Technical questions

Technical questions about the expert.ai NL API

  • 13 Topics
  • 21 Replies

13 Topics

phlootr
phlootrEmployee
asked in Technical questions

retrieve segments with nlapi/edge

Hi,would anyone know how to retrieve segmentation results from a document analysis that have been created by a studio rules set?I can see the segments in studio analysis results in the results file <testfile>.ctx.json: In the documentation of nlapi/edge (https://docs.expert.ai/nlapi/latest/), though, I can’t find any explanation on how to retrieve segment boundaries.Thanks for any hint! 

0
phlootr
10 months ago
Venkat
VenkatKnown Participant
asked in Technical questions

How to use RegEX while writing the rules for extracting a sender name

Hi I would like to know how to use a RegEx pattern while writing rules in the expert.ai studio. Here is an example of the sender name that I would like to retreive from an emailFrom: Venkat from Raedan AI <venkat@raedanai.com>I would like to retrieve Venkat from Raedan AI and I think I can only retrieve this by using RegEx Pattern in my rules.I am new to Regex and would like to know how to write a rule to extract Venkat from Raedan AI in between From: and <Any help would be appreciated.Cheers,Venkat

1
Nico
1 year ago
cogitotech
cogitotechNew Participant
asked in Technical questions

How Can Outsourcing Video Transcription Services Benefit Your Company?

Outsourcing is one of the most important methods for organizations to become more efficient and successful, both financially and in terms of human resources. Beyond the traditional outsourcing functions, today’s businesses are looking at the sheer amount of recorded audio and video content to see how they can outsource and turn it into something more valuable.Outsourcing transcriptions is a natural next step for organizations that capture audio and video from meetings, interviews, podcasts, webinars, and other relevant content. When you transcribe a video to text, it becomes instantaneously searchable, legible, and ready to publish or share in any format.Here are a few interesting reasons to consider outsourcing transcribing services if you haven’t already:1. Refocus on your companyIt’s never a bad idea to focus on your major company operations, goals, and strategies. Every firm, in some form, has limited resources, and every department manager has limited time and attention daily. Out

0
cogitotech
1 year ago
N
nub4lifeNew Participant
asked in Technical questions

is it down?

I am getting a 503 service unavailable when I try to use the NL API, as well as when I try to access developer.expert.ai Is anyone else experiencing this issue?

4
monoceros
1 year ago
Venkat
VenkatKnown Participant
asked in Technical questions

Email Management package rule working for one test email and not for other

Hi All,I was trying to customize the open source Email management package to my outlook email needs. The problem I am getting is the extraction rules are working perfectly fine one test email in the expert.ai studio. But the same rules are not extracting information for other test emails. Sample Example scenario:TestEmail1.txt with just from addressFrom: Venkat Praveen Tatini <venkat@xyz.com>I was able to extract the name [Venkat Praveen Tatini] from the TestEmail1.txt  TestEmail2.txt with just from addressFrom: Sherlock Holmes <sherlock@xyz.com>I was unable to extract the name [Sherlock Holmes] from the TestEmail2.txtThis is weird because the rule is pretty simple which is extract people name. I looked at the Original package and compared with my custom package. Haven’t missed anything. but unable to figure out why the extraction rule that works for one TestEmail1.txt is not working on TestEmail2.txt.It would be extremely helpful for me if anyone knows what the issue might

3
lmusetti
1 year ago
Venkat
VenkatKnown Participant
asked in Technical questions

Match Supplier Invoice product data with Customer Purchase product data and customer Purchase receipt

Hi Bmunz,As discussed previously. I would like to learn how Expert.ai studio rules can that we create helps to match both supplier and purchase invoices along with Purchase receipts in a 3Combination way.First step I would like to learn is Does Expert.ai reads the PDF document from OCR as it is a demo requirement.If it does how are you guys do it at Expert.ai and if its not how you resolve these kind of issuesSecond Step would be building the rules in StudioHere are the attached supplier, Purchase order and purchase receipt invoice in a PDF and PNG format.Here Sanitarium Dairy company is SupplierColes is purchasing the order as you can see it with the product SKU’sAlso there is a Coles purchase receipt with 2 pages and I want to know if we can match the three by building semantics around the product.It would be appreciated if you can help me as we are going to present a demo in 2 weeks.Cheers,Venkat.

0
Venkat
1 year ago
Venkat
VenkatKnown Participant
asked in Technical questions

AI Powered chatbot using Expert.ai

Hi All,One of my friends is trying to build a AI powered Financial Assistant chatbot.The intent is for users is to interact with the chat bot via both Voice Commands and Text. User can ask chatbot to calculate their potential monthly car loan payments, mortgage payments, credit card payments, investment returns etc. User can also ask chatbot about current mortgage rates in the market, car loan rates, insurance rates etc.AI would need to pick data from user’s speech and use it in the calculations. User can also convey the questions and data via texts to AI. AI would then have to perform calculations and talk back to the user to convey the results and also text the results to the user.If a user asks a question about mortgage payments or car payments, then the AI may have to search the web to provide the best or lowest interest rate to the user and perform the calculations based on that interest rate.The AI would also look at the user’s spending history and pattern and would suggest how m

1
bmunz
1 year ago
Venkat
VenkatKnown Participant
asked in Technical questions

Expert.ai Email Management Package rules

Hi All,I am currently running the Email Management Package from within the studio. It was a great platform to create as many rules as I can in order to get most of the information from the Email. However if there are 3-4 company names were mentioned in the Email. I was only able to extract two companies.I understood the semantic analysis, Knowledge graph, categorization, extraction clearly.I also understood what is a scope sentence, ancestor and type of entity while writing the rules.Sample example of my problem: -In a sample Email If I type Coles(Which is a supermarket company in Australia) its not detecting this Coles as a company.But If i type Coles supermarket then it’s extracting this as a company.Perhaps there is a lack of semantic understanding from my side. I was hoping to get some help from the community on better rules designing/understanding. Any help from the community is appreciated. Cheers,Venkat  

3
lmusetti
1 year ago
A
adiNew Participant
asked in Technical questions

Are there any api endpoints for text summarization?

Same as question

1
monoceros
1 year ago
T
TradelastNew Participant
asked in Technical questions

Return value for emotion-traits and behavioral-traits

Can analysis for behavioral-traits and emotion-traits return an array of possibly more than one behavior or more than one emotion (like topics can return more than one topic), or will there only be one behavior trait and one emotion trait returned?

1
bmunz
1 year ago
A
adriman2New Participant
asked in Technical questions

Expert AI NL API scores scale

Hey everyone!  Does anyone know how Expert AI NL API assigns a score to each of the Key Elements and topics? Are the results ranked in a scale from 0 to 100 or could they also score more (or less) than that? Thank you in advance 

1
lgorrieri
1 year ago
A
ambarishgNew Participant
asked in Technical questions

403 Error

I am getting a 403 error . I suspect that I have exceeded the Dev Requests quota. When will this be reset ? Is it next month. I am participating in the Sentiment Hackathon. Regards,Ambarish 

5
monoceros
1 year ago
luisaherrmann
luisaherrmannEmployee
asked in Technical questions

Response status code: 500 - Python SDK

This is happening with expertai-nlapi-2.1.3I have an export from a product (Roam Research) that is return results in a psedu-markdown template. I've extracted it out and then run the following code to clean it up a little bit:eaiString = eaiString + s.get('string').replace('\n', ' ').replace('\r', ' ').replace('{',' ').replace('}',' ') + "\n"I then called the SDK with the following codedocument = client.specific_resource_analysis( body={"document": {"text":text}}, params={'language':'en', 'resource': 'relevants'})The text is about 6500 lines and 658k characters.I had submitted a much smaller excerpt earlier with out any problems so I don't think its an authentication issue.

1
luisaherrmann
1 year ago

Badge winners

Show all badges
Terms & ConditionsCookie settings