Spaces:
Paused
Paused
Update app.py
Browse files
app.py
CHANGED
|
@@ -3,16 +3,15 @@ import datetime
|
|
| 3 |
import warnings
|
| 4 |
import gradio as gr
|
| 5 |
|
| 6 |
-
# Suppress
|
| 7 |
warnings.filterwarnings("ignore", category=UserWarning, module="langchain_community")
|
| 8 |
|
| 9 |
from langchain_community.vectorstores import Chroma
|
| 10 |
from langchain_huggingface import HuggingFaceEmbeddings, HuggingFaceEndpoint
|
| 11 |
-
from langchain_core.prompts import
|
| 12 |
-
from langchain_core.runnables import RunnablePassthrough
|
| 13 |
from langchain_core.output_parsers import StrOutputParser
|
| 14 |
|
| 15 |
-
# 1. Fetching the Hugging Face Space security token
|
| 16 |
hf_token = os.environ.get("HF_TOKEN") or os.environ.get("HUGGINGFACEHUB_API_TOKEN")
|
| 17 |
|
| 18 |
# 2. Setup Vector Store & Embeddings Pipeline (Using ChromaDB)
|
|
@@ -28,43 +27,43 @@ simplilearn_faq_data = [
|
|
| 28 |
"Data Science Bootcamp Prerequisites: This flagship program spans 6 months. It requires basic exposure to high-school level mathematics and rudimentary programming logic (Python familiarity is highly recommended but not mandatory)."
|
| 29 |
]
|
| 30 |
|
| 31 |
-
# Create an in-memory Chroma instance
|
| 32 |
vectorstore = Chroma.from_texts(texts=simplilearn_faq_data, embedding=embeddings)
|
| 33 |
retriever = vectorstore.as_retriever(search_type="similarity", search_kwargs={"k": 2})
|
| 34 |
|
| 35 |
# 3. Setup Low Parameter Open-Source LLM Generator via Serverless API
|
| 36 |
print("Configuring LLM Interface...")
|
| 37 |
chatModel = HuggingFaceEndpoint(
|
| 38 |
-
repo_id="Qwen/Qwen2.5-1.5B-Instruct",
|
| 39 |
task="text-generation",
|
| 40 |
-
max_new_tokens=500,
|
| 41 |
-
temperature=0.
|
| 42 |
do_sample=False,
|
| 43 |
huggingfacehub_api_token=hf_token
|
| 44 |
)
|
| 45 |
|
| 46 |
-
# 4. Constructing the Chain using
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
("system", system_prompt),
|
| 59 |
-
("human", "{input}"),
|
| 60 |
-
]
|
| 61 |
-
)
|
| 62 |
|
| 63 |
-
# Helper function to combine document chunks
|
| 64 |
def format_docs(docs):
|
| 65 |
return "\n\n".join(doc.page_content for doc in docs)
|
| 66 |
|
| 67 |
-
# The modern LCEL pipeline
|
| 68 |
rag_chain = (
|
| 69 |
{
|
| 70 |
"context": lambda x: format_docs(retriever.invoke(x["input"])),
|
|
@@ -75,7 +74,7 @@ rag_chain = (
|
|
| 75 |
| StrOutputParser()
|
| 76 |
)
|
| 77 |
|
| 78 |
-
# 5. UI Event Handlers
|
| 79 |
def process_chat(message, history):
|
| 80 |
if not message.strip():
|
| 81 |
return "", history
|
|
@@ -84,25 +83,31 @@ def process_chat(message, history):
|
|
| 84 |
history = []
|
| 85 |
|
| 86 |
try:
|
| 87 |
-
# Executes
|
| 88 |
bot_response = rag_chain.invoke({"input": message})
|
|
|
|
|
|
|
|
|
|
|
|
|
| 89 |
except Exception as e:
|
|
|
|
| 90 |
bot_response = (
|
| 91 |
-
f"
|
| 92 |
-
f"
|
|
|
|
|
|
|
| 93 |
)
|
| 94 |
|
| 95 |
-
# Appending messages via
|
| 96 |
history.append({"role": "user", "content": message})
|
| 97 |
history.append({"role": "assistant", "content": bot_response})
|
| 98 |
return "", history
|
| 99 |
|
| 100 |
-
# Handles automatic prompt submission when clicking dashboard quick-action buttons
|
| 101 |
def click_preset_button(button_text, history):
|
| 102 |
_, updated_history = process_chat(button_text, history)
|
| 103 |
return updated_history
|
| 104 |
|
| 105 |
-
# 6. Custom CSS UI Styling
|
| 106 |
custom_css = """
|
| 107 |
.dashboard-container { background: linear-gradient(135deg, #e1f5fe 0%, #e8f5e9 100%); padding: 20px; border-radius: 12px; min-height: 100vh; }
|
| 108 |
.about-section { background-color: #002f6c; color: white; padding: 25px; border-radius: 8px; }
|
|
@@ -112,7 +117,6 @@ custom_css = """
|
|
| 112 |
.preset-btn { background-color: #e0f7fa !important; border: 1px solid #b2ebf2 !important; color: #006064 !important; font-weight: 600; }
|
| 113 |
"""
|
| 114 |
|
| 115 |
-
# Client-side JavaScript execution string for instant Day/Night toggles
|
| 116 |
toggle_js = """
|
| 117 |
function() {
|
| 118 |
var body = document.querySelector('body');
|
|
@@ -124,10 +128,9 @@ function() {
|
|
| 124 |
}
|
| 125 |
"""
|
| 126 |
|
| 127 |
-
# 7. Building the Visual Workspace Layout
|
| 128 |
with gr.Blocks(elem_classes=["dashboard-container"]) as demo:
|
| 129 |
|
| 130 |
-
# Header Row: About Us Introduction & Live Clock/Theme Controller
|
| 131 |
with gr.Row():
|
| 132 |
with gr.Column(scale=2, elem_classes=["about-section"]):
|
| 133 |
gr.Markdown("<div class='about-title'>About Us</div>")
|
|
@@ -145,13 +148,10 @@ with gr.Blocks(elem_classes=["dashboard-container"]) as demo:
|
|
| 145 |
|
| 146 |
gr.Markdown("<br>")
|
| 147 |
|
| 148 |
-
# Main Core Interface Workspace Row
|
| 149 |
with gr.Row():
|
| 150 |
-
# Chat Framework Engine
|
| 151 |
with gr.Column(scale=3):
|
| 152 |
chatbot = gr.Chatbot(label="Simplilearn FAQ Support Stream")
|
| 153 |
|
| 154 |
-
# Interactive Quick-Action Buttons Layout (Realigned to Simplilearn Scope)
|
| 155 |
with gr.Row():
|
| 156 |
preset_refund = gr.Button("What is the course refund policy?", elem_classes=["preset-btn"])
|
| 157 |
preset_cert = gr.Button("How do I unlock my completion certificate?", elem_classes=["preset-btn"])
|
|
@@ -163,19 +163,14 @@ with gr.Blocks(elem_classes=["dashboard-container"]) as demo:
|
|
| 163 |
scale=9
|
| 164 |
)
|
| 165 |
|
| 166 |
-
# Sidebar Status Panel
|
| 167 |
with gr.Column(scale=1, elem_classes=["sidebar-panel"]):
|
| 168 |
gr.Markdown("## Lane AI")
|
| 169 |
gr.Markdown("### *Your Agentic Learning Assistant*")
|
| 170 |
gr.Markdown("<br>🎓<br><br>🛡️ **Secure Session Activated**<br>Operational Node: Simplilearn-Chroma-01<br>Processing Hardware: Base CPU Node")
|
| 171 |
|
| 172 |
-
# Mapping event listeners
|
| 173 |
msg_input.submit(process_chat, [msg_input, chatbot], [msg_input, chatbot])
|
| 174 |
-
|
| 175 |
-
# Mapping quick-action click handlers
|
| 176 |
preset_refund.click(fn=click_preset_button, inputs=[preset_refund, chatbot], outputs=[chatbot])
|
| 177 |
preset_cert.click(fn=click_preset_button, inputs=[preset_cert, chatbot], outputs=[chatbot])
|
| 178 |
|
| 179 |
-
# 8. Launching the interface with Gradio 6.0 parameters
|
| 180 |
if __name__ == "__main__":
|
| 181 |
demo.launch(css=custom_css, theme=gr.themes.Default())
|
|
|
|
| 3 |
import warnings
|
| 4 |
import gradio as gr
|
| 5 |
|
| 6 |
+
# Suppress deprecation warnings to keep Hugging Face logs clean
|
| 7 |
warnings.filterwarnings("ignore", category=UserWarning, module="langchain_community")
|
| 8 |
|
| 9 |
from langchain_community.vectorstores import Chroma
|
| 10 |
from langchain_huggingface import HuggingFaceEmbeddings, HuggingFaceEndpoint
|
| 11 |
+
from langchain_core.prompts import PromptTemplate
|
|
|
|
| 12 |
from langchain_core.output_parsers import StrOutputParser
|
| 13 |
|
| 14 |
+
# 1. Fetching the Hugging Face Space security token
|
| 15 |
hf_token = os.environ.get("HF_TOKEN") or os.environ.get("HUGGINGFACEHUB_API_TOKEN")
|
| 16 |
|
| 17 |
# 2. Setup Vector Store & Embeddings Pipeline (Using ChromaDB)
|
|
|
|
| 27 |
"Data Science Bootcamp Prerequisites: This flagship program spans 6 months. It requires basic exposure to high-school level mathematics and rudimentary programming logic (Python familiarity is highly recommended but not mandatory)."
|
| 28 |
]
|
| 29 |
|
| 30 |
+
# Create an in-memory Chroma instance
|
| 31 |
vectorstore = Chroma.from_texts(texts=simplilearn_faq_data, embedding=embeddings)
|
| 32 |
retriever = vectorstore.as_retriever(search_type="similarity", search_kwargs={"k": 2})
|
| 33 |
|
| 34 |
# 3. Setup Low Parameter Open-Source LLM Generator via Serverless API
|
| 35 |
print("Configuring LLM Interface...")
|
| 36 |
chatModel = HuggingFaceEndpoint(
|
| 37 |
+
repo_id="Qwen/Qwen2.5-1.5B-Instruct",
|
| 38 |
task="text-generation",
|
| 39 |
+
max_new_tokens=500,
|
| 40 |
+
temperature=0.3,
|
| 41 |
do_sample=False,
|
| 42 |
huggingfacehub_api_token=hf_token
|
| 43 |
)
|
| 44 |
|
| 45 |
+
# 4. Constructing the Chain using standard PromptTemplate (Fixes Data Type Error for Qwen)
|
| 46 |
+
# We use Qwen's native ChatML tags so the model understands System/User/Assistant roles
|
| 47 |
+
template = """<|im_start|>system
|
| 48 |
+
You are the Simplilearn MOOC Support Agent, an advanced, polite, and professional AI learning assistant named Lane.
|
| 49 |
+
Answer the student's inquiry accurately using ONLY the retrieved context below.
|
| 50 |
+
If the answer cannot be found in the context, politely inform them that you only handle Simplilearn academic protocols and advise them to contact support@simplilearn.com.
|
| 51 |
+
|
| 52 |
+
Context:
|
| 53 |
+
{context}<|im_end|>
|
| 54 |
+
<|im_start|>user
|
| 55 |
+
{input}<|im_end|>
|
| 56 |
+
<|im_start|>assistant
|
| 57 |
+
"""
|
| 58 |
|
| 59 |
+
# Switched from ChatPromptTemplate to standard PromptTemplate
|
| 60 |
+
prompt = PromptTemplate.from_template(template)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
+
# Helper function to combine document chunks
|
| 63 |
def format_docs(docs):
|
| 64 |
return "\n\n".join(doc.page_content for doc in docs)
|
| 65 |
|
| 66 |
+
# The modern LCEL pipeline
|
| 67 |
rag_chain = (
|
| 68 |
{
|
| 69 |
"context": lambda x: format_docs(retriever.invoke(x["input"])),
|
|
|
|
| 74 |
| StrOutputParser()
|
| 75 |
)
|
| 76 |
|
| 77 |
+
# 5. UI Event Handlers
|
| 78 |
def process_chat(message, history):
|
| 79 |
if not message.strip():
|
| 80 |
return "", history
|
|
|
|
| 83 |
history = []
|
| 84 |
|
| 85 |
try:
|
| 86 |
+
# Executes the RAG Chain
|
| 87 |
bot_response = rag_chain.invoke({"input": message})
|
| 88 |
+
|
| 89 |
+
# Clean up the response if Qwen accidentally prints the stop tokens
|
| 90 |
+
bot_response = bot_response.replace("<|im_end|>", "").strip()
|
| 91 |
+
|
| 92 |
except Exception as e:
|
| 93 |
+
# NOW WE SHOW THE ACTUAL ERROR ON SCREEN!
|
| 94 |
bot_response = (
|
| 95 |
+
f"⚠️ **Server/API Error Encountered:**\n\n"
|
| 96 |
+
f"`{str(e)}`\n\n"
|
| 97 |
+
f"**Fix required:** If it says '401 Unauthorized', you must go to your Space **Settings -> Variables and secrets** "
|
| 98 |
+
f"and add a New Secret named `HF_TOKEN` containing your Hugging Face Access Token."
|
| 99 |
)
|
| 100 |
|
| 101 |
+
# Appending messages via Gradio 6.x specification
|
| 102 |
history.append({"role": "user", "content": message})
|
| 103 |
history.append({"role": "assistant", "content": bot_response})
|
| 104 |
return "", history
|
| 105 |
|
|
|
|
| 106 |
def click_preset_button(button_text, history):
|
| 107 |
_, updated_history = process_chat(button_text, history)
|
| 108 |
return updated_history
|
| 109 |
|
| 110 |
+
# 6. Custom CSS UI Styling
|
| 111 |
custom_css = """
|
| 112 |
.dashboard-container { background: linear-gradient(135deg, #e1f5fe 0%, #e8f5e9 100%); padding: 20px; border-radius: 12px; min-height: 100vh; }
|
| 113 |
.about-section { background-color: #002f6c; color: white; padding: 25px; border-radius: 8px; }
|
|
|
|
| 117 |
.preset-btn { background-color: #e0f7fa !important; border: 1px solid #b2ebf2 !important; color: #006064 !important; font-weight: 600; }
|
| 118 |
"""
|
| 119 |
|
|
|
|
| 120 |
toggle_js = """
|
| 121 |
function() {
|
| 122 |
var body = document.querySelector('body');
|
|
|
|
| 128 |
}
|
| 129 |
"""
|
| 130 |
|
| 131 |
+
# 7. Building the Visual Workspace Layout
|
| 132 |
with gr.Blocks(elem_classes=["dashboard-container"]) as demo:
|
| 133 |
|
|
|
|
| 134 |
with gr.Row():
|
| 135 |
with gr.Column(scale=2, elem_classes=["about-section"]):
|
| 136 |
gr.Markdown("<div class='about-title'>About Us</div>")
|
|
|
|
| 148 |
|
| 149 |
gr.Markdown("<br>")
|
| 150 |
|
|
|
|
| 151 |
with gr.Row():
|
|
|
|
| 152 |
with gr.Column(scale=3):
|
| 153 |
chatbot = gr.Chatbot(label="Simplilearn FAQ Support Stream")
|
| 154 |
|
|
|
|
| 155 |
with gr.Row():
|
| 156 |
preset_refund = gr.Button("What is the course refund policy?", elem_classes=["preset-btn"])
|
| 157 |
preset_cert = gr.Button("How do I unlock my completion certificate?", elem_classes=["preset-btn"])
|
|
|
|
| 163 |
scale=9
|
| 164 |
)
|
| 165 |
|
|
|
|
| 166 |
with gr.Column(scale=1, elem_classes=["sidebar-panel"]):
|
| 167 |
gr.Markdown("## Lane AI")
|
| 168 |
gr.Markdown("### *Your Agentic Learning Assistant*")
|
| 169 |
gr.Markdown("<br>🎓<br><br>🛡️ **Secure Session Activated**<br>Operational Node: Simplilearn-Chroma-01<br>Processing Hardware: Base CPU Node")
|
| 170 |
|
|
|
|
| 171 |
msg_input.submit(process_chat, [msg_input, chatbot], [msg_input, chatbot])
|
|
|
|
|
|
|
| 172 |
preset_refund.click(fn=click_preset_button, inputs=[preset_refund, chatbot], outputs=[chatbot])
|
| 173 |
preset_cert.click(fn=click_preset_button, inputs=[preset_cert, chatbot], outputs=[chatbot])
|
| 174 |
|
|
|
|
| 175 |
if __name__ == "__main__":
|
| 176 |
demo.launch(css=custom_css, theme=gr.themes.Default())
|