Movavi Video Editor Crack + Activation Key [2025]

👉COPY & PASTE LINK👉
https://upcommunity.net/dl/

Movavi Video Editor is a beginner-friendly multimedia application that can help you create professional-level videos.

1. EMPOWERING SALES WITH
INTELLIGENT BI AGENTS:
DWH, LLM, AND RAG
INTEGRATION
ŠIMUN ŠUNJIĆ
LOVRO MATOŠEVIĆ

3. Challenges
User related Technically related

4. Can simple retry help?

5. BI LLM Advanced Database Chat System
LLM-enhanced
SQL generation
Retrieval-Augmented
Generation (RAG) for context
understanding
Multi-agent architecture for
autonomous management of
various processing aspects
and state retention
Graph databases for
global schema context
and understanding
User-friendly UI for
visualization and
reporting

6. Technical Deep Dive

7. Core

8. Integration

9. Data

10. Schema Linking
Essential for handling complex,
multi-table queries
Why?

11. Schema Linking
How?
Embed user query and schema for similarity search
​
Periodically update schema
Only pick portion of the schema
Few-shot with Golden SQL queries and relevance scoring

12. Schema Linking
Bridges the gap between natural
language and database structure
Conclusion?

13. Query Generation Process

14. Query Generation Process
Properly detect users' intent
via confidence scoring
recommendation
utterances: using natural
language parsers / LLM

15. Query Generation Process
System prompts: Guide LLM
through system prompts by
injecting few-shot examples,
relevant data from high cardinality
columns and the relevant portion
of DDL context

16. Query Generation Process
Conversation history:
Cache
 and database records

17. Query Generation Process
Chatty agents: make sure
agents don't fall into
recursion

18. Query Generation Process
Context manager: ensure
agents share common
context storage

19. Query Generation Process
Query Optimizer: built in
generation process with SQL
validation and fixing

20. High-cardinal columns
•Values with millions of unique
product IDs
•Helps with "vague terms into
specific database values"
conversions
•User query to sub-queries
decomposition

21. Query Generation Process
•The system maintains
conversation context and
understands business terminology,
allowing users to ask follow-up
questions naturally.
•For example, after seeing sales
data, users can simply ask without
needing to specify all the details
again:
oShow this as a chart
oCompare with previous year

22. Agents
•Generate skeleton SQL using
graphs and similarity search
•Improve the
 WHERE clause with
high-cardinal data
•Sub-query agent breaks down the
query into different components

23. Graphs
•"What is the most effective sales strategy employed by a contemporary
of top sales leaders in the industry?"
•Reason about relationships to create DAG (directed acyclic graph)
•Extract non-local entities connected through multi-hop
•Identify root node -> Graph -> Sub-graph = Query -> Sub-query
Traditional efficient search methods, such as locality-sensitive hashing, which
are designed for similarity search, are not well-suited for extracting complex
structural patterns such as paths or subgraphs. Extracting structural
information must cover the critical evidence needed to answer the query
without exceeding the reasoning capacity of LLMs. Expanding the context
window increases computational complexity and can degrade RAG
performance by introducing irrelevant information.

24. Fine-Tuning Llama 3.1

25. Fine-Tuning Llama 3.1
Enhancing Query Generation Accuracy
Fine-tuning adapts Llama 3.1
to our client's specific needs
Improves understanding of
complex queries

26. Fine-Tuning Llama 3.1
Customization to Business Context
Incorporates specific
terminology and data schemas
Aligns model with industry-
specific language

27. Fine-Tuning Llama 3.1
Handling Domain-Specific Terms
"Customer churn" in telecom
"Inventory turnover" in retail
Examples:

28. Crafting a Custom Synthetic Dataset

29. Crafting a Custom Synthetic Dataset
Utilizing LLMs for Dataset Generation
Employed models like ChatGPT and Anthropic
Generated tailored question-query pairs for the
client's DWH

30. Crafting a Custom Synthetic Dataset
Building a Robust Training Set
Created and validated 100 extremely complex queries
Added 200 less complex queries for
comprehensive coverage

31. Crafting a Custom Synthetic Dataset
Building a Robust Training Set
Created and validated 100 extremely complex queries
Added 200 less complex queries for
comprehensive coverage
WITH CustomerOrderValues AS (
    SELECT
        "f_sales"."BILL_CUSTOMER_SID",
        DATE_TRUNC('quarter', "d_date"."DATE") AS "quarter",
        AVG("f_sales"."EXTENDED_PRICE") AS "avg_order_value",
        COUNT(DISTINCT "f_sales"."SALES_DOCUMENT_SID") AS "order_count"
    FROM "f_sales"
    JOIN "d_date" ON "f_sales"."ORDER_DATE_SID" = "d_date".date_sid
    WHERE "d_date"."DATE" >= DATE_TRUNC('quarter', CURRENT_DATE) - INTERVAL '3 months'
      AND "d_date"."DATE" < DATE_TRUNC('quarter', CURRENT_DATE) + INTERVAL '3 months'
    GROUP BY "f_sales"."BILL_CUSTOMER_SID", DATE_TRUNC('quarter', "d_date"."DATE")
),
CustomerGrowth AS (
    SELECT
        "c"."CUSTOMER_SID",
        "c"."CUSTOMER_NAME",
        "cov_current"."avg_order_value" AS "current_avg_order_value",
        "cov_previous"."avg_order_value" AS "previous_avg_order_value",
        ("cov_current"."avg_order_value" - "cov_previous"."avg_order_value") / "cov_previous"."avg_order_value" AS "growth_rate"
    FROM "d_customers" "c"
    JOIN CustomerOrderValues "cov_current" ON "c"."CUSTOMER_SID" = "cov_current"."BILL_CUSTOMER_SID"
    JOIN CustomerOrderValues "cov_previous" ON "c"."CUSTOMER_SID" = "cov_previous"."BILL_CUSTOMER_SID"
    WHERE "cov_current"."quarter" = DATE_TRUNC('quarter', CURRENT_DATE)
      AND "cov_previous"."quarter" = DATE_TRUNC('quarter', CURRENT_DATE) - INTERVAL '3 months'
      AND "cov_current"."order_count" >= 5
      AND "cov_previous"."order_count" >= 5
),
CompanyAverage AS (
    SELECT SUM("f_sales"."EXTENDED_PRICE") / COUNT("f_sales"."SALES_DOCUMENT_SID") AS "company_avg_order_value"
    FROM "f_sales"
    JOIN "d_date" ON "f_sales"."ORDER_DATE_SID" = "d_date".date_sid
    WHERE "d_date"."DATE" >= DATE_TRUNC('quarter', CURRENT_DATE)
      AND "d_date"."DATE" < DATE_TRUNC('quarter', CURRENT_DATE) + INTERVAL '3 months'
)
SELECT
    "cg"."CUSTOMER_NAME",
    ROUND("cg"."current_avg_order_value", 2) AS "current_avg_order_value",
    ROUND("cg"."previous_avg_order_value", 2) AS "previous_avg_order_value",
    ROUND("cg"."growth_rate" * 100, 2) AS "growth_percentage",
    ROUND(("cg"."current_avg_order_value" - "ca"."company_avg_order_value") / "ca"."company_avg_order_value" * 100, 2) AS "percent_difference_from_company_avg"
FROM CustomerGrowth "cg"
CROSS JOIN CompanyAverage "ca"
WHERE "cg"."growth_rate" > 0
ORDER BY "cg"."growth_rate" DESC
LIMIT 10;
"Which customers have
shown the highest increase
in average order value from
last quarter to this quarter,
and how does their current
performance compare to
the overall company
average?"

32. Crafting a Custom Synthetic Dataset
Building a Robust Training Set
Created and validated 100 extremely complex queries
Added 200 less complex queries for
comprehensive coverage

33. Crafting a Custom Synthetic Dataset
Expanding Through Paraphrasing
Addressed natural language ambiguities
Added 200 less complex queries for
comprehensive coverage

34. Crafting a Custom Synthetic Dataset
Impact on Model Performance
Improved accuracy and relevance in query results
Enhanced ability to handle varied expressions
and complex queries

35. System in Action

37. Expanding Capabilities and Tackling Challenges
•Current Challenges:
•Ongoing model tuning for diverse datasets
•Context management for complex queries
•SQL accuracy and injection prevention
•Future Directions:
•Reduced latency
•High precision during the query generation
•Better intention detection

38. Thank you!