Building a Scalable Web Crawling and Indexing Pipeline with Azure storage and AI Search
In the ever-evolving world of data management, keeping search indexes up-to-date with dynamic data can be challenging. Traditional approaches, such as manual or scheduled indexing, are resource-intensive, delay-prone, and difficult to scale. Azure Blob Trigger combined with an AI Search Indexer offers a cutting-edge solution to overcome these challenges, enabling real-time, scalable, and enriched data indexing. This blog explores how Blob Trigger, integrated with Azure Cognitive Search, transforms the indexing process by automating workflows and enriching data with AI capabilities. It highlights the step-by-step process of configuring Blob Storage, creating Azure Functions for triggers, and seamlessly connecting with an AI-powered search index. The approach leverages Azure's event-driven architecture, ensuring efficient and cost-effective data management.Building an AI-Powered ESG Consultant Using Azure AI Services: A Case Study
In today's corporate landscape, Environmental, Social, and Governance (ESG) compliance has become increasingly important for stakeholders. To address the challenges of analyzing vast amounts of ESG data efficiently, a comprehensive AI-powered solution called ESGai has been developed. This blog explores how Azure AI services were leveraged to create a sophisticated ESG consultant for publicly listed companies. https://youtu.be/5-oBdge6Q78?si=Vb9aHx79xk3VGYAh The Challenge: Making Sense of Complex ESG Data Organizations face significant challenges when analyzing ESG compliance data. Manual analysis is time-consuming, prone to errors, and difficult to scale. ESGai was designed to address these pain points by creating an AI-powered virtual consultant that provides detailed insights based on publicly available ESG data. Solution Architecture: The Three-Agent System ESGai implements a sophisticated three-agent architecture, all powered by Azure's AI capabilities: Manager Agent: Breaks down complex user queries into manageable sub-questions containing specific keywords that facilitate vector search retrieval. The system prompt includes generalized document headers from the vector database for context. Worker Agent: Processes the sub-questions generated by the Manager, connects to the vector database to retrieve relevant text chunks, and provides answers to the sub-questions. Results are stored in Cosmos DB for later use. Director Agent: Consolidates the answers from the Worker agent into a comprehensive final response tailored specifically to the user's original query. It's important to note that while conceptually there are three agents, the Worker is actually a single agent that gets called multiple times - once for each sub-question generated by the Manager. Current Implementation State The current MVP implementation has several limitations that are planned for expansion: Limited Company Coverage: The vector database currently stores data for only 2 companies, with 3 documents per company (Sustainability Report, XBRL, and BRSR). Single Model Deployment: Only one GPT-4o model is currently deployed to handle all agent functions. Basic Storage Structure: The Blob container has a simple structure with a single directory. While Azure Blob storage doesn't natively support hierarchical folders, the team plans to implement virtual folders in the future. Free Tier Limitations: Due to funding constraints, the AI Search service is using the free tier, which limits vector data storage to 50MB. Simplified Vector Database: The current index stores all 6 files (3 documents × 2 companies) in a single vector database without filtering capabilities or schema definition. Azure Services Powering ESGai The implementation of ESGai leverages multiple Azure services for a robust and scalable architecture: Azure AI Services: Provides pre-built APIs, SDKs, and services that incorporate AI capabilities without requiring extensive machine learning expertise. This includes access to 62 pre-trained models for chat completions through the AI Foundry portal. Azure OpenAI: Hosts the GPT-4o model for generating responses and the Ada embedding model for vectorization. The service combines OpenAI's advanced language models with Azure's security and enterprise features. Azure AI Foundry: Serves as an integrated platform for developing, deploying, and governing generative AI applications. It offers a centralized management centre that consolidates subscription information, connected resources, access privileges, and usage quotas. Azure AI Search (formerly Cognitive Search): Provides both full-text and vector search capabilities using the OpenAI ada-002 embedding model for vectorization. It's configured with hybrid search algorithms (BM25 RRF) for optimal chunk ranking. Azure Storage Services: Utilizes Blob Storage for storing PDFs, Business Responsibility Sustainability Reports (BRSRs), and other essential documents. It integrates seamlessly with AI Search using indexers to track database changes. Cosmos DB: Employs MongoDB APIs within Cosmos DB as a NoSQL database for storing chat history between agents and users. Azure App Services: Hosts the web application using a B3-tier plan optimized for cost efficiency, with GitHub Actions integrated for continuous deployment. Project Evolution: From Concept to Deployment The development of ESGai followed a structured approach through several phases: Phase 1: Data Cleaning Extracted specific KPIs from XML/XBRL datasets and BRSR reports containing ESG data for 1,000 listed companies Cleaned and standardized data to ensure consistency and accuracy Phase 2: RAG Framework Development Implemented Retrieval-Augmented Generation (RAG) to enhance responses by dynamically fetching relevant information Created a workflow that includes query processing, data retrieval, and response generation Phase 3: Initial Deployment Deployed models locally using Docker and n8n automation tools for testing Identified the need for more scalable web services Phase 4: Transition to Azure Services Migrated automation workflows from n8n to Azure AI Foundry services Leveraged Azure's comprehensive suite of AI services, storage solutions, and app hosting capabilities Technical Implementation Details Model Configurations: The GPT model is configured with: Model version: 2024-11-20 Temperature: 0.7 Max Response Token: 800 Past Messages: 10 Top-p: 0.95 Frequency/Presence Penalties: 0 The embedding model uses OpenAI-text-embedding-Ada-002 with 1536 dimensions and hybrid semantic search (BM25 RRF) algorithms. Cost Analysis and Efficiency A detailed cost breakdown per user query reveals: App Server: $390-400 AI Search: $5 per query RAG Query Processing: $4.76 per query Agent-specific costs: Manager: $0.05 (30 input tokens, 210 output tokens) Worker: $3.71 (1500 input tokens, 1500 output tokens) Director: $1.00 (600 input tokens, 600 output tokens) Challenges and Solutions The team faced several challenges during implementation: Quota Limitations: Initial deployments encountered token quota restrictions, which were resolved through Azure support requests (typically granted within 24 hours). Cost Optimization: High costs associated with vectorization required careful monitoring. The team addressed this by shutting down unused services and deploying on services with free tiers. Integration Issues: GitHub Actions raised errors during deployment, which were resolved using GitHub's App Service Build Service. Azure UI Complexity: The team noted that Azure AI service naming conventions were sometimes confusing, as the same name is used for both parent and child resources. Free Tier Constraints: The AI Search service's free tier limitation of 50MB for vector data storage restricts the amount of company information that can be included in the current implementation. Future Roadmap The current implementation is an MVP with several areas for expansion: Expand the database to include more publicly available sustainability reports beyond the current two companies Optimize token usage by refining query handling processes Research alternative embedding models to reduce costs while maintaining accuracy Implement a more structured storage system with virtual folders in Blob storage Upgrade from the free tier of AI Search to support larger data volumes Develop a proper schema for the vector database to enable filtering and more targeted searches Scale to multiple GPT model deployments for improved performance and redundancy Conclusion ESGai demonstrates how advanced AI techniques like Retrieval-Augmented Generation can transform data-intensive domains such as ESG consulting. By leveraging Azure's comprehensive suite of AI services alongside a robust agent-based architecture, this solution provides users with actionable insights while maintaining scalability and cost efficiency. https://youtu.be/5-oBdge6Q78?si=Vb9aHx79xk3VGYAh
Azure OpenAI Content Filter Result is always content_filter_error
I'm exploring blocklists as a solution for OpenAI not detecting sensitive words (specifically "wrist-cutting" in my local language (Cantonese) (to be fair not even Chinese AIs know the word) I have created a Blocklist with 1 entry: Term: [鎅𰾛𠝹]手 Type: Regex It can block inputs with ease: { "error": { "message": "The response was filtered due to the prompt triggering Azure OpenAI's content management policy. Please modify your prompt and retry. To learn more about our content filtering policies please read our documentation: https://go.microsoft.com/fwlink/?linkid=2198766", "type": null, "param": "prompt", "code": "content_filter", "status": 400, "innererror": { "code": "ResponsibleAIPolicyViolation", "content_filter_result": { "custom_blocklists": { "details": [ { "filtered": true, "id": "ChineseBlockList" } ], "filtered": true }, "hate": { "filtered": false, "severity": "safe" }, "profanity": { "filtered": false, "detected": false }, "self_harm": { "filtered": false, "severity": "safe" }, "sexual": { "filtered": false, "severity": "safe" }, "violence": { "filtered": false, "severity": "safe" } } } } } However, it cannot block outputs. { "choices": [ { "content_filter_result": { "error": { "code": "content_filter_error", "message": "The contents are not filtered" } }, "content_filter_results": {}, "finish_reason": "stop", "index": 0, "logprobs": null, "message": { "content": "𠝹手（也寫作“拍手”）是一種手部動作，通常是將雙手合攏並用力拍打在一起，發出聲音。這個動作常用於表達讚賞、鼓勵或慶祝，像是在演出結束後觀眾的掌聲，或是在某些活動中用來引起注意。𠝹手也可以用於節奏感的表達，像是在音樂中隨著節拍拍手。這個動作在許多文化中都有其獨特的意義和用途。", "refusal": null, "role": "assistant" } } ], "created": 1737702254, "id": "chatcmpl-At81eUTIzDkZPCKznSKr19YMJU1ud", "model": "gpt-4o-mini-2024-07-18", "object": "chat.completion", "prompt_filter_results": [ { "prompt_index": 0, "content_filter_results": { "custom_blocklists": { "filtered": false }, "hate": { "filtered": false, "severity": "safe" }, "profanity": { "filtered": false, "detected": false }, "self_harm": { "filtered": false, "severity": "safe" }, "sexual": { "filtered": false, "severity": "safe" }, "violence": { "filtered": false, "severity": "safe" } } } ], "system_fingerprint": "fp_5154047bf2", "usage": { "completion_tokens": 138, "completion_tokens_details": { "accepted_prediction_tokens": 0, "audio_tokens": 0, "reasoning_tokens": 0, "rejected_prediction_tokens": 0 }, "prompt_tokens": 34, "prompt_tokens_details": { "audio_tokens": 0, "cached_tokens": 0 }, "total_tokens": 172 } }Dell APEX File Storage for Microsoft Azure brings a powerful new option to our customers
Dell PowerScale OneFS has been trusted by customers across all industries to provide performant, resilient, and scalable multiprotocol file storage for nearly two decades. At Ignite 2024 we announced a new Dell managed variant that compliments the existing offering to give you powerful choice from a proven industry leader.
Search Selected Documents with Azure Open AI BYOD Search
I have azure blob with 3 documents (Doc 1, Doc 2, Doc 3) and they are being search through azure open and azure search service which is working perfectly fine. But my requirement is to restrict my search to only Doc 2 and Doc 3. But m unable to find any option through which i can do this. How can this be done? Below is the sample body- { "dataSources": [ { "type": "AzureCognitiveSearch", "parameters": { "endpoint": "https://@@@@@@@@@@@@@.search.windows.net", "key": "@@@@@@@@@@@@@", "indexName": "abcd-index", "semanticConfiguration": "", "queryType": "simple", "fieldsMapping": { "contentFieldsSeparator": "\n", "contentFields": [ "content" ], "filepathField": null, "titleField": "title", "urlField": null }, "inScope": true, "roleInformation": "You are an AI assistant that helps people find information." } } ], "messages": [ { "role": "user", "content": "tell me about solution versioning" } ] }
