Chat Quickstart Guide

Welcome to the Quickstart guide for running a Chat Service, powered by Bigdata.com.

Why Build Your Chatbot with Bigdata.com?

Bigdata.com is designed specifically for business and finance professionals, delivering real-time, AI-driven insights with precision and speed.

✅ Unmatched Data Access – Instantly analyze vast, high-quality datasets.

✅ Finance & Business Expertise – Designed for professionals, not generic use.

✅ Seamless Integration – Easily power your chatbot with cutting-edge AI.


In just 5 minutes, you’ll learn how to:

✅ Install bigdata-client package

✅ Authenticate to Bigdata.com

✅ Chat with the Bigdata.com research assistant

✅ Delete the chat instance


Ready to get started? Let’s dive in!

We recommend to try this Quickstart guide directly on Google Colab.

Important

  • The Chat API is experimental, and future updates may not be backward-compatible.

  • Each question queries Bigdata.com and consumes API units — Monitor usage accordingly.

Install bigdata-client package

First of all, let’s install bigdata-client package in a python virtual environment.

Open the terminal and create a virtual environment with the following command:

$ python3 -m venv bigdata_venv

Activate the virtual environment, every time you want to use it:

$ source ./bigdata_venv/bin/activate

And install the bigdata-client within the environment bigdata_venv.

(bigdata_venv) $ pip install bigdata-client

Authenticate to bigdata.com

Enter the python interpreter with the following command

(bigdata_venv) $ python3

Now you can import the Bigdata object from the bigdata_client package,

>>> from bigdata_client import Bigdata

And initiate it with your bigdata.com personal credentials.

>>> bigdata = Bigdata("YOUR_USERNAME", "YOUR_PASSWORD")

Chat with bigdata.com

Your proprietary App or Server can leverage this programmatic Chat experience similar to the chat of bigdata.com App.

Create a new Chat

Let’s create a Chat instance:

# Create a new chat
chat = bigdata.chat.new("Pfizer company analysis")

Note

Chat support formatter. This is the mechanism to customize inline attribution in chat answers. By default DefaultFormatter is used. For more information see Inline Attribution Formatter

First question

We can ask a question and print both, the question and the answer:

# First question
response = chat.ask("Evaluate the experience and reputation of the management team of Pfizer")
print(f"\nQuestion:\n - {response.question}")
print(f"\nAnswer:\n{response.answer}")

Question:
- Evaluate the experience and reputation of the management team of Pfizer

Answer:
## Pfizer's Executive Leadership Team

### Albert Bourla, Chairman and Chief Executive Officer
- Bourla has been Pfizer's CEO since 2019 and was recently appointed as the new chair of the Pharmaceutical Research and Manufacturers of America (PhRMA) board.
- Under Bourla's leadership, Pfizer has seen strong financial performance, with the company reporting robust Q4 2024 results and raising its 2024 guidance.

### Chris Boshoff, Chief Scientific Officer and President, Research & Development
- Boshoff was promoted to this role in November 2024, succeeding Mikael Dolsten.
- Boshoff has been praised for his vision and leadership, and is tasked with taking Pfizer's pipeline and productivity to the next level.
- He will oversee all R&D functions across Pfizer's therapeutic areas and report directly to CEO Albert Bourla.

### Patrizia Cavazzoni, Chief Medical Officer
- Cavazzoni is a highly experienced pharmaceutical executive, having previously served as the director of the Center for Drug Evaluation and Research at the FDA.  ,
- Her appointment to Pfizer's CMO role in February 2025 was seen as a strategic move to strengthen the company's regulatory and drug safety operations.
- However, Cavazzoni's transition from the FDA to Pfizer has raised some concerns about the "revolving door" between regulators and the pharmaceutical industry.  ,

Overall, Pfizer's executive leadership team is composed of seasoned industry veterans with deep expertise in drug development, regulatory affairs, and commercial operations. The company's strong financial performance and pipeline progress under Bourla's leadership suggest that Pfizer's management team is well-equipped to drive the company's continued success.

Ask any follow up questions

You can continue asking questions. It will remember your previous questions and answers within this chat instance.

# Follow up question
response = chat.ask("Has it hired any senior AI expert?")
print(f"\nQuestion:\n - {response.question}")
print(f"\nAnswer:\n{response.answer}")

Question:
- Has it hired any senior AI expert?

Answer:
## Pfizer Hires Senior AI Expert

Yes, Pfizer has hired a senior AI expert to bolster its digital leadership team. In August 2024, the company appointed Berta Rodriguez-Hervas as its Chief AI and Analytics Officer.

According to the information:

- Rodriguez-Hervas is joining Pfizer after previous roles at Stellantis, Nvidia, and Tesla, where she focused on algorithms, computer vision, and machine learning.
- Pfizer's EVP and Chief Digital and Technology Officer, Lidia Fonseca, expressed confidence that Rodriguez-Hervas' "leadership and fresh perspective will continue to take our enterprise AI strategies and capabilities to the next level."
- The appointment of a dedicated Chief AI Officer signals Pfizer's focus on leveraging AI and analytics to accelerate its drug development and patient care initiatives.

In summary, Pfizer has bolstered its digital leadership team by hiring Berta Rodriguez-Hervas, an experienced AI and analytics expert, as its Chief AI and Analytics Officer.

Chat with bigdata.com in Streaming mode

Chat support streaming mode

When streaming=True param provided to chat.ask method it return StreamingChatInteraction insead of ChatInteraction

StreamingChatInteraction implements iterator. Also it has same interface as ChatInteracion and contains exactly same properties.

Ask question with streaming

We can ask a question and print both, the question and the answer:

# In this case `response` is a `StreamingChatInteracton` which support iteraton
response = chat.ask("Evaluate the experience and reputation of the management team of Pfizer", streaming=True)

# Consume `chunks` iterating over `response`
print("Streaming results:")
for chunk in response:
    print(f"chunk: {chunk}")

# At this point it is possible to access `StreamingChatInteracton` properties
print(f"\nQuestion:\n - {response.question}")

Streaming results:
chunk: ## Pfizer's Executive
chunk:  Leadership Team
chunk: ### Albert Bourla
chunk: , Chairman and Chief Executive Officer
...
chunk: company's continued success.

Question:
- Evaluate the experience and reputation of the management team of Pfizer

Note

Unless iterator fully consumed, StreamingChatInteraction properties are not filled with data

Delete the chat instance

We can delete this chat instance if we no longer need to ask follow-up questions.

# Delete chat
bigdata.chat.delete(chat.id)

Summary

Congratulations! 🎉 You have successfully integrated with Bigdata.com chat service programmatically, and we can’t wait to see what you build. We’re always around to help.

Next steps

We recommend exploring the following pages: