Spaces:
Build error
Build error
changed from pdf to url loader
Browse files
app.py
CHANGED
@@ -6,7 +6,7 @@ from langchain.text_splitter import CharacterTextSplitter
|
|
6 |
text_splitter = CharacterTextSplitter(chunk_size=350, chunk_overlap=0)
|
7 |
|
8 |
from langchain.llms import HuggingFaceHub
|
9 |
-
|
10 |
|
11 |
from langchain.embeddings import HuggingFaceHubEmbeddings
|
12 |
embeddings = HuggingFaceHubEmbeddings()
|
@@ -14,17 +14,19 @@ embeddings = HuggingFaceHubEmbeddings()
|
|
14 |
from langchain.vectorstores import Chroma
|
15 |
|
16 |
from langchain.chains import RetrievalQA
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
|
|
|
|
28 |
|
29 |
def add_text(history, text):
|
30 |
history = history + [(text, None)]
|
@@ -57,19 +59,10 @@ title = """
|
|
57 |
|
58 |
with gr.Blocks(css=css) as demo:
|
59 |
with gr.Column(elem_id="col-container"):
|
60 |
-
gr.HTML(title)
|
61 |
-
|
62 |
-
with gr.Column():
|
63 |
-
pdf_doc = gr.File(label="Load a pdf", file_types=['.pdf'], type="file")
|
64 |
-
with gr.Row():
|
65 |
-
langchain_status = gr.Textbox(label="Status", placeholder="", interactive=False)
|
66 |
-
load_pdf = gr.Button("Load pdf to langchain")
|
67 |
-
|
68 |
chatbot = gr.Chatbot([], elem_id="chatbot").style(height=350)
|
69 |
with gr.Row():
|
70 |
question = gr.Textbox(label="Question", placeholder="Type your question and hit Enter ")
|
71 |
-
load_pdf.click(loading_pdf, None, langchain_status, queue=False)
|
72 |
-
load_pdf.click(pdf_changes, pdf_doc, langchain_status, queue=False)
|
73 |
question.submit(add_text, [chatbot, question], [chatbot, question]).then(
|
74 |
bot, chatbot, chatbot
|
75 |
)
|
|
|
6 |
text_splitter = CharacterTextSplitter(chunk_size=350, chunk_overlap=0)
|
7 |
|
8 |
from langchain.llms import HuggingFaceHub
|
9 |
+
model_id = HuggingFaceHub(repo_id="HuggingFaceH4/zephyr-7b-beta", model_kwargs={"temperature":0.1, "max_new_tokens":300})
|
10 |
|
11 |
from langchain.embeddings import HuggingFaceHubEmbeddings
|
12 |
embeddings = HuggingFaceHubEmbeddings()
|
|
|
14 |
from langchain.vectorstores import Chroma
|
15 |
|
16 |
from langchain.chains import RetrievalQA
|
17 |
+
|
18 |
+
from langchain.document_loaders import WebBaseLoader
|
19 |
+
|
20 |
+
web_links = ["https://www.databricks.com/","https://help.databricks.com","https://databricks.com/try-databricks","https://help.databricks.com/s/","https://docs.databricks.com","https://kb.databricks.com/","http://docs.databricks.com/getting-started/index.html","http://docs.databricks.com/introduction/index.html","http://docs.databricks.com/getting-started/tutorials/index.html","http://docs.databricks.com/release-notes/index.html","http://docs.databricks.com/ingestion/index.html","http://docs.databricks.com/exploratory-data-analysis/index.html","http://docs.databricks.com/data-preparation/index.html","http://docs.databricks.com/data-sharing/index.html","http://docs.databricks.com/marketplace/index.html","http://docs.databricks.com/workspace-index.html","http://docs.databricks.com/machine-learning/index.html","http://docs.databricks.com/sql/index.html","http://docs.databricks.com/delta/index.html","http://docs.databricks.com/dev-tools/index.html","http://docs.databricks.com/integrations/index.html","http://docs.databricks.com/administration-guide/index.html","http://docs.databricks.com/security/index.html","http://docs.databricks.com/data-governance/index.html","http://docs.databricks.com/lakehouse-architecture/index.html","http://docs.databricks.com/reference/api.html","http://docs.databricks.com/resources/index.html","http://docs.databricks.com/whats-coming.html","http://docs.databricks.com/archive/index.html","http://docs.databricks.com/lakehouse/index.html","http://docs.databricks.com/getting-started/quick-start.html","http://docs.databricks.com/getting-started/etl-quick-start.html","http://docs.databricks.com/getting-started/lakehouse-e2e.html","http://docs.databricks.com/getting-started/free-training.html","http://docs.databricks.com/sql/language-manual/index.html","http://docs.databricks.com/error-messages/index.html","http://www.apache.org/","https://databricks.com/privacy-policy","https://databricks.com/terms-of-use"]
|
21 |
+
loader = WebBaseLoader(web_links)
|
22 |
+
documents = loader.load()
|
23 |
+
|
24 |
+
texts = text_splitter.split_documents(documents)
|
25 |
+
db = Chroma.from_documents(texts, embeddings)
|
26 |
+
retriever = db.as_retriever()
|
27 |
+
global qa
|
28 |
+
qa = RetrievalQA.from_chain_type(llm=model_id, chain_type="stuff", retriever=retriever, return_source_documents=True)
|
29 |
+
|
30 |
|
31 |
def add_text(history, text):
|
32 |
history = history + [(text, None)]
|
|
|
59 |
|
60 |
with gr.Blocks(css=css) as demo:
|
61 |
with gr.Column(elem_id="col-container"):
|
62 |
+
gr.HTML(title)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
chatbot = gr.Chatbot([], elem_id="chatbot").style(height=350)
|
64 |
with gr.Row():
|
65 |
question = gr.Textbox(label="Question", placeholder="Type your question and hit Enter ")
|
|
|
|
|
66 |
question.submit(add_text, [chatbot, question], [chatbot, question]).then(
|
67 |
bot, chatbot, chatbot
|
68 |
)
|