Category: Microsoft
Category Archives: Microsoft
Resolving QuickBooks Error 6144 and 301 After Windows Update
How can I resolve QuickBooks Error 6144 and 301 that appeared after a recent Windows update? I’ve tried restarting my computer and updating QB, but the error persists. What steps should I follow to fix this issue?
How can I resolve QuickBooks Error 6144 and 301 that appeared after a recent Windows update? I’ve tried restarting my computer and updating QB, but the error persists. What steps should I follow to fix this issue? Read More
“New” to Viva Engage, with over 100 existing M365 Groups (private) – how to approach communities?
Hi,
I have used Yammer in the past (pre 2016) and have refrained and not encouraged usage in our organization due to the very disconnected user experience and also not having the ressources to manage yet another channel of communications.
I want revisit the current Viva Engage situation. I’ve let the Yammer Support reprovision our network for EU data residency, so it’s completely empty. By reading the documentation I would assume we’re about as aligend to M365 as is possible.
It seems like I can create Communities that are connected to M365 Groups by-default, but I haven’t found the other way around.
What am I todo with our existing 100 private M365 Groups that mostly represent organizational departments, project teams, larger organizational topics/interests?
Are we expected to re-create all these groups? Are there any useful “migration” paths/ideas for this scenario?
I’m really not a fan of M365 Groups clutter and also do not allow the creation of groups outside of administrator for this very reason.
any help or further links to other resources are high appreciated.
Hi, I have used Yammer in the past (pre 2016) and have refrained and not encouraged usage in our organization due to the very disconnected user experience and also not having the ressources to manage yet another channel of communications. I want revisit the current Viva Engage situation. I’ve let the Yammer Support reprovision our network for EU data residency, so it’s completely empty. By reading the documentation I would assume we’re about as aligend to M365 as is possible. It seems like I can create Communities that are connected to M365 Groups by-default, but I haven’t found the other way around. What am I todo with our existing 100 private M365 Groups that mostly represent organizational departments, project teams, larger organizational topics/interests? Are we expected to re-create all these groups? Are there any useful “migration” paths/ideas for this scenario?I’m really not a fan of M365 Groups clutter and also do not allow the creation of groups outside of administrator for this very reason. any help or further links to other resources are high appreciated. Read More
Trade Evista 1000 Reviews 2024: Trade Evista 1000 App Scam OR Not Trading AI Platform?
After diving into the functionalities and benefits of the Evista 1000 trading platform, it’s clear that this tool offers a robust solution for beginners eager to step into the trading world. With its user-friendly interface, comprehensive resources, and advanced tools adapted for novice traders, the Evista 1000 provides a solid foundation for anyone starting their trading journey.
Remember, the key to successful trading lies in continuous learning and practice. The Evista 1000 is designed to support your growth, making it easier to track markets, analyze trends, and execute trades efficiently. So, take your time to explore each feature, utilize the educational materials available, and start your trading experience with confidence. Happy trading!
After diving into the functionalities and benefits of the Evista 1000 trading platform, it’s clear that this tool offers a robust solution for beginners eager to step into the trading world. With its user-friendly interface, comprehensive resources, and advanced tools adapted for novice traders, the Evista 1000 provides a solid foundation for anyone starting their trading journey. Remember, the key to successful trading lies in continuous learning and practice. The Evista 1000 is designed to support your growth, making it easier to track markets, analyze trends, and execute trades efficiently. So, take your time to explore each feature, utilize the educational materials available, and start your trading experience with confidence. Happy trading! Read More
Optimizing Retrieval for RAG Apps: Vector Search and Hybrid Techniques
In our previous blog, we talked about LLMs and incorporating domain knowledge techniques such as Retrieval Augmentation Generation (RAG) to solve the issue of outdated knowledge.
In this blog we are going to dive into optimizing our search strategy with Hybrid search techniques. Common practices for implementing the retrieval step in retrieval-augmented generation (RAG) applications are;
Keyword search
Vector Search
Hybrid search (Keyword + Vector)
Hybrid + Semantic ranker
Optimal search strategy
Keyword search – Uses traditional full-text search methods – content is broken into terms through language-specific text analysis, inverted indexes are created for fast retrieval, and the BM25 probabilistic model is used for scoring.
Vector search – is best for finding semantically related matches, which is a fully supported pattern in Azure AI Search . Documents are converted from text to vector representations using an embedding model. Retrieval is performed by generating a query embedding and finding the documents whose vectors are closest to the query’s. We used Azure Open AI text-embedding-ada-002 (Ada-002) embeddings and cosine similarity.
Vector embeddings – An embedding encodes an input as a list of floating-point numbers. Different models output different embeddings, with varying lengths.
”dog” → [0.017198, -0.007493, -0.057982, 0.054051, -0.028336, 0.019245,…]
Vector similarity – We compute embeddings so that we can calculate similarity between inputs. The most common distance measurement is cosine similarity.
In the above image we can use Cosine similarity, a common way to measure vector similarity is by calculating the cosine similarity between two vectors. A cosine similarity value close to 1 indicates high similarity, while a value close to 0 indicates dissimilarity, this is in the context of natural language processing (NLP) and machine learning.
Let’s say we have word embeddings for “dog,” “woof,” and “cat.”
If we calculate the cosine similarity between the vectors for “dog” and “woof,” we might get a high value (close to 1) because they are related.
However, the cosine similarity between “dog” and “cat” would likely be lower (closer to 0) because they represent different animals with distinct characteristics. Remember that this concept extends beyond words; it applies to any vectors in an embedding space. Whether it’s words, images, or other data points, measuring similarity helps us understand relationships and make informed decisions in various applications
Hybrid search (Keyword + Vector) – combines vector search and keyword search, optimally using Reciprocal-Rank-Fusion for merging results and a Machine Learning model to re-rank results after
Hybrid + Semantic ranker – generative AI scenarios typically use the top 3 to 5 results as their grounding context to prioritize the most important results. AI Search applications work best with a calibrated relevance score that can be used to filter out low quality results. The semantic ranker runs the query and documents text simultaneously though transformer models that utilize the cross-attention mechanism to produce a ranker score.
A score of 0 represents a very irrelevant chunk, and a score of 4 represents an excellent one. In the chart below, Hybrid + Semantic ranking finds the best content for the LLM at each result set size. See code example on this repo by Pamela fox.
RAG with hybrid search
Using the above image, when user sends the prompt “do my company…” the embedding model creates vector representations of that text. These embeddings capture the semantic meaning allowing similarity comparisons between different pieces of text. These embedding models include word2vec, BERT, and GPT (Generative Pre-trained Transformer). Using hybrid search we are able to use keyword + vector search and sematic search to retrieve more accurate response from our source ie pdf.
RAG With Vector Databases
We can extend this robust retrieval for RAG with a vector Database. A vector database is specifically designed for first, efficient storage and retrieval of high-dimensional vectors. There two types of Vector database there two types of Vector databases
Integrated vector database
pure vector database
A pure vector database is designed to efficiently store and manage vector embeddings, along with a small amount of metadata; it is separate from the data source from which the embeddings are derived
A vector database that is integrated in a highly performant NoSQL or relational database provides additional capabilities. The integrated vector database in a NoSQL or relational database can store, index, and query embeddings alongside the corresponding original data. This approach eliminates the extra cost of replicating data in a separate pure vector database. Moreover, keeping the vector embeddings and original data together better facilitates multi-modal data operations, and enables greater data consistency, scale, and performance.
Integrated vector database on Azure
Azure Cosmos DB for MongoDB vCore
Azure Cosmos DB for PostgreSQL.
Azure Cosmos Db for NoSQL API – is under development and will be announced on May 2024.
Read more
Open-source vector databases
How to enable and use pgvector on Azure Cosmos DB for PostgreSQL
Build applications for free with Azure Cosmos DB for MongoDB (vCore) Free Tie
Querying in Azure AI Search
Transparency note: Azure AI Search
Code samples
Python notebook tutorial – Vector database integration through LangChain
Python RAG pattern – Azure product chatbot
Microsoft Tech Community – Latest Blogs –Read More
Dealing With QuickBooks Company File Error 6190 and 816 How to Fix it
I’m encountering QuickBooks Company File Error 6190 and 816 when trying to access my company file. How can I resolve this issue? Any help would be appreciated!
I’m encountering QuickBooks Company File Error 6190 and 816 when trying to access my company file. How can I resolve this issue? Any help would be appreciated! Read More
Why Can’t open company file in QuickBooks Desktop After latest update?
I’m having trouble opening my company file in QuickBooks Desktop. Every time I try, I get an error message saying the file cannot be opened. I’ve tried restarting my computer and QuickBooks, but the problem persists. What could be causing this issue, and how can I resolve it?
I’m having trouble opening my company file in QuickBooks Desktop. Every time I try, I get an error message saying the file cannot be opened. I’ve tried restarting my computer and QuickBooks, but the problem persists. What could be causing this issue, and how can I resolve it? Read More
Why Is QuickBooks Direct Deposit Not Working on Window 10/11
I’m experiencing an issue where QuickBooks Direct Deposit is not working on Windows 10/11. It was functioning fine previously, but now it fails to process payments. What could be causing this problem, and how can I resolve it?
I’m experiencing an issue where QuickBooks Direct Deposit is not working on Windows 10/11. It was functioning fine previously, but now it fails to process payments. What could be causing this problem, and how can I resolve it? Read More
Why is My QuickBooks is Unable to open this company file Error 6190 Windows 10/11?
I’m encountering an error with QuickBooks: “Unable to open this company file Error 6190.” This issue is preventing me from accessing my company file, and it’s causing significant disruption to my business operations. What are the steps I can take to troubleshoot and resolve this error?
I’m encountering an error with QuickBooks: “Unable to open this company file Error 6190.” This issue is preventing me from accessing my company file, and it’s causing significant disruption to my business operations. What are the steps I can take to troubleshoot and resolve this error? Read More
Why I am Getting QuickBooks error 1603 when trying to Install or Update QB
I’m encountering QuickBooks error 1603 when trying to install or update QB. This error is causing significant disruption to my business operations. Could you provide a solution to fix this issue?
I’m encountering QuickBooks error 1603 when trying to install or update QB. This error is causing significant disruption to my business operations. Could you provide a solution to fix this issue? Read More
Resolve Quickbooks Desktop Error 6190 and 816 Windows 11
I’ve encountered QuickBooks Desktop Error 6190 and 816 on Windows 11. How can I resolve this issue? It’s urgent as it’s affecting my business operations. Any troubleshooting steps or solutions would be greatly appreciated.
I’ve encountered QuickBooks Desktop Error 6190 and 816 on Windows 11. How can I resolve this issue? It’s urgent as it’s affecting my business operations. Any troubleshooting steps or solutions would be greatly appreciated. Read More
Azure Monitor cost optimization using Azure Advisor
We in Azure Monitor are committed to assisting you in optimizing your budget allocation, making informed decisions about monitoring options, and discovering features and configurations that enable you to get more out of your infrastructure.
Azure Advisor is a free offering that can help you avoid problems and save money by providing you with proactive best practice guidance.
Consider configuring the low-cost Basic logs plan on selected tables:
This recommendation identifies an ingestion of more than 1 GB per month for tables eligible for the low-cost Basic Log data plan.
The Basic Log plan gives the you the ability to use search capabilities for debugging and troubleshooting at a much lower cost – Read more about Basic logs.
Consider Changing Pricing Tier:
Each Log Analytics workspace in Azure Monitor can have a different price tier.
This recommendation identifies Log Analytics workspaces that should be in a different pricing tier and tells which tier your workspace should change to – Read more about pricing tiers.
Consider removing unused restored tables:
If you use the restore function, you may forget to delete the restored tables after the operation is complete, resulting in high costs and frustration.
This recommendation detects restored data that has been active in your workspace for more than a week.
It is then recommends to delete the table to avoid unnecessary costs. Read more about restore tables.
How do I see my recommendations?
Log in to Azure Portal
New recommendations will be added in the next few months to help you reduce your overall cost in Azure Monitor and detect anomalies.
New recommendations will be added in the next few months to help you reduce your overall cost in Azure Monitor and detect anomalies.
Search for Advisor, in the search pane:
New recommendations will be added in the next few months to help you reduce your overall cost in Azure Monitor and detect anomalies.
Microsoft Tech Community – Latest Blogs –Read More
Pro 10 with Snapdragon Elite
I drank the Koolaid and ordered a Pro Elite. However, I have a question about the 5g ability that will come in the future. Is no 5g for now a hardware restriction, ie that there is no nano SIM slot built in? Or is it a software issue where either (or both) the slot IS built-in, or the eSIM chip is built in, but the software to activate or the device drivers are not yet developed and tested? Or, as noted by either Thurott or Zac, the Pro 10 case has open cooling vents that seem to mean that there were a bunch of cases in a store room somewhere and they used those up to (1) save money and (2) get Pro 10 ARMs out the door into the public’s hands that are not quite what the pro 11 is going to be about Christmas time.
I drank the Koolaid and ordered a Pro Elite. However, I have a question about the 5g ability that will come in the future. Is no 5g for now a hardware restriction, ie that there is no nano SIM slot built in? Or is it a software issue where either (or both) the slot IS built-in, or the eSIM chip is built in, but the software to activate or the device drivers are not yet developed and tested? Or, as noted by either Thurott or Zac, the Pro 10 case has open cooling vents that seem to mean that there were a bunch of cases in a store room somewhere and they used those up to (1) save money and (2) get Pro 10 ARMs out the door into the public’s hands that are not quite what the pro 11 is going to be about Christmas time. Read More
Exploring the New Frontier of AI: OpenAI’s GPT-4-o For Indic Languages
In the ever-evolving landscape of artificial intelligence, OpenAI has once again pushed the boundaries with the introduction of the GPT-4-o model, featuring the innovative o200k_base tokenizer. This development marks a significant leap forward in the field, offering unprecedented speed, affordability, and multimodal capabilities.
What is GPT-4-o?
GPT-4-o, where the ‘o’ stands for “omni,” is OpenAI’s latest flagship generative model introduced on May 13, 2024. It is designed to handle a diverse array of inputs including text, speech, and video, and can generate outputs in various formats such as text, audio, and images. This versatility makes it a powerful tool for a wide range of applications. This integration marks a pivotal evolution from its predecessors, primarily focusing on text-based processing.
The o200k_base Tokenizer
The o200k_base tokenizer is a new tokenization algorithm that forms the backbone of the GPT-4-o model. Tokenization is a critical process in natural language processing that involves breaking down text into smaller units called tokens. These tokens can be words, subwords, or even characters, depending on the tokenizer’s design.
The o200k_base tokenizer represents an evolution in this process, designed to be faster and more efficient than its predecessors. It allows GPT-4-o to process and generate language at speeds that were previously unattainable. The o200kbase tokenizer not only improves the semantic coherence of the generated text but also plays a crucial role in handling multiple languages more effectively, thereby broadening the scope of GPT-4o’s applications across different linguistic contexts.
Features and Capabilities
Multimodal Inputs and Outputs: GPT-4-o accepts and emits a variety of data types, setting it apart from earlier models that were limited to text. This makes it an “omni” model, capable of more complex tasks that mirror human interaction with various forms of data.
Improved Token Generation Speed: GPT-4-o is reported to generate tokens twice as fast as GPT-4 Turbo, enhancing its efficiency and making it suitable for real-time applications.
Cost-Effectiveness: Despite its advanced capabilities, GPT-4-o is more affordable than its predecessors. The API costs have been significantly reduced, making it accessible for a broader range of users and developers.
Enhanced Vision Capabilities: Compared to previous models, GPT-4-o has improved vision capabilities, allowing it to handle tasks involving image recognition and manipulation with greater finesse.
Analysis of Indic languages
The analysis of the o200k_base tokenizer’s performance across various Indic languages demonstrates significant improvements in efficiency and reduction in token usage when working with GPT-4o models. The data highlights that the Malayalam language experienced the most substantial efficiency improvement of almost 4x. Kannada and Telugu also show impressive improvements, with reduction percentages nearing 79% and 77%, respectively, and high improvement factors suggesting much greater processing efficiency. This trend continues notably with Gujarati and Tamil, showcasing over 74% reduction in token usage. On the lower end of the scale, languages like Kashmiri and Manipuri displayed lesser improvement, with Kashmiri only showing a 37.70% reduction and Manipuri showing no improvement in token usage. This indicates variability in how the new tokenizer handles different linguistic structures and scripts, which might be due to the inherent linguistic features or the training data’s coverage and quality.
Language Name
Avg Tokens GPT-4
Avg Tokens GPT-4o
Avg % Reduction in Tokens
Improvement Factor
Malayalam (മലയാളം)
4775
957
79.35%
3.99x
Kannada (ಕನ್ನಡ)
3681
766
78.83%
3.8x
Telugu (తెలుగు)
4097
893
76.63%
3.59x
Gujarati (ગુજરાતી)
3408
758
74.36%
3.49x
Tamil (தமிழ்)
3949
948
74.46%
3.17x
Bangla (বাংলা)
2550
704
70.06%
2.62x
Punjabi (ਪੰਜਾਬੀ)
4208
1297
67.73%
2.24x
Assamese (অসমীয়া)
2866
884
67.11%
2.24x
Hindi (हिन्दी)
2090
655
64.20%
2.19x
Nepali (नेपाली)
2638
878
61.59%
2.0x
Urdu (اردو)
2428
854
62.31%
1.84x
Marathi (मराठी)
2593
912
62.65%
1.84x
Bhojpuri (Bhojpuri)
1970
699
62.31%
1.82x
Chhattisgarhi
1958
733
59.89%
1.67x
Maithili (Maithili)
1975
767
60.04%
1.58x
Odia (ଓଡ଼ିଆ)
6074
2432
60.34%
1.5x
Konkani (Konkani)
2135
875
56.91%
1.44x
Sindhi (سنڌي)
2188
921
55.08%
1.37x
Dogri (Dogri)
2361
1025
55.98%
1.3x
Kashmiri (کٲشُر)
2291
1484
37.70%
0.54x
Manipuri
6715
6715
0.00%
0.0x
Now we if we look from a cost perspective we get the additional benefit as GPT-4o is offered in 50% reduction in pricing compared to GPT-4-Turbo which then leads to further reduction in overall cost of typical RAG request. Here is a comparison of a typical RAG request with 1000 input words and 200 output words. Over all there is almost 5 fold reduction in overall cost.
How did we analyze?
The analysis of the o200k_base tokenizer’s performance across Indic languages was meticulously conducted using English language documents of varying lengths—approximately 10, 100, 500, and 1200 words. These documents were translated into each target Indic language using Azure AI Translator. Each translated document was then processed through both the tokenizer for GPT-4 and GPT-4o models to assess and record the number of tokens required by each model. This method allowed us to compare the efficiency of the new o200k_base tokenizer against its predecessor across different text lengths, providing a broad and robust dataset for analysis. After processing, the token counts from each document size were averaged to mitigate any anomalies that might occur at specific text lengths and to provide a more generalized view of performance across typical usage scenarios.
Real-world Applications
The implications of GPT-4-o’s capabilities are vast. Here are just a few potential applications:
Language Translation: With its efficient tokenization, GPT-4-o could provide near-instantaneous translation across multiple languages, breaking down communication barriers.
Content Creation: The model’s ability to handle text and images makes it an excellent tool for content creators, enabling the generation of rich multimedia content.
Educational Tools: GPT-4-o could revolutionize online learning by providing interactive multimodal content that adapts to various learning styles.
Accessibility Features: The model can convert speech to text and vice versa, offering new tools for individuals with disabilities to interact with technology.
Conclusion
The GPT-4-o model with the o200k_base tokenizer is a testament to OpenAI’s commitment to advancing AI technology. By enhancing speed, reducing costs, and expanding capabilities, GPT-4-o stands to democratize access to cutting-edge AI tools and pave the way for innovative applications that were once the realm of science fiction. As we stand on the brink of this new AI era, it is clear that OpenAI’s GPT-4-o is not just a technological milestone but also a harbinger of a future where AI and human creativity converge in exciting and transformative ways.
Microsoft Tech Community – Latest Blogs –Read More
Windows 11 Explorer close
Hello. Any time i tries to select or right click on a zip file explorer close right away.
i have 7zip installed.
any help ?
Thanks
Hello. Any time i tries to select or right click on a zip file explorer close right away.i have 7zip installed. any help ?Thanks Read More
Excel 365 storing date as serial number
Hello
I’m using an Excel Ghant Chart template from Excel – I’ve added a line to add in mmm-yy and it displays as the 5 digit serial number. The cell is formatted as a Custom mmm-yy, but still displays as the 5 digit number. When I click on the cell the formula bar shows the date but the cell doesn’t.
I’m wondering if it’s locked as it is a ‘standard’ template. I can see a lot of Naming conventions have been applied throughout. Does anyone know what the fix may be?
Thanks in advance
April
HelloI’m using an Excel Ghant Chart template from Excel – I’ve added a line to add in mmm-yy and it displays as the 5 digit serial number. The cell is formatted as a Custom mmm-yy, but still displays as the 5 digit number. When I click on the cell the formula bar shows the date but the cell doesn’t.I’m wondering if it’s locked as it is a ‘standard’ template. I can see a lot of Naming conventions have been applied throughout. Does anyone know what the fix may be?Thanks in advanceApril Read More
Is Windows 10 better than Windows 11?
I’ve been using Windows 10 for a while now, but I’m considering upgrading to Windows 11. I’ve heard mixed reviews about the new operating system and I’m not sure if it’s worth the upgrade. I’ve been wondering if Windows 11 has any significant improvements or features that would make it a better choice than Windows 10. For example, is the user interface more intuitive? Are there any new security features that would make my computer more secure? I’d love to hear from people who have experience with both operating systems and can compare the two.
I’ve been using Windows 10 for a while now, but I’m considering upgrading to Windows 11. I’ve heard mixed reviews about the new operating system and I’m not sure if it’s worth the upgrade. I’ve been wondering if Windows 11 has any significant improvements or features that would make it a better choice than Windows 10. For example, is the user interface more intuitive? Are there any new security features that would make my computer more secure? I’d love to hear from people who have experience with both operating systems and can compare the two. Read More
SharePoint list to Forms
Hi Everyone,
I would like to ask, how to reflect the lookup items to the form? Thanks in Advance
Hi Everyone,I would like to ask, how to reflect the lookup items to the form? Thanks in Advance Read More
Is there a safe and reliable TikTok to MP3 converter available for Windows 11?
I’m looking for a reliable and safe software to convert TikTok videos to MP3 on my Windows 11 PC. I’ve tried several tools, but none have been satisfactory—they’re either difficult to use or don’t convert effectively. Additionally, I’m wary of the security risks and intrusive ads often found in free online tiktok to mp3 converters. I’m seeking a recommendation for a user-friendly software that maintains high audio quality during conversion. If anyone has suggestions based on their experience, I would greatly appreciate it.
I’m looking for a reliable and safe software to convert TikTok videos to MP3 on my Windows 11 PC. I’ve tried several tools, but none have been satisfactory—they’re either difficult to use or don’t convert effectively. Additionally, I’m wary of the security risks and intrusive ads often found in free online tiktok to mp3 converters. I’m seeking a recommendation for a user-friendly software that maintains high audio quality during conversion. If anyone has suggestions based on their experience, I would greatly appreciate it. Read More
FOOTNOTE DISPLAY THE WRONG SEQUENCE OF NUMBERS
Hi, i’m having problem where my footnotes display the wrong sequence of numbers. As u can see, its supposed to be starting from 1,2 and then 3 as sequenced on the upper part of the document. but instead, it shows 2,3 and then 1. How to fix this issue?
Hi, i’m having problem where my footnotes display the wrong sequence of numbers. As u can see, its supposed to be starting from 1,2 and then 3 as sequenced on the upper part of the document. but instead, it shows 2,3 and then 1. How to fix this issue? Read More
Embed Copilot News Blog into SharePoint Page
Hi – within the Adoption Kit, there is guidance around how to build your own CoE. I am trying to add the Microsoft-365-Copilot-Blog-Updates as a web part in a page, but can’t find an embed code or any workaround to get it into the page… Any help? (I’m assuming it’s this link: Microsoft Copilot Blog | The latest AI News & Insights)
Refer to the screenshot below of the guidance provided.
Hi – within the Adoption Kit, there is guidance around how to build your own CoE. I am trying to add the Microsoft-365-Copilot-Blog-Updates as a web part in a page, but can’t find an embed code or any workaround to get it into the page… Any help? (I’m assuming it’s this link: Microsoft Copilot Blog | The latest AI News & Insights) Refer to the screenshot below of the guidance provided. Read More
