vish-rag-lib 0.1.1__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -0,0 +1,48 @@
1
+ Metadata-Version: 2.4
2
+ Name: vish-rag-lib
3
+ Version: 0.1.1
4
+ Summary: Simple RAG library
5
+ Author: Vishakha
6
+ Author-email: Vishakha <badgujarvishakha8@gmail.com>
7
+ Requires-Python: >=3.8
8
+ Description-Content-Type: text/markdown
9
+ Requires-Dist: numpy
10
+ Requires-Dist: faiss-cpu
11
+ Requires-Dist: sentence-transformers
12
+ Requires-Dist: requests
13
+ Requires-Dist: PyPDF2
14
+ Dynamic: author
15
+ Dynamic: requires-python
16
+
17
+ # Vishakha Rag lib
18
+ A simple RAG (Retrival-Agumented-Generation) Library Using PDFs and LLMs.
19
+
20
+ ## Features ##
21
+ -Load Pdf files
22
+ -Chuks texts
23
+ -generate embeddings
24
+ -store in vector database
25
+ -search nearast vectors
26
+ -Retirive revelant Data
27
+ -Connect With any LLM Api
28
+
29
+ ## Usage ##
30
+ ''' Python
31
+ from vish_rag_lib import RAGSystem
32
+
33
+ rag=RAGSystem()
34
+ rag.ingest("Sample.pdf")
35
+
36
+ def my_llm(prompt):
37
+ return "LLM respones"
38
+ answer=rag.ask("What is AI?",my_llm)
39
+ print(answer)
40
+
41
+ # Installation #
42
+ pip install vish-rag-lib
43
+
44
+ # Work-Flow-RAG #
45
+ Chunks-Text divided into small Parts
46
+ Embedding-Sentence convert into meaining base vectors
47
+ vectors-Loading embeddings search the similar queary answers
48
+ Retriever- User queary storted in vectorDB (Most relevan chunks search)
@@ -0,0 +1,32 @@
1
+ # Vishakha Rag lib
2
+ A simple RAG (Retrival-Agumented-Generation) Library Using PDFs and LLMs.
3
+
4
+ ## Features ##
5
+ -Load Pdf files
6
+ -Chuks texts
7
+ -generate embeddings
8
+ -store in vector database
9
+ -search nearast vectors
10
+ -Retirive revelant Data
11
+ -Connect With any LLM Api
12
+
13
+ ## Usage ##
14
+ ''' Python
15
+ from vish_rag_lib import RAGSystem
16
+
17
+ rag=RAGSystem()
18
+ rag.ingest("Sample.pdf")
19
+
20
+ def my_llm(prompt):
21
+ return "LLM respones"
22
+ answer=rag.ask("What is AI?",my_llm)
23
+ print(answer)
24
+
25
+ # Installation #
26
+ pip install vish-rag-lib
27
+
28
+ # Work-Flow-RAG #
29
+ Chunks-Text divided into small Parts
30
+ Embedding-Sentence convert into meaining base vectors
31
+ vectors-Loading embeddings search the similar queary answers
32
+ Retriever- User queary storted in vectorDB (Most relevan chunks search)
@@ -0,0 +1,21 @@
1
+ [build-system]
2
+ requires = ["setuptools>=61.0"]
3
+ build-backend = "setuptools.build_meta"
4
+
5
+ [project]
6
+ name = "vish-rag-lib"
7
+ version = "0.1.1"
8
+ description = "Simple RAG library"
9
+ authors = [
10
+ { name="Vishakha", email="badgujarvishakha8@gmail.com" }
11
+ ]
12
+ readme = "README.md"
13
+ requires-python = ">=3.8"
14
+
15
+ dependencies = [
16
+ "numpy",
17
+ "faiss-cpu",
18
+ "sentence-transformers",
19
+ "requests",
20
+ "PyPDF2"
21
+ ]
@@ -0,0 +1,4 @@
1
+ [egg_info]
2
+ tag_build =
3
+ tag_date = 0
4
+
@@ -0,0 +1,19 @@
1
+ from setuptools import setup, find_packages
2
+
3
+ setup(
4
+ name="vish-rag-lib",
5
+ version="0.1.1",
6
+ author="Vishakha",
7
+ description="Simple RAG library",
8
+ long_description=open("README.md", encoding="utf-8").read(),
9
+ long_description_content_type="text/markdown",
10
+ packages=find_packages(),
11
+ install_requires=[
12
+ "numpy",
13
+ "faiss-cpu",
14
+ "sentence-transformers",
15
+ "requests",
16
+ "PyPDF2"
17
+ ],
18
+ python_requires=">=3.8",
19
+ )
@@ -0,0 +1,48 @@
1
+ Metadata-Version: 2.4
2
+ Name: vish-rag-lib
3
+ Version: 0.1.1
4
+ Summary: Simple RAG library
5
+ Author: Vishakha
6
+ Author-email: Vishakha <badgujarvishakha8@gmail.com>
7
+ Requires-Python: >=3.8
8
+ Description-Content-Type: text/markdown
9
+ Requires-Dist: numpy
10
+ Requires-Dist: faiss-cpu
11
+ Requires-Dist: sentence-transformers
12
+ Requires-Dist: requests
13
+ Requires-Dist: PyPDF2
14
+ Dynamic: author
15
+ Dynamic: requires-python
16
+
17
+ # Vishakha Rag lib
18
+ A simple RAG (Retrival-Agumented-Generation) Library Using PDFs and LLMs.
19
+
20
+ ## Features ##
21
+ -Load Pdf files
22
+ -Chuks texts
23
+ -generate embeddings
24
+ -store in vector database
25
+ -search nearast vectors
26
+ -Retirive revelant Data
27
+ -Connect With any LLM Api
28
+
29
+ ## Usage ##
30
+ ''' Python
31
+ from vish_rag_lib import RAGSystem
32
+
33
+ rag=RAGSystem()
34
+ rag.ingest("Sample.pdf")
35
+
36
+ def my_llm(prompt):
37
+ return "LLM respones"
38
+ answer=rag.ask("What is AI?",my_llm)
39
+ print(answer)
40
+
41
+ # Installation #
42
+ pip install vish-rag-lib
43
+
44
+ # Work-Flow-RAG #
45
+ Chunks-Text divided into small Parts
46
+ Embedding-Sentence convert into meaining base vectors
47
+ vectors-Loading embeddings search the similar queary answers
48
+ Retriever- User queary storted in vectorDB (Most relevan chunks search)
@@ -0,0 +1,8 @@
1
+ README.md
2
+ pyproject.toml
3
+ setup.py
4
+ vish_rag_lib.egg-info/PKG-INFO
5
+ vish_rag_lib.egg-info/SOURCES.txt
6
+ vish_rag_lib.egg-info/dependency_links.txt
7
+ vish_rag_lib.egg-info/requires.txt
8
+ vish_rag_lib.egg-info/top_level.txt
@@ -0,0 +1,5 @@
1
+ numpy
2
+ faiss-cpu
3
+ sentence-transformers
4
+ requests
5
+ PyPDF2