Update app.py
Browse files
app.py
CHANGED
@@ -3,27 +3,37 @@ import gradio as gr
|
|
3 |
from langchain.document_loaders import OnlinePDFLoader
|
4 |
|
5 |
from langchain.text_splitter import CharacterTextSplitter
|
6 |
-
text_splitter = CharacterTextSplitter(chunk_size=350, chunk_overlap=0)
|
7 |
|
8 |
from langchain.llms import HuggingFaceHub
|
9 |
-
flan_ul2 = HuggingFaceHub(repo_id="google/flan-ul2", model_kwargs={"temperature":0.1, "max_new_tokens":300})
|
10 |
|
11 |
from langchain.embeddings import HuggingFaceHubEmbeddings
|
12 |
-
embeddings = HuggingFaceHubEmbeddings()
|
13 |
|
14 |
from langchain.vectorstores import Chroma
|
15 |
|
16 |
from langchain.chains import RetrievalQA
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
def loading_pdf():
|
18 |
return "Loading..."
|
|
|
19 |
def pdf_changes(pdf_doc):
|
|
|
20 |
loader = OnlinePDFLoader(pdf_doc.name)
|
21 |
documents = loader.load()
|
|
|
22 |
texts = text_splitter.split_documents(documents)
|
|
|
23 |
db = Chroma.from_documents(texts, embeddings)
|
24 |
retriever = db.as_retriever()
|
25 |
global qa
|
26 |
-
qa = RetrievalQA.from_chain_type(llm=
|
27 |
return "Ready"
|
28 |
|
29 |
def add_text(history, text):
|
|
|
3 |
from langchain.document_loaders import OnlinePDFLoader
|
4 |
|
5 |
from langchain.text_splitter import CharacterTextSplitter
|
|
|
6 |
|
7 |
from langchain.llms import HuggingFaceHub
|
|
|
8 |
|
9 |
from langchain.embeddings import HuggingFaceHubEmbeddings
|
|
|
10 |
|
11 |
from langchain.vectorstores import Chroma
|
12 |
|
13 |
from langchain.chains import RetrievalQA
|
14 |
+
|
15 |
+
global llm
|
16 |
+
|
17 |
+
def define_llm_model(repo_id):
|
18 |
+
llm = HuggingFaceHub(repo_id=repo_id, model_kwargs={"temperature":0.1, "max_new_tokens":300})
|
19 |
+
return "LLM model loaded"
|
20 |
+
|
21 |
+
define_llm_model("google/flan-ul2")
|
22 |
+
|
23 |
def loading_pdf():
|
24 |
return "Loading..."
|
25 |
+
|
26 |
def pdf_changes(pdf_doc):
|
27 |
+
|
28 |
loader = OnlinePDFLoader(pdf_doc.name)
|
29 |
documents = loader.load()
|
30 |
+
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
|
31 |
texts = text_splitter.split_documents(documents)
|
32 |
+
embeddings = HuggingFaceHubEmbeddings()
|
33 |
db = Chroma.from_documents(texts, embeddings)
|
34 |
retriever = db.as_retriever()
|
35 |
global qa
|
36 |
+
qa = RetrievalQA.from_chain_type(llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True)
|
37 |
return "Ready"
|
38 |
|
39 |
def add_text(history, text):
|