Update Class and release 0.2.2

Signed-off-by: samadpls <[email protected]>

README.md

@@ -10,9 +10,14 @@
 
 
 
-Welcome to **BestRAG**! This Python library enables you to efficiently store and retrieve embeddings using a hybrid Retrieval-Augmented Generation (RAG) approach. It combines dense, sparse, and late interaction embeddings to provide a robust solution for handling large datasets.
+Introducing **BestRAG**! This Python library leverages a hybrid Retrieval-Augmented Generation (RAG) approach to efficiently store and retrieve embeddings. By combining dense, sparse, and late interaction embeddings, **BestRAG** offers a robust solution for managing large datasets.
 
----
+
+## ✨ Features
+
+🚀 **Hybrid RAG**: Utilizes dense, sparse, and late interaction embeddings for enhanced performance.  
+🔌 **Easy Integration**: Simple API for storing and searching embeddings.  
+📄 **PDF Support**: Directly store embeddings from PDF documents.  
 
 ## 🚀 Installation
 
@@ -43,13 +48,7 @@ results = rag.search(query="your search query", limit=10)
 print(results)
 ```
 
-> **Note**: To generate your API key and endpoint, visit [Qdrant](https://qdrant.tech/).
-
-## ✨ Features
-
-- **Hybrid RAG**: Utilizes dense, sparse, and late interaction embeddings for enhanced performance.
-- **Easy Integration**: Simple API for storing and searching embeddings.
-- **PDF Support**: Directly store embeddings from PDF documents.
+> **Note**: Qdrant offers a free tier with 1GB of storage. To generate your API key and endpoint, visit [Qdrant](https://qdrant.tech/).
 
 ## 🤝 Contributing
 

bestrag/best_rag.py

@@ -1,11 +1,11 @@
-"""B-RAG"""
+"""BestRAG"""
 # Authors: Abdul Samad Siddiqui <[email protected]>
 
 import re
 import uuid
 from typing import List, Optional
 from qdrant_client import QdrantClient, models
-from qdrant_client.http.models import Distance, VectorParams
+from qdrant_client.http.models import Distance
 from fastembed import TextEmbedding
 from fastembed.sparse.bm25 import Bm25
 import PyPDF2
@@ -35,6 +35,8 @@ def __init__(self,
                  late_interaction_model_name: Optional[str] = "BAAI/bge-small-en-v1.5"
                  ):
         self.collection_name = collection_name
+        self.api_key = api_key
+        self.url = url
         self.client = QdrantClient(url=url, api_key=api_key)
 
         self.dense_model = TextEmbedding()
@@ -216,7 +218,7 @@ def search(self, query: str, limit: int = 10):
                 models.Prefetch(
                     query=query_vector["dense-vector"],
                     using="dense-vector",
-                    limit=50,
+                    limit=20,
                 )
             ],
             query=query_vector["output-token-embeddings"],
@@ -225,3 +227,18 @@ def search(self, query: str, limit: int = 10):
         )
 
         return results
+
+    def __str__(self):
+        """
+        Return a string representation of the BestRAG object, including its parameters.
+        """
+        info = (
+            "**************************************************\n"
+            "* BestRAG Object Information                     *\n"
+            "**************************************************\n"
+            f"* URL: {self.url}\n"
+            f"* API Key: {self.api_key}\n"
+            f"* Collection Name: {self.collection_name}\n"
+            "**************************************************"
+        )
+        return info

requirements.txt

@@ -2,7 +2,7 @@ fastembed==0.4.1
 streamlit
 pytest
 flake8
-PyPDF2
+PyPDF2==3.0.1
 qdrant-client
 onnxruntime==1.19.2
 pytest

setup.py

@@ -5,10 +5,8 @@
 
 setup(
     name="bestrag",
-    version="0.2.0",
-    description="BestRAG (Best Retrieval Augmented) is a library for storing and"
-    " searching document embeddings in a Qdrant vector database. It uses a "
-    "hybrid embedding technique combining dense, late interaction and sparse representations for better performance.",
+    version="0.2.1",
+    description="bestrag: Library for storing and searching document embeddings in a Qdrant vector database using hybrid embedding techniques.",
     author="samadpls",
     author_email="[email protected]",
     long_description=long_description,
@@ -17,10 +15,7 @@
     packages=find_packages(),
     install_requires=[
         "fastembed==0.4.1",
-        "streamlit",
-        "pytest",
-        "flake8",
-        "PyPDF2",
+        "PyPDF2==3.0.1",
         "qdrant-client",
         "onnxruntime==1.19.2",
     ],