fullstack-rag-ai 0.1.0__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.
- fullstack_rag_ai-0.1.0/PKG-INFO +12 -0
- fullstack_rag_ai-0.1.0/README.md +0 -0
- fullstack_rag_ai-0.1.0/fullstack_rag_ai.egg-info/PKG-INFO +12 -0
- fullstack_rag_ai-0.1.0/fullstack_rag_ai.egg-info/SOURCES.txt +13 -0
- fullstack_rag_ai-0.1.0/fullstack_rag_ai.egg-info/dependency_links.txt +1 -0
- fullstack_rag_ai-0.1.0/fullstack_rag_ai.egg-info/requires.txt +7 -0
- fullstack_rag_ai-0.1.0/fullstack_rag_ai.egg-info/top_level.txt +1 -0
- fullstack_rag_ai-0.1.0/fullstack_rag_lib/__init__.py +3 -0
- fullstack_rag_ai-0.1.0/fullstack_rag_lib/config.py +11 -0
- fullstack_rag_ai-0.1.0/fullstack_rag_lib/fullstack_rag_pipeline.py +35 -0
- fullstack_rag_ai-0.1.0/fullstack_rag_lib/ingestion.py +13 -0
- fullstack_rag_ai-0.1.0/fullstack_rag_lib/loaders.py +12 -0
- fullstack_rag_ai-0.1.0/fullstack_rag_lib/vectordb.py +20 -0
- fullstack_rag_ai-0.1.0/pyproject.toml +22 -0
- fullstack_rag_ai-0.1.0/setup.cfg +4 -0
|
@@ -0,0 +1,12 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: fullstack-rag-ai
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: Lightweight RAG library for internal knowledge systems
|
|
5
|
+
Author: fullstack
|
|
6
|
+
Requires-Dist: langchain
|
|
7
|
+
Requires-Dist: langchain-community
|
|
8
|
+
Requires-Dist: langchain-huggingface
|
|
9
|
+
Requires-Dist: langchain-ollama
|
|
10
|
+
Requires-Dist: faiss-cpu
|
|
11
|
+
Requires-Dist: sentence-transformers
|
|
12
|
+
Requires-Dist: pypdf
|
|
File without changes
|
|
@@ -0,0 +1,12 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: fullstack-rag-ai
|
|
3
|
+
Version: 0.1.0
|
|
4
|
+
Summary: Lightweight RAG library for internal knowledge systems
|
|
5
|
+
Author: fullstack
|
|
6
|
+
Requires-Dist: langchain
|
|
7
|
+
Requires-Dist: langchain-community
|
|
8
|
+
Requires-Dist: langchain-huggingface
|
|
9
|
+
Requires-Dist: langchain-ollama
|
|
10
|
+
Requires-Dist: faiss-cpu
|
|
11
|
+
Requires-Dist: sentence-transformers
|
|
12
|
+
Requires-Dist: pypdf
|
|
@@ -0,0 +1,13 @@
|
|
|
1
|
+
README.md
|
|
2
|
+
pyproject.toml
|
|
3
|
+
fullstack_rag_ai.egg-info/PKG-INFO
|
|
4
|
+
fullstack_rag_ai.egg-info/SOURCES.txt
|
|
5
|
+
fullstack_rag_ai.egg-info/dependency_links.txt
|
|
6
|
+
fullstack_rag_ai.egg-info/requires.txt
|
|
7
|
+
fullstack_rag_ai.egg-info/top_level.txt
|
|
8
|
+
fullstack_rag_lib/__init__.py
|
|
9
|
+
fullstack_rag_lib/config.py
|
|
10
|
+
fullstack_rag_lib/fullstack_rag_pipeline.py
|
|
11
|
+
fullstack_rag_lib/ingestion.py
|
|
12
|
+
fullstack_rag_lib/loaders.py
|
|
13
|
+
fullstack_rag_lib/vectordb.py
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
fullstack_rag_lib
|
|
@@ -0,0 +1,35 @@
|
|
|
1
|
+
from langchain_community.vectorstores import FAISS
|
|
2
|
+
from langchain_huggingface import HuggingFaceEmbeddings
|
|
3
|
+
from langchain_ollama import ChatOllama
|
|
4
|
+
import warnings
|
|
5
|
+
warnings.filterwarnings("ignore")
|
|
6
|
+
|
|
7
|
+
def ask_question(question, index_path, model, embedding_model):
|
|
8
|
+
|
|
9
|
+
embeddings = HuggingFaceEmbeddings(
|
|
10
|
+
model_name=embedding_model
|
|
11
|
+
)
|
|
12
|
+
|
|
13
|
+
vectordb = FAISS.load_local(
|
|
14
|
+
index_path,
|
|
15
|
+
embeddings,
|
|
16
|
+
allow_dangerous_deserialization=True
|
|
17
|
+
)
|
|
18
|
+
|
|
19
|
+
docs = vectordb.similarity_search(question, k=3)
|
|
20
|
+
|
|
21
|
+
context = "\n\n".join(d.page_content for d in docs)
|
|
22
|
+
|
|
23
|
+
llm = ChatOllama(model=model)
|
|
24
|
+
|
|
25
|
+
prompt = f"""
|
|
26
|
+
Answer using the context below.
|
|
27
|
+
|
|
28
|
+
Context:
|
|
29
|
+
{context}
|
|
30
|
+
|
|
31
|
+
Question:
|
|
32
|
+
{question}
|
|
33
|
+
"""
|
|
34
|
+
|
|
35
|
+
return llm.invoke(prompt)
|
|
@@ -0,0 +1,13 @@
|
|
|
1
|
+
import os
|
|
2
|
+
from langchain_community.document_loaders import PyPDFLoader
|
|
3
|
+
|
|
4
|
+
def load_documents(path):
|
|
5
|
+
|
|
6
|
+
documents = []
|
|
7
|
+
|
|
8
|
+
for file in os.listdir(path):
|
|
9
|
+
if file.endswith(".pdf"):
|
|
10
|
+
loader = PyPDFLoader(os.path.join(path, file))
|
|
11
|
+
documents.extend(loader.load())
|
|
12
|
+
|
|
13
|
+
return documents
|
|
@@ -0,0 +1,20 @@
|
|
|
1
|
+
from langchain.text_splitter import RecursiveCharacterTextSplitter
|
|
2
|
+
from langchain_community.vectorstores import FAISS
|
|
3
|
+
from langchain_huggingface import HuggingFaceEmbeddings
|
|
4
|
+
|
|
5
|
+
def build_vector_db(documents, index_path, embedding_model):
|
|
6
|
+
|
|
7
|
+
splitter = RecursiveCharacterTextSplitter(
|
|
8
|
+
chunk_size=800,
|
|
9
|
+
chunk_overlap=100
|
|
10
|
+
)
|
|
11
|
+
|
|
12
|
+
chunks = splitter.split_documents(documents)
|
|
13
|
+
|
|
14
|
+
embeddings = HuggingFaceEmbeddings(
|
|
15
|
+
model_name=embedding_model
|
|
16
|
+
)
|
|
17
|
+
|
|
18
|
+
vectorstore = FAISS.from_documents(chunks, embeddings)
|
|
19
|
+
|
|
20
|
+
vectorstore.save_local(index_path)
|
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
[project]
|
|
2
|
+
name = "fullstack-rag-ai"
|
|
3
|
+
version = "0.1.0"
|
|
4
|
+
description = "Lightweight RAG library for internal knowledge systems"
|
|
5
|
+
authors = [{name = "fullstack"}]
|
|
6
|
+
dependencies = [
|
|
7
|
+
"langchain",
|
|
8
|
+
"langchain-community",
|
|
9
|
+
"langchain-huggingface",
|
|
10
|
+
"langchain-ollama",
|
|
11
|
+
"faiss-cpu",
|
|
12
|
+
"sentence-transformers",
|
|
13
|
+
"pypdf"
|
|
14
|
+
]
|
|
15
|
+
|
|
16
|
+
[build-system]
|
|
17
|
+
requires = ["setuptools", "wheel"]
|
|
18
|
+
build-backend = "setuptools.build_meta"
|
|
19
|
+
|
|
20
|
+
[tool.setuptools.packages.find]
|
|
21
|
+
where = ["."]
|
|
22
|
+
include = ["fullstack_rag_lib*"]
|