feat: added section why and how

content/en/docs/_index.md

@@ -10,14 +10,6 @@ AdvisorLens is a neuro-symbolic AI online conversation platform that offers  exp
 It could be used to various industries, such as financial advice, business consulting, career guidance, or even personal development.
 
 
-**Why Choose AdvisorLens?**
-
-* **Unique Perspectives:** Our platform delves into a wealth of private documents, offering you a perspective that's as unique as your needs. Every answer provided is rooted in factual information sourced directly from your extensive document repository. 
-
-* **Infinite Knowledge:** At AdvisorLens, there are no limits. We believe in the power of knowledge, which is why our knowledge base constantly expands. The more reference documents you have, the more robust and informed our conversations become.
-
-* **Professional Human-Friendly Dialogue:** We understand the importance of a professional yet human touch. AdvisorLens seamlessly blends artificial intelligence with human-friendly dialogue. Our platform leverages state-of-the-art LLM technologies, ensuring every conversation feels natural and insightful.
-
 **Join the Conversation:**
 
 Ready to embark on a journey where every dialogue is enlightening and every answer is rooted in facts? Join AdvisorLens today and experience the difference a knowledgeable conversation can make.

content/en/docs/how it works.md

@@ -0,0 +1,49 @@
+---
+title: How it works
+description: Learn how How do AdvisorLens work?
+weight: 15
+---
+
+AdvisorLens is a innovative implementaton of neuro-symbolic AI platform that operates in two phases: Retrieval and content generation.
+
+In the retrieval phase:
+
+Algorithms actively search for and retrieve relevant information based on the user’s prompt. This retrieved information is the basis for generating coherent and contextually relevant responses.
+
+AdvisorLens works both in open and close domain enterprise settings, a more restricted set of trusted sources is typically used to enhance the security and reliability of internal knowledge. For example, AdvisorLens system can look for:
+- Current contextual factors, such as real-time weather updates and the user’s precise location
+- User-centric details, their previous orders on the website, their interactions with the website, and their current account status
+- Relevant factual data in private documents that are  private  
+
+In the content generation phase:
+
+After retrieving the relevant information, a generative language model, such as a transformer-based model, takes over. It uses the retrieved context to generate natural language responses. The generated text can be further conditioned or fine-tuned based on the retrieved content to ensure that it aligns with the context and is contextually accurate. The system  includes references to the sources it consulted for transparency and verification purposes.
+
+```plantuml
+database "Proprietary data" as data
+actor "User Question" as questions
+node "AdvisorLens Model" as model
+database "Knowlege graph db" as kb #line.dashed
+file "Semantic Context" as prompt #line.dashed
+agent LLM
+file "answers"
+
+data --> model
+questions --> model
+model -> kb : Store
+model -> kb : Search
+
+questions --> prompt
+kb --> prompt : most relevant documents
+
+prompt -> LLM
+LLM -> answers
+```
+
+The image shows how AdvisorLens works: the AdvisorLens model parses proprietary data, detect semantics and store it in a knowledge graph. Then the model receives the user question and search it in the semanti knowledge base. It retrieves the top relevant documents and prompt the original question and information to LLM which leads LLM to generate an accurate answer.
+
+
+AdvisorLens use two systems to obtain external data:
+
+- **Knowledge graph**: Knowledge graph help find relevant documents using semantic searches. They can also work independently.
+- **Feature stores**: These are systems or platforms to manage and store structured data features used in machine learning and AI applications. They provide organized and accessible data for training and inference processes in machine learning models like LLMs.

content/en/docs/why.md

@@ -0,0 +1,26 @@
+---
+title: Why Choose AdvisorLens?
+description: Read why AdvisorLens is better than the standard generative AI
+linkTitle: Why AdvisorLens
+menu: {main: {weight: 10}}
+weight: 10
+---
+
+We build AdvisorLens with these three key points in mind: 
+
+1. **Explainability:** Our platform delves into a wealth of private documents, offering you a perspective that's as unique as your needs. Every answer provided is rooted in factual information sourced directly from your extensive document repository. You are always in control of any answers you receive from our platform. Say goodbye to hallucinations in responses.
+2. **Infinite Knowledge:** At AdvisorLens, there are no limits. We believe in the power of knowledge, which is why our knowledge base constantly expands. The more reference documents you have, the more robust and informed our conversations become.
+3. **Professional Human-Friendly Dialogue:** We understand the importance of a professional yet human touch. AdvisorLens seamlessly blends artificial intelligence with human-friendly dialogue. Our platform levrages the  state-of-the-art LLM technologies, ensuring every conversation feels natural and insightful.
+
+
+AdvisorLens can be applied to various NLP applications, including chatbots, question-answering systems, and content generation, where correct information retrieval and natural language generation are critical. The key advantages AdvisorLens provides include:
+
+- **Improved relevance and accuracy:** By incorporating a retrieval component, AdvisorLens models can access external knowledge sources, ensuring the generated text is grounded in accurate and up-to-date information. This leads to more contextually relevant and accurate responses, reducing hallucinations in question answering and content generation.
+- **Contextual coherence:** AdvisorLens provide context for the generation process, making generating coherent and contextually appropriate text easier. This leads to more cohesive and understandable responses, as the generation component can build upon the retrieved information.
+- **Handling open-domain queries:** AdvisorLens models excel in taking open-domain questions where the required information may not be in the training data. The retrieval component can fetch relevant information from a vast knowledge base, allowing the model to provide answers or generate content on various topics.
+- **Reduced generation bias:** Incorporating retrieval can help mitigate some inherent biases in purely generative models. By relying on existing information from a diverse range of sources, AdvisorLens models can generate less biased and more objective responses.
+- **Efficient computation:** Retrieval-based models can be computationally efficient for tasks where the knowledge base is already available and structured. Instead of generating responses from scratch, they can retrieve and adapt existing information, reducing the computational cost.
+- **Multi-modal capabilities:** AdvisorLens models can be extended to work with multiple modalities, such as database and images. This allows them to generate contextually relevant text to textual and visual content, opening up possibilities for applications in image captioning, content summarization, and more.
+- **Customization and fine-tuning:** AdvisorLens models can be customized for specific domains or use cases. This adaptability makes them suitable for various applications, including domain-specific chatbots, customer support, and information retrieval systems.
+- **Human-AI Collaboration:** AdvisorLens models can assist humans in information retrieval tasks by quickly summarizing and presenting relevant information from a knowledge base, reducing the time and effort required for manual search.
+- **Symbolic knowledge integration:** AdvisorLens seamlessly integrates with semantic technologies and knowledge graphs to always obtain the references and motivation behind the provided answers.

hugo.toml

@@ -41,6 +41,7 @@ pygmentsUseClassic = false
 # See https://help.farbox.com/pygments.html
 pygmentsStyle = "tango"
 
+
 # Configure how URLs look like per section.
 [permalinks]
 blog = "/:section/:year/:month/:day/:slug/"
@@ -178,6 +179,9 @@ enable = false
 [params.links]
 # End user relevant links. These will show up on left side of footer and in the community page if you have one.
 
+[params.plantuml]
+enable = true
+
 
 # hugo module configuration