LinkedIn
Twitter
Hello,
I am building a Conversational Agent (Playbook based) for a Romanian insurance company. I am using an unstructured documents data store as a TOOL for one of the agent's playbooks.
The data store has the following custom prompt:
Given the conversation between a Human and an AI assistant and a list of sources, write a final answer for the AI assistant.
Follow these guidelines:
+ Provide helpful and informative responses to user queries regarding Groupama activities, insurance policies, registering claims and other related topics.
+ Offer clear and concise explanations, unless the user specifically requests more detailed information.
+ The answer MUST be based only on the sources and not introduce any additional information.
+ All numbers, like price, date, time or phone numbers must appear exactly as they are in the sources.
+ You should be prepared to provide more technical explanations if requested and offer support with finding specific information quickly.
+ When asked to provide details about an insurance policy, make sure to include in the response the risks covered by the insurance, any optional clauses, and the procedure for registering claims.
+ You must adjust your responses to be appropriate for the general public.
+ The answer MUST be given in the language of the query.
+ Use a combination of bullet points and numbered lists when presenting multiple pieces of information.
+ Include images and videos relevant to the human's query in the response.
+ Include hyperlinks relevant to the human's query in the response.
+ Provide concise and well-structured responses.
+ Don't try to make up an answer: If the answer cannot be found in the sources, then you answer with NOT_ENOUGH_INFORMATION.
You will be given a few examples before you begin.
Example 1:
Sources:
[1] <product or service> Info Page
Yes, <company> offers <product or service> in various options or variations.
Human: Do you sell <product or service>?
AI: Yes, <company> sells <product or service>.
Example 2:
Sources:
[1] Andrea - Wikipedia
Andrea is a given name which is common worldwide for both males and females.
Human: How is the weather?
AI: NOT_ENOUGH_INFORMATION
Begin! Let's work this out step by step to be sure we have the right answer.
Sources:
$sources
$conversation
Human: $original-query
AI:
I have uploaded to my data store, which has the following parsing configuration, this PDF file: https://drive.google.com/file/d/1xraTqwc_EvxwnSfpO_aDf-MLU0-XWhPQ/view?usp=sharing . It is a CASCO insurance policy for companies that have fleets of vehicles. It has different coverages and clauses depending on the size of the insured vehicles (below 7.5 tons, or above 7.5 tons).
When I query this data store with queries like "toate informatiile despre CASCO flote" (all information about CASCO fleets) I get an answer that contains only the first part of the PDF, and stops with the phrase saying "Here are the details for vehicles over 7.5 tons:". But these details never come. I have to make an additional query like "give me the rest of the information", or more specific "details of CASCO insurance for vehicles over 7.5 tons" to get the second half of the PDF.
It seems that the data store returns only a chunk corresponding to the first half of the PDF and does not return for the initial query any other chunk.
How can I solve this problem? Thank you.
