Introducing Contextual Answers, bringing generative AI to the enterprise with a ready-to-use question answering engine that taps into organizational knowledge.
Generative AI is engaging billions of people around the world with tools that inspire creativity - writing text, composing music, and creating digital art.
Today we’d like to introduce the evolution of GenAI from creativity to business productivity. A major step in this direction is Contextual Answers, allowing businesses to tap into their organization data with the tremendous power of generative AI.
Starting today, Contextual Answers lets businesses upload entire libraries of documents – knowledge bases, help center libraries, business reports, policies, guidelines, manuals and playbooks – and then provides an answering engine entirely grounded in the corpus of information.
While generative AI shows incredible promise, according to a recent KMPG survey, most businesses struggle to adopt it, citing cost, complexity and lack of the models’ specialization in their organizational data, leading to responses that are incorrect, ‘hallucinated’ or inappropriate for the context. This can cause huge liabilities and in many instances, make generative AI completely unusable for use cases.
This is why we’ve developed Contextual Answers, an end-to-end API solution where answers are designed to be completely grounded in organizational knowledge and avoid hallucinations.
We’re seeing tremendous demand from businesses that wish to leverage Contextual Answers to supercharge organizational productivity and provide superior customer experiences.
Clarivate, a leading global information services provider, partnered with us to apply Contextual Answers across their suite of library solutions, providing students, faculty and researchers answers to questions grounded in curated and trusted scholarly content.
Here are a few other examples.
Customer Support for CRMs and Independent Software Vendors: answering end user support questions using internal organization documentation, reducing the load and cost and improving customer satisfaction
Financial Service Institutions: assisting in the analysis of business documents such as financial reports, call logs, and past presentations, allowing analysts to cover more resources
Education Service Providers: allowing students, teachers, and researchers to quickly find answers in large databases full of articles, books and research papers
Legal Services and Insurance: providing the ability to quickly look up relevant legal documents, including legislation, regulations and internal compliance guidelines
Sales and Marketing: supporting sales associates by pulling information from product documents, competitor analysis, marketing materials, and sales playbooks to answer customer queries or build pitches
Field Technicians: enabling field technicians to quickly reference manual specific questions without having to waste time searching through countless technical documents
Walkthrough: Build a knowledge management system using Contextual Answers
As an example, let’s leverage these capabilities to create an efficient knowledge management system (KMS) for an organization. According to a recent report from Coveo, the average employee spends 3.6 hours daily searching for relevant information, including internal company policies (for example, hybrid work guidelines).
Now with Contextual Answers, you can easily deploy a full question-answering system based solely on organizational data alone. By providing employees with rapid answers backed by attributed sources, businesses can dramatically increase productivity.
Ready to get started?
Step 1: Upload your files
You can upload your files to your Library, where we offer free storage. In this example, we will upload three documents with company policies (working from abroad, hybrid work guidelines, IT security).
This can be done with a simple call using our Python SDK (or an HTTP request):
You can upload a file as it is, store it in a directory (for those who like working with directories) or add labels. This can help you organize your filing system, while focusing your questions on a subset of documents.
Step 2: Ask a question
Your users can now ask a question and immediately get the answer with attribution to the relevant source. The system works as follows:
The question is used as a query for a retrieval mechanism, which searches over the entire knowledge base and retrieves the most relevant contexts.
With rapid changes occurring in work environments lately, a common question from employees is about working remotely:
response = ai21.Library.Answer.execute(question="How many days can I work from home?")
The response will be:
Two days a week
Note that the full response returned from the model also contains the sources used as context (see “sources” field).
However, if the answer to the question is not in any of the documents, the model will indicate that by returning an empty response. For instance, if we will ask the following question:
response = ai21.Library.Answer.execute(question="What's my meal allowance when working from home?")
The response will indicate that the answer is not found in any of the documents within your Library.
You can also do it via our Studio platform:
If you have a large collection of documents or have your own retrieval mechanism, you may want to ask a question on a subset of your knowledge base.
Learn more on how to refine answer retrieval here.
ABOUT THE AUTHOR
Senior Product Marketing Manager
Stay up to date with the latest research and updates from AI21 Labs.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
In August 2021 we released Jurassic-1, a 178B-parameter autoregressive language model. We’re thankful for the reception it got – over 10,000 developers signed up, and hundreds of commercial applications are in various stages of development. Mega models such as Jurassic-1, GPT-3 and others are indeed amazing, and open up exciting opportunities. But these models are also inherently limited. They can’t access your company database, don’t have access to current information (for example, latest COVID numbers or dollar-euro exchange rate), can’t reason (for example, their arithmetic capabilities don’t come close to that of an HP calculator from the 1970s), and are prohibitively expensive to update. A MRKL system such as Jurassic-X enjoys all the advantages of mega language models, with none of these disadvantages. Here’s how it works.
Compositive multi-expert problem: the list of “Green energy companies” is routed to Wiki API, “last month” dates are extracted from the calendar and “share prices” from the database. The “largest increase“ is computed by the calculator and finally, the answer is formatted by the language model.
There are of course many details and challenges in making all this work - training the discrete experts, smoothing the interface between them and the neural network, routing among the different modules, and more. To get a deeper sense for MRKL systems, how they fit in the technology landscape, and some of the technical challenges in implementing them, see our MRKL paper. For a deeper technical look at how to handle one of the implementation challenges, namely avoiding model explosion, see our paper on leveraging frozen mega LMs.
A further look at the advantages of Jurassic-X
Even without diving into technical details, it’s easy to get a sense for the advantages of Jurassic-X. Here are some of the capabilities it offers, and how these can be used for practical applications.
Reading and updating your database in free language
Language models are closed boxes which you can use, but not change. However, in many practical cases you would want to use the power of a language model to analyze information you possess - the supplies in your store, your company’s payroll, the grades in your school and more. Jurassic-X can connect to your databases so that you can ‘talk’ to your data to explore what you need- “Find the cheapest Shampoo that has a rosy smell”, “Which computing stock increased the most in the last week?” and more. Furthermore, our system also enables joining several databases, and has the ability to update your database using free language (see figure below).
Jurassic-X enables you to plug in YOUR company's database (inventories, salary sheets, etc.) and extract information using free language
AI-assisted text generation on current affairs
Language models can generate text, yet can not be used to create text on current affairs, because their vast knowledge (historic dates, world leaders and more) represents the world as it was when they were trained. This is clearly (and somewhat embarrassingly) demonstrated when three of the world’s leading language models (including our own Jurassic-1) still claim Donald Trump is the US president more than a year after Joe Biden was sworn into office. Jurassic-X solves this problem by simply plugging into resources such as Wikidata, providing it with continuous access to up-to-date knowledge. This opens up a new avenue for AI-assisted text generation on current affairs.
Who is the president of the United States?
Joe Biden is the 46th and current president
Jurassic-X can assist in text generation on up-to-date events by combining a powerful language model with access to Wikidata
Performing math operations
A 6 year old child learns math from rules, not only by memorizing examples. In contrast, language models are designed to learn from examples, and consequently are able to solve very basic math like 1-, 2-, and possibly 3- digit addition, but struggle with anything more complex. With increased training time, better data and larger models, the performance will improve, but will not reach the robustness of an HP calculator from the 1970s. Jurassic-X takes a different approach and calls upon a calculator whenever a math problem is identified by the router. The problem can be phrased in natural language and is converted by the language model to the format required by the calculator (numbers and math operations). The computation is performed and the answer is converted back into free language. Importantly (see example below) the process is made transparent to the user by revealing the computation performed, thus increasing the trust in the system. In contrast, language models provide answers which might seem reasonable, but are wrong, making them impractical to use.
The company had 655400 shares which they divided equally among 94 employees. How many did each employee get?
Each employee got 7000 stocks
(No answer provided)
6972.3 X= 655400/94
Jurassic-X can answer non-trivial math operations which are phrased in natural language, made possible by the combination of a language model and a calculator
Solving simple questions might require multiple steps, for example - “Do more people live in Tel Aviv or in Berlin?” requires answering: i. What is the population of Tel-Aviv? ii. What is the population of Berlin? iii. Which is larger? This is a highly non-trivial process for a language model, and language models fail to answer this question (see example). Moreover, the user can’t know the process leading to the answers, hence is unable to trust them. Jurassic-X can decompose such problems into the basic questions, route each to the relevant expert, and put together an answer in free language. Importantly, Jurassic-X not only provides the correct answer but also displays the steps taken to reach it, increasing the trust in the system.
Do more people live in Tel Aviv or in Berlin?
There are more people living in Tel Aviv than in Berlin.
Berlin and Tel Aviv are roughly the same size
(First hit is a comparison between Tel Aviv and Berlin)
More people live in Berlin than in Tel-Aviv
[‘Return population of Tel Aviv’; Return population of Berlin’; Return which is bigger between #1 and #2’] Step 1: Population of Tel Aviv. Result - 451523. Step 1: Population of Berlin. Result - 3664088. Step 3: Which is bigger, #1 or #2. Result - Berlin.
Jurassic-X breaks down compositional questions, answers the basic sub-questions, and puts together the answer. Importantly, this process is transparent to the user greatly increasing the trust in the system
Dynamic information (like weather and currency exchange rates)
Certain types of information change continuously - weather, currency exchange rates, share values and more. Such information will never be captured by language models, yet can easily be handled by Jurassic-X by integrating it with a reliable source of information. We performed a proof-of-concept on two such features - weather and currency exchange rates, and the design enables quick integration with more sources to solve your use-case. Weather - a loosely phrased question about the weather elicits an answer from all language models, where language models always return the same answer, regardless of when the question was asked (funny, right?), while Jurassic-X provides an answer based on the actual weather prediction.
I’m going to be in New-York in 3 days. Should I pack my umbrella?
Yes, you should pack your umbrella.
Yes, you should. The weather forecast is rain.
(Links to weather websites)
Yes, you should pack your umbrella, because in New York in 3 days there will be broken clouds and the temperature will be -2 degrees.
Currency exchange rates change much faster than weather predictions, yet the Jurassic-X concept - a language model connected to a reliable source of information - easily solves this problem as well.
How much Moroccan money will I get for 100 bucks?
100 moroccan dirhams is about 27$.
How much is 100 dollars in moroccan money?
100 dirhams = 10.75 dollars
100 USD = 934.003 MAD
Jurassic-X combines a language model with access to APIs with continuously changing information. This is demonstrated for weather forecasts and currency exchange rates, and can easily be extended to other information sources
Transparency and trust
Transparency is a critical element that is lacking in language models, preventing a much wider adoption of these models. This lack of transparency is demonstrated by the answers to the question - “Was Clinton ever elected as president of the United States?”. The answer, of course, depends on which Clinton you have in mind, which is only made clear by Jurassic-X that has a component for disambiguation. More examples of Jurassic-X’s transparency were demonstrated above - displaying the math operation performed to the user, and the answer to the simple sub-questions in the multi-step setting.
Was Clinton ever elected president of the United States?
No, Clinton was never elected as president of the United States.
Clinton was elected president in the 1992 presidential elections…
Bill Clinton was elected president.
Jurassic-X is designed to be more transparent by displaying which expert answered which part of the question, and by presenting the intermediate steps taken and not just the black-box response
That's it, you get the picture. The use cases above give you a sense for some things you could do with Jurassic-X, but now it's your turn. A MRKL system such as Jurassic-X is as flexible as your imagination. What do you want to accomplish? Contact us for early access
Your submission has been received!
Oops! Something went wrong while submitting the form.