Update app.py

app.py

@@ -1,162 +1,58 @@
-import faicons as fa
-import plotly.express as px
-
-# Load data and compute static values
-from shared import app_dir, tips
-from shinywidgets import render_plotly
-
-from shiny import reactive, render
-from shiny.express import input, ui
-
-bill_rng = (min(tips.total_bill), max(tips.total_bill))
-
-# Add page title and sidebar
-ui.page_opts(title="Restaurant tipping", fillable=True)
-
-with ui.sidebar(open="desktop"):
-    ui.input_slider(
-        "total_bill",
-        "Bill amount",
-        min=bill_rng[0],
-        max=bill_rng[1],
-        value=bill_rng,
-        pre="$",
-    )
-    ui.input_checkbox_group(
-        "time",
-        "Food service",
-        ["Lunch", "Dinner"],
-        selected=["Lunch", "Dinner"],
-        inline=True,
-    )
-    ui.input_action_button("reset", "Reset filter")
-
-# Add main content
-ICONS = {
-    "user": fa.icon_svg("user", "regular"),
-    "wallet": fa.icon_svg("wallet"),
-    "currency-dollar": fa.icon_svg("dollar-sign"),
-    "ellipsis": fa.icon_svg("ellipsis"),
-}
-
-with ui.layout_columns(fill=False):
-    with ui.value_box(showcase=ICONS["user"]):
-        "Total tippers"
-
-        @render.express
-        def total_tippers():
-            tips_data().shape[0]
-
-    with ui.value_box(showcase=ICONS["wallet"]):
-        "Average tip"
-
-        @render.express
-        def average_tip():
-            d = tips_data()
-            if d.shape[0] > 0:
-                perc = d.tip / d.total_bill
-                f"{perc.mean():.1%}"
-
-    with ui.value_box(showcase=ICONS["currency-dollar"]):
-        "Average bill"
-
-        @render.express
-        def average_bill():
-            d = tips_data()
-            if d.shape[0] > 0:
-                bill = d.total_bill.mean()
-                f"${bill:.2f}"
-
-
-with ui.layout_columns(col_widths=[6, 6, 12]):
-    with ui.card(full_screen=True):
-        ui.card_header("Tips data")
-
-        @render.data_frame
-        def table():
-            return render.DataGrid(tips_data())
-
-    with ui.card(full_screen=True):
-        with ui.card_header(class_="d-flex justify-content-between align-items-center"):
-            "Total bill vs tip"
-            with ui.popover(title="Add a color variable", placement="top"):
-                ICONS["ellipsis"]
-                ui.input_radio_buttons(
-                    "scatter_color",
-                    None,
-                    ["none", "sex", "smoker", "day", "time"],
-                    inline=True,
-                )
-
-        @render_plotly
-        def scatterplot():
-            color = input.scatter_color()
-            return px.scatter(
-                tips_data(),
-                x="total_bill",
-                y="tip",
-                color=None if color == "none" else color,
-                trendline="lowess",
-            )
-
-    with ui.card(full_screen=True):
-        with ui.card_header(class_="d-flex justify-content-between align-items-center"):
-            "Tip percentages"
-            with ui.popover(title="Add a color variable"):
-                ICONS["ellipsis"]
-                ui.input_radio_buttons(
-                    "tip_perc_y",
-                    "Split by:",
-                    ["sex", "smoker", "day", "time"],
-                    selected="day",
-                    inline=True,
-                )
-
-        @render_plotly
-        def tip_perc():
-            from ridgeplot import ridgeplot
-
-            dat = tips_data()
-            dat["percent"] = dat.tip / dat.total_bill
-            yvar = input.tip_perc_y()
-            uvals = dat[yvar].unique()
-
-            samples = [[dat.percent[dat[yvar] == val]] for val in uvals]
-
-            plt = ridgeplot(
-                samples=samples,
-                labels=uvals,
-                bandwidth=0.01,
-                colorscale="viridis",
-                colormode="row-index",
-            )
-
-            plt.update_layout(
-                legend=dict(
-                    orientation="h", yanchor="bottom", y=1.02, xanchor="center", x=0.5
-                )
-            )
-
-            return plt
-
-
-ui.include_css(app_dir / "styles.css")
-
-# --------------------------------------------------------
-# Reactive calculations and effects
-# --------------------------------------------------------
-
-
-@reactive.calc
-def tips_data():
-    bill = input.total_bill()
-    idx1 = tips.total_bill.between(bill[0], bill[1])
-    idx2 = tips.time.isin(input.time())
-    return tips[idx1 & idx2]
-
-
-@reactive.effect
-@reactive.event(input.reset)
-def _():
-    ui.update_slider("total_bill", value=bill_rng)
-    ui.update_checkbox_group("time", selected=["Lunch", "Dinner"])
+import os
+import gradio as gr
+import pinecone
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import Pinecone
+from langchain.chat_models import ChatOpenAI
+from langchain.chains import ConversationalRetrievalChain
+from langchain.memory import ConversationBufferMemory
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+# Load your keys from environment variables (set in HF Space secrets)
+OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY")
+PINECONE_API_KEY = os.environ.get("PINECONE_API_KEY")
+PINECONE_ENV = os.environ.get("PINECONE_ENV")  # e.g., 'us-east1-gcp'
+
+# Initialize Pinecone
+pinecone.init(api_key=PINECONE_API_KEY, environment=PINECONE_ENV)
+index_name = "workflow-helper-index"
+
+embedding = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)
+
+# Connect to Pinecone index or create if it doesn't exist
+if index_name not in pinecone.list_indexes():
+    pinecone.create_index(index_name, dimension=1536)
+
+vectorstore = Pinecone.from_existing_index(index_name, embedding)
+
+# Setup LLM and memory
+llm = ChatOpenAI(model_name="gpt-4o", temperature=0, openai_api_key=OPENAI_API_KEY)
+memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+
+# Create Conversational Retrieval Chain
+qa_chain = ConversationalRetrievalChain.from_llm(
+    llm=llm,
+    retriever=vectorstore.as_retriever(search_type="similarity", k=4),
+    memory=memory,
+    return_source_documents=False,
+)
+
+def chat(message, chat_history):
+    response = qa_chain.run(message)
+    chat_history.append((message, response))
+    return chat_history, chat_history
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 💬 Workflow Approvals Assistant")
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(placeholder="Ask about a PO or approval process...")
+    clear = gr.Button("Clear Chat")
+
+    state = gr.State([])
+
+    msg.submit(chat, [msg, state], [chatbot, state])
+    clear.click(lambda: ([], []), None, [chatbot, state])
+
+if __name__ == "__main__":
+    demo.launch()