initial

Dockerfile

@@ -0,0 +1,27 @@
+FROM python:3.10
+
+WORKDIR /app
+
+COPY ./requirements.txt /app/requirements.txt
+
+RUN if [ -z "$GITHUB_TOKEN" ]; then echo "GITHUB_TOKEN is not set"; exit 1; fi && \
+    sed -i "s/{GITHUB_TOKEN}/$GITHUB_TOKEN/g" /app/requirements.txt
+RUN pip3 install --no-cache-dir -r /app/requirements.txt
+
+# User
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME /home/user
+ENV PATH $HOME/.local/bin:$PATH
+
+WORKDIR $HOME
+RUN mkdir app
+WORKDIR $HOME/app
+COPY . $HOME/app
+
+EXPOSE 8501
+CMD streamlit run app.py \
+    --server.headless true \
+    --server.enableCORS false \
+    --server.enableXsrfProtection false \
+    --server.fileWatcherType none

README.md

@@ -1,13 +1,14 @@
 ---
-title: Finance Chat With Vectara Agent
-emoji: 👁
-colorFrom: yellow
-colorTo: purple
+title: Finance Chatbot
+emoji: 🐨
+colorFrom: indigo
+colorTo: indigo
 sdk: streamlit
-sdk_version: 1.35.0
+sdk_version: 1.32.2
 app_file: app.py
 pinned: false
 license: apache-2.0
+short_description: An AI assistant with company financial reports
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,178 @@
+
+from omegaconf import OmegaConf
+import streamlit as st
+import os
+from PIL import Image
+import re
+import sys
+
+from pydantic import Field, BaseModel
+from vectara_agent.agent import Agent, AgentType, AgentStatusType
+from vectara_agent.tools import ToolsFactory
+
+
+tickers = {
+    "AAPL": "Apple Computer", 
+    "GOOG": "Google", 
+    "AMZN": "Amazon",
+    "SNOW": "Snowflake",
+    "TEAM": "Atlassian",
+    "TSLA": "Tesla",
+    "NVDA": "Nvidia",
+    "MSFT": "Microsoft",
+    "AMD": "Advanced Micro Devices",
+}
+years = [2020, 2021, 2022, 2023, 2024]
+initial_prompt = "How can I help you today?"
+
+def create_tools(cfg):    
+
+    def get_company_info() -> list[str]:
+        """
+        Returns a dictionary of companies you can query about their financial reports.
+        The output is a dictionary of valid ticker symbols mapped to company names.
+        You can use this to identify the companies you can query about, and their ticker information.
+        """
+        return tickers
+
+    def get_valid_years() -> list[str]:
+        """
+        Returns a list of the years for which financial reports are available.
+        """
+        return years
+    
+    class QueryFinancialReportsArgs(BaseModel):
+        query: str = Field(..., description="The user query. Must be a question about the company's financials, and should not include the company name, ticker or year.")
+        year: int = Field(..., description=f"The year. an integer between {min(years)} and {max(years)}.")
+        ticker: str = Field(..., description=f"The company ticker. Must be a valid ticket symbol from the list {tickers.keys()}.")
+
+    tools_factory = ToolsFactory(vectara_api_key=cfg.api_key, 
+                                 vectara_customer_id=cfg.customer_id, 
+                                 vectara_corpus_id=cfg.corpus_id)
+    query_financial_reports = tools_factory.create_rag_tool(
+        tool_name = "query_financial_reports",
+        tool_description = """
+        Given a company name and year, 
+        returns a response (str) to a user query about the company's financials for that year.
+        When using this tool, make sure to provide the a valid company ticker and a year. 
+        Use this tool to get financial information one metric at a time.
+        """,
+        tool_args_schema = QueryFinancialReportsArgs,
+        tool_filter_template = "doc.year = {year} and doc.ticker = '{ticker}'",
+        reranker = "slingshot", rerank_k = 100, 
+        n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.0,
+        summary_num_results = 15,
+        vectara_summarizer = 'vectara-summary-ext-24-05-med-omni',
+    )
+
+    return (tools_factory.get_tools(
+                [
+                    get_company_info, 
+                    get_valid_years,
+                ]
+            ) +
+            tools_factory.standard_tools() + 
+            tools_factory.financial_tools() + 
+            [query_financial_reports]
+    )
+
+def launch_bot(agent_type: AgentType):
+    def reset():
+        cfg = st.session_state.cfg
+        st.session_state.messages = [{"role": "assistant", "content": initial_prompt, "avatar": "🦖"}]
+        st.session_state.thinking_message = "Agent at work..."
+
+        # Create the agent
+        print("Creating agent...")
+
+        def update_func(status_type: AgentStatusType, msg: str):
+            output = f"{status_type.value} - {msg}"
+            st.session_state.thinking_placeholder.text(output)
+
+        financial_bot_instructions = """
+        - You are a helpful financial assistant in conversation with a user. Use your financial expertise when crafting a query to the tool, to ensure you get the most accurate information.
+        - You can answer questions, provide insights, or summarize any information from financial reports.
+        - A user may refer to a company's ticker instead of its full name - consider those the same when a user is asking about a company.
+        - When calculating a financial metric, make sure you have all the information from tools to complete the calculation.
+        - In many cases you may need to query tools on each sub-metric separately before computing the final metric.
+        - When using a tool to obtain financial data, consider the fact that information for a certain year may be reported in the the following year's report.
+        - Report financial data in a consistent manner. For example if you report revenue in thousands, always report revenue in thousands.
+        """
+
+        st.session_state.agent = Agent(
+            agent_type = agent_type,
+            tools = create_tools(cfg),
+            topic = "10-K financial reports",
+            custom_instructions = financial_bot_instructions,
+            update_func = update_func
+        )
+
+    if 'cfg' not in st.session_state:
+        cfg = OmegaConf.create({
+            'customer_id': str(os.environ['VECTARA_CUSTOMER_ID']),
+            'corpus_id': str(os.environ['VECTARA_CORPUS_ID']),
+            'api_key': str(os.environ['VECTARA_API_KEY']),
+        })
+        st.session_state.cfg = cfg
+        reset()
+
+    cfg = st.session_state.cfg
+    st.set_page_config(page_title="Financial Assistant", layout="wide")
+
+    # left side content
+    with st.sidebar:
+        image = Image.open('Vectara-logo.png')
+        st.image(image, width=250)
+        st.markdown("## Welcome to the financial assistant demo.\n\n\n")
+        companies = ", ".join(tickers.values())
+        st.markdown(
+            f"This assistant can help you with any questions about the financials of the following companies:\n\n **{companies}**.\n\n"
+            "You can ask questions, analyze data, provide insights, or summarize any information from financial reports."
+        )
+
+        st.markdown("\n\n")
+        if st.button('Start Over'):
+            reset()
+
+        st.markdown("---")
+        st.markdown(
+            "## How this works?\n"
+            "This app was built with [Vectara](https://vectara.com).\n\n"
+            "It demonstrates the use of Agentic Chat functionality with Vectara"
+        )
+        st.markdown("---")
+
+
+    if "messages" not in st.session_state.keys():
+        reset()
+
+    # Display chat messages
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"], avatar=message["avatar"]):
+            st.write(message["content"])
+
+    # User-provided prompt
+    if prompt := st.chat_input():
+        st.session_state.messages.append({"role": "user", "content": prompt, "avatar": '🧑‍💻'})
+        with st.chat_message("user", avatar='🧑‍💻'):
+            print(f"Starting new question: {prompt}\n")
+            st.write(prompt)
+    
+    # Generate a new response if last message is not from assistant
+    if st.session_state.messages[-1]["role"] != "assistant":
+        with st.chat_message("assistant", avatar='🤖'):
+            with st.spinner(st.session_state.thinking_message):
+                st.session_state.thinking_placeholder = st.empty()
+                res = st.session_state.agent.chat(prompt)
+                cleaned = re.sub(r'\[\d+\]', '', res.response).replace('$', '\\$')
+                st.write(cleaned)
+            message = {"role": "assistant", "content": cleaned, "avatar": '🤖'}
+            st.session_state.messages.append(message)
+            st.session_state.thinking_placeholder.empty()
+
+    sys.stdout.flush()
+
+if __name__ == "__main__":
+    print("Starting up...")
+    launch_bot(agent_type = AgentType.REACT)
+    

requirements.txt

@@ -0,0 +1,10 @@
+requests_to_curl==1.1.0
+toml==0.10.2
+omegaconf==2.3.0
+syrupy==4.0.8
+streamlit==1.32.2
+llama-index==0.10.42
+llama-index-indices-managed-vectara==0.1.4
+llama-index-agent-openai==0.1.5
+pydantic==1.10.15
+git+https://{GITHUB_TOKEN}@github.com/vectara/vectara-agent.git