +25,24 @@ Dynamic: summary
 
 # Vectoriz
 
+[![PyPI version](https://badge.fury.io/py/vectoriz.svg)](https://pypi.org/project/vectoriz/)
+
+[![GitHub license](https://img.shields.io/github/license/PedroHenriqueDevBR/vectoriz)](https://github.com/PedroHenriqueDevBR/vectoriz/blob/main/LICENSE)
+
+[![Python Version](https://img.shields.io/badge/python-3.12%2B-blue)](https://www.python.org/downloads/)
+
+[![GitHub issues](https://img.shields.io/github/issues/PedroHenriqueDevBR/vectoriz)](https://github.com/PedroHenriqueDevBR/vectoriz/issues)
+
+[![GitHub stars](https://img.shields.io/github/stars/PedroHenriqueDevBR/vectoriz)](https://github.com/PedroHenriqueDevBR/vectoriz/stargazers)
+
+[![GitHub forks](https://img.shields.io/github/forks/PedroHenriqueDevBR/vectoriz)](https://github.com/PedroHenriqueDevBR/vectoriz/network)
+
+Vectoriz is available on PyPI and can be installed via pip:
+
+```bash
+pip install vectoriz
+```
+
 A tool for generating vector embeddings for Retrieval-Augmented Generation (RAG) applications.
 
 ## Overview
@@ -63,7 +81,8 @@ files_features = FilesFeature()
 argument = files_features.load_all_files_from_directory(directory_path)
 
 # Created FAISS index to be used in queries
-index = transformer.create_index(argument.text_list)
+token_data = transformer.create_index(argument.text_list)
+index = token_data.index
 
 # To load files from VectorDB use
 vector_client = VectorDBClient()
@@ -74,6 +93,12 @@ argument = vector_client.file_argument
 # To save data on VectorDB use
 vector_client = VectorDBClient(index, argument)
 vector_client.save_data(index_db_path, np_db_path)
+
+# To search information on index
+query = input(">>> ")
+amoount_content = 1
+response = self.transformer.search(query, self.index, self.argument.text_list, amoount_content)
+print(response)
 ```
 
 ## Contributing

vectoriz-0.1.0b0.dist-info/RECORD

@@ -0,0 +1,10 @@
+tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tests/test_files.py,sha256=jNIcwdDrPGKv78zGJReb6s0kPZLr3mTvkwwl3cP6MlM,1622
+vectoriz/__init__.py,sha256=fnnle0EjVejiZQ8t243kvFiqcTTFh9dzmZbNwayjh4U,156
+vectoriz/files.py,sha256=VxqRlHgUVUm2Afq7LX5YMvEX5T1XgQW8he2r4NY9WPQ,9041
+vectoriz/token_transformer.py,sha256=1KIGL6EAiuqFhFzh3grkJcdEjjwTC3kH6RNqRkYMkQU,5811
+vectoriz/vector_db.py,sha256=xxQjhfLiZ4inV5XHYHWcr-RRbH2BcpSCqTli9lOv_g8,6835
+vectoriz-0.1.0b0.dist-info/METADATA,sha256=nohEcf7bCgvQDBM4fyhKfpLS7lLWAlWk9TRHX1TTR5o,3696
+vectoriz-0.1.0b0.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
+vectoriz-0.1.0b0.dist-info/top_level.txt,sha256=Tcfk3kazBwJ_yySjjhlIhLoTWLQGSb5xV006X18O6Nk,15
+vectoriz-0.1.0b0.dist-info/RECORD,,

vectoriz-0.0.4.dist-info/RECORD

@@ -1,10 +0,0 @@
-tests/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/test_files.py,sha256=jNIcwdDrPGKv78zGJReb6s0kPZLr3mTvkwwl3cP6MlM,1622
-vectoriz/__init__.py,sha256=fnnle0EjVejiZQ8t243kvFiqcTTFh9dzmZbNwayjh4U,156
-vectoriz/files.py,sha256=dbieWMdYYWWc6XPse3Al-VQnAJyXTj_Kmi31zUtUyHY,9040
-vectoriz/token_transformer.py,sha256=mfn3UI8i1x108iQ5dV_FyA-IhZoSSlXl7yO39s0m7C0,5786
-vectoriz/vector_db.py,sha256=_2dcq-9F9_tmu543Uw5-lKJiLA00QpaBebRBtwzecxI,7052
-vectoriz-0.0.4.dist-info/METADATA,sha256=fP_HtDi58xT-zn9VxLwjfAyM7oWyDgI7Kma1-mdEoz8,2603
-vectoriz-0.0.4.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-vectoriz-0.0.4.dist-info/top_level.txt,sha256=Tcfk3kazBwJ_yySjjhlIhLoTWLQGSb5xV006X18O6Nk,15
-vectoriz-0.0.4.dist-info/RECORD,,