@clidey/dory 0.14.0 → 0.16.0

package/docs/features.mdx

@@ -1,217 +1,440 @@
 ---
-title: "Conversational AI: Chatting with Your Documents"
-description: "Enable interactive Q&A over your uploaded documents using the Morphik Agent and Console chat. This step-by-step guide shows how to setup, invoke, and optimize conversational workflows for research and support scenarios."
+title: 'Features'
+description: 'Overview of available components and features'
 ---
 
-# Conversational AI: Chatting with Your Documents
+## Headings Examples
 
-Enable interactive Q&A over your uploaded documents using the Morphik Agent and Console chat. This step-by-step guide shows you how to set up, invoke, and optimize conversational workflows for research and support scenarios, empowering you to get precise, context-aware answers directly from your document collections.
+```mdx
+# Heading 1
+```
+# Heading 1
 
----
+```mdx
+## Heading 2
+```
+# Heading 2
 
-## 1. Introduction
+```mdx
+### Heading 3
+```
+# Heading 3
+```mdx
+#### Heading 4
+```
+# Heading 4
+```mdx
+##### Heading 5
+```
+# Heading 5
+```mdx
+###### Heading 6
+```
+# Heading 6
 
-Conversational AI with Morphik lets you transform your document repositories into intelligent, interactive knowledge assistants. By leveraging Morphik's agent framework and chat interface, you can ask natural language questions about your documents and receive accurate, sourced responses combining search, analysis, and knowledge graph insights.
+<br />
 
-This guide focuses specifically on the **chatting experience** — how to activate and use the Morphik Agent alongside the Morphik Console or SDK to carry contextual conversations grounded in your document data.
+## Lists Examples
 
----
+```mdx
+- List item 1
+- List item 2
+- List item 3
+```
 
-## 2. Prerequisites
+- List item 1
+- List item 2
+- List item 3
 
-Before starting, ensure you have:
+```mdx
+1. List item 1
+2. List item 2
+3. List item 3
+```
 
-- A running Morphik server instance (hosted or self-hosted).
-- Documents uploaded to Morphik via the Console or SDK.
-- The Morphik Agent enabled and configured (part of Morphik Core).
-- Access to the Morphik Console for interactive chat or access to the Python SDK for programmatic use.
+1. List item 1
+2. List item 2
+3. List item 3
 
-> <Check>
-> Make sure your user account has permissions to query documents and knowledge graphs.
-> 
----
 
-## 3. Workflow Overview
 
-### What You Will Accomplish
+<br />
 
-- Set up Morphik Agent to interpret user queries.
-- Use natural language to query documents interactively.
-- Receive well-organized answers with clear source attributions.
-- Understand how the agent leverages multiple tools for retrieval and analysis.
+### Images
 
-### Time Estimate
+```mdx
+<img src="./assets/dory.jpeg" alt="Example image" className="object-cover w-64 h-64" />
+```
 
-~15–30 minutes to get a working chat interface and basic conversational flow.
+<img src="./assets/dory.jpeg" alt="Example image" className="object-cover w-64 h-64" />
 
-### Difficulty Level
 
-Intermediate — some familiarity with Morphik platform and basic querying.
+<br />
+<br />
+<br />
 
----
+## Code Components
 
-## 4. Setting Up Conversational AI
+### Code Block
+```typescript
+function example() {
+  return "Hello World";
+}
+```
 
-### Step 1: Confirm Documents Are Ingested
+### Code Group Block
 
-You must have documents ingested into Morphik.
+<CodeGroup>
+```typescript
+function example(): string {
+  return "Hello World";
+}
+```
+```javascript
+function example() {
+  return "Hello World";
+}
+```
+</CodeGroup>
 
-- Use the Console to upload or verify documents.
-- Or use the Python SDK `ingest_text()` or `ingest_file()` functions.
 
-### Step 2: Configure the Morphik Agent
+<br />
+<br />
+<br />
 
-The Morphik Agent acts as the orchestrator between user queries and Morphik's internal tools.
 
-- The agent uses a system prompt describing available tools like chunk retrieval, document analysis, knowledge graph queries, and code execution.
-- It converts user input into function calls to relevant Morphik APIs.
+## Interactive Components
 
-Typical agent setup (embedded in Morphik Core):
+### Mermaid
 
-```python
-from core.agent import MorphikAgent
+```mdx
+mermaid
+graph TD
 
-# Assume document_service is your Morphik document API client
-agent = MorphikAgent(document_service=document_service, model="gpt-4")  # or any supported model
-```
+  %% Main Start
+  Start([Start Process]) --> Validate[Validate Input]
 
-### Step 3: Build a Chat Interface
+  %% Decision Point
+  Validate -->|Valid| ProcessData{Is Data Clean?}
+  Validate -->|Invalid| Error[Show Error Message]
 
-You can interact with the agent through several clients:
+  %% Clean Data Branch
+  ProcessData -->|Yes| Clean[Clean Data]
+  Clean --> Analyze[Analyze Data]
 
-- **Morphik Console Chat**: Web-based chat UI within the Morphik Console.
-- **Python SDK**: Run queries programmatically by sending conversational history and user queries.
+  %% Dirty Data Branch
+  ProcessData -->|No| Notify[Notify User]
+  Notify --> Wait[Wait for Input]
+  Wait --> Validate
 
-Example: Basic agent run call from Python
+  %% Parallel Branches After Analysis
+  Analyze --> Split1 & Split2
 
-```python
-import asyncio
+  subgraph Parallel Tasks
+    Split1[Generate Report] --> Merge
+    Split2[Update Dashboard] --> Merge
+  end
 
-async def chat(agent, user_query):
-    auth_context = ...  # your auth context
-    response = await agent.run(query=user_query, auth=auth_context)
-    print(response["response"])
+  Merge --> Decision2{Is More Input Needed?}
+  Decision2 -->|Yes| WaitMore[Wait for More Input]
+  WaitMore --> Validate
+  Decision2 -->|No| End([End Process])
+
+  %% Style and Class Definitions
+  classDef decision fill:#f9f,stroke:#333,stroke-width:2px;
+  class ProcessData,Decision2 decision;
 
-asyncio.run(chat(agent, "What is reinforcement learning?"))
 ```
 
-> <Tip>
-> The agent requires an authenticated user context (`auth`) to respect data access control.
-> 
-### Step 4: Execute Conversational Queries
+<strong>
+<p>Note: Mermaid should be inside a code block with type "mermaid"</p>
+</strong>
 
-With the agent configured and interface in place, you can ask questions like:
+```mermaid
+graph TD
 
-- "Summarize the key points in the document about AI."
-- "Show me diagrams related to reinforcement learning."
-- "What entities appear in the contract documents?"
+  %% Main Start
+  Start([Start Process]) --> Validate[Validate Input]
 
-The agent breaks these queries into tool calls behind the scenes and constructs rich, sourced responses.
+  %% Decision Point
+  Validate -->|Valid| ProcessData{Is Data Clean?}
+  Validate -->|Invalid| Error[Show Error Message]
 
----
+  %% Clean Data Branch
+  ProcessData -->|Yes| Clean[Clean Data]
+  Clean --> Analyze[Analyze Data]
 
-## 5. How the Morphik Agent Works Behind the Scenes
+  %% Dirty Data Branch
+  ProcessData -->|No| Notify[Notify User]
+  Notify --> Wait[Wait for Input]
+  Wait --> Validate
 
-The Morphik Agent integrates several internal tools to answer user questions effectively:
+  %% Parallel Branches After Analysis
+  Analyze --> Split1 & Split2
 
-- **`retrieve_chunks`**: Finds the most relevant text and image fragments from indexed documents.
-- **`retrieve_document`**: Accesses full documents or metadata by ID.
-- **`document_analyzer`**: Extracts entities, facts, sentiment, and summaries.
-- **`knowledge_graph_query`**: Navigates entities and relationships in knowledge graphs.
-- **Other tools** like code execution and persistent memory saving.
+  subgraph Parallel Tasks
+    Split1[Generate Report] --> Merge
+    Split2[Update Dashboard] --> Merge
+  end
 
-The agent dynamically decides which APIs to invoke based on the query context.
+  Merge --> Decision2{Is More Input Needed?}
+  Decision2 -->|Yes| WaitMore[Wait for More Input]
+  WaitMore --> Validate
+  Decision2 -->|No| End([End Process])
 
----
+  %% Style and Class Definitions
+  classDef decision fill:#f9f,stroke:#333,stroke-width:2px;
+  class ProcessData,Decision2 decision;
 
-## 6. Best Practices & Tips
+```
 
-- **Scope Your Queries**: Use filters like folder name or user ID to limit results and speed up responses.
-- **Use Multi-Turn Conversations**: Provide context from earlier messages to get more precise answers.
-- **Attribute Your Sources**: The agent returns source references for transparent answers.
-- **Monitor Token Limits**: Be mindful of model token constraints; truncate or segment documents if needed.
-- **Keep Your Documents Up to Date**: Re-ingest changed documents so retrieval returns current info.
+### Accordion
 
----
+```mdx
+<AccordionGroup>
+  <Accordion title="First Section" icon="DocumentIcon">
+    This is the content of the first accordion section.
+  </Accordion>
+  <Accordion title="Second Section" icon="CodeBracketIcon">
+    This is the content of the second accordion section.
+  </Accordion>
+</AccordionGroup>
+```
 
-## 7. Troubleshooting Common Issues
-
-<AccordionGroup title="Troubleshooting Conversational AI">
-<Accordion title="Agent Returns No or Irrelevant Results">
-- Verify your documents are indexed and visible to your user.
-- Check query filters and ensure they match existing document metadata.
-- Increase the number of chunks retrieved to widen the search scope.
-</Accordion>
-<Accordion title="Agent Fails or Crashes During Execution">
-- Confirm your Morphik service is running with adequate resources.
-- Check logs for errors related to tool invocation or model loading.
-- Validate your authentication token or context is correct.
-- Check model supported in your configuration (e.g. GPT-4).
-</Accordion>
-<Accordion title="Sources or Citations Are Missing in Responses">
-- Ensure your documents contain proper metadata with chunks.
-- Confirm the agent is using the correct source map.
-- Verify that retrieval calls return source IDs.
-</Accordion>
+<AccordionGroup>
+  <Accordion title="First Section" icon="DocumentIcon">
+    This is the content of the first accordion section.
+  </Accordion>
+  <Accordion title="Second Section" icon="CodeBracketIcon">
+    This is the content of the second accordion section.
+  </Accordion>
 </AccordionGroup>
 
----
+### Callouts
 
-## 8. Example: Interactive Chat with Morphik Console
+```mdx
+<Note>
+  This is a note callout with important information.
+</Note>
+```
 
-1. Open the Morphik Console in your browser.
-2. Navigate to the 'Chat' tab.
-3. Enter the query:
+<Note>
+  This is a note callout with important information.
+</Note>
 
-```text
-What does the document say about reinforcement learning?
+```mdx
+<Warning>
+  This is a warning callout for critical information.
+</Warning>
 ```
 
-4. The chat will return a detailed answer with markdown formatting and source attributions.
-5. Explore linked entities or images directly within the chat where available.
+<Warning>
+  This is a warning callout for critical information.
+</Warning>
 
----
+```mdx
+<Info>
+  This is an info callout for general information.
+</Info>
+```
 
-## 9. Example: Python SDK Conversational Query
+<Info>
+  This is an info callout for general information.
+</Info>
 
-```python
-from morphik import Morphik
+```mdx
+<Tip>
+  This is a tip callout for helpful suggestions.
+</Tip>
+```
 
-morphik = Morphik("morphik://user:token@api.morphik.ai")
+<Tip>
+  This is a tip callout for helpful suggestions.
+</Tip>
 
-response = morphik.query("Explain the advantage of Retrieval Augmented Generation.")
-print(response.completion)
+```mdx
+<Check>
+  This is a check callout for completed items.
+</Check>
 ```
 
-This sends a natural language query routed to the Morphik Agent that returns composed answers referencing documents.
+<Check>
+  This is a check callout for completed items.
+</Check>
+
+
+<br />
+
+### Cards
+```mdx
+<CardGroup cols={2}>
+  <Card 
+    title="Example Card" 
+    description="This is an example card component with an icon and title."
+    icon="FileText"
+    href="#"
+  />
+  <Card 
+    title="Another Card" 
+    description="This is another example card with different content."
+    icon="Code"
+    href="#"
+  />
+</CardGroup>
+```
 
----
+<CardGroup cols={2}>
+  <Card 
+    title="Example Card" 
+    description="This is an example card component with an icon and title."
+    icon="FileText"
+    href="#"
+  />
+  <Card 
+    title="Another Card" 
+    description="This is another example card with different content."
+    icon="Code"
+    href="#"
+  />
+</CardGroup>
+
+<br />
+
+### Expandable
+
+```mdx
+<Expandable title="Click to Expand">
+  This is an expandable section that can be toggled.
+</Expandable>
+```
 
-## 10. Next Steps & Further Reading
+<Expandable title="Click to Expand">
+  This is an expandable section that can be toggled.
+</Expandable>
 
-- Explore [Multimodal Search & Retrieval guide](/guides/core-workflows/multimodal-search) to understand how retrieval integrates with chat.
-- Learn about [Building Knowledge Graphs](/guides/knowledge-graphs/build-knowledge-graph) to enhance entity-level understanding.
-- Review [Cache-Augmented Generation](/guides/integrations-and-caching/cache-augmentation) to accelerate response times via document caching.
-- Deep dive into Morphik Console features in [Using the Morphik Console](/getting-started/first-steps-and-validation/using-the-morphik-console).
-- Consult the [Agent code & tools description](/core/agent.py) for advanced customization.
+### Source
 
----
+```mdx
+<Source url="https://github.com/clidey/dory" paths={[
+  { path: "src/mdx/source.tsx", range: "1-46" },
+  { path: "docs/features.mdx", range: "318-322" },
+]} />
+```
 
-## 11. Summary
+<Source url="https://github.com/clidey/dory" paths={[
+  { path: "src/mdx/source.tsx", range: "1-46" },
+  { path: "docs/features.mdx", range: "318-322" },
+]} />
 
-By following this guide, you will have enabled a robust conversational AI interface backed by Morphik’s multimodal document understanding and knowledge graph capabilities. This conversational workflow transforms your static documents into interactive assistants that can support research, customer support, and knowledge discovery efficiently.
+<br />
+<br />
+<br />
 
----
 
-## References and Links
+## Special Components
 
-- [Morphik Console Guide](https://morphik.ai/docs/getting-started/first-steps-and-validation/using-the-morphik-console)
-- [Morphik Python SDK](https://morphik.ai/docs/sdks/python/README)
-- [Multimodal Search Guide](https://morphik.ai/docs/guides/core-workflows/multimodal-search)
-- [Knowledge Graph Guide](https://morphik.ai/docs/guides/knowledge-graphs/build-knowledge-graph)
-- [Cache Augmented Generation Guide](https://morphik.ai/docs/guides/integrations-and-caching/cache-augmentation)
-- [Morphik Agent Source Code](https://github.com/morphik-org/morphik-core/blob/main/core/agent.py)
+### Grids
 
-<Tip>
-Engage with the Morphik Discord community for live support and tips on using conversational AI effectively.
-</Tip>
+#### Rows
+```mdx
+<Row cols={2}>
+  <Icon icon="FileText" />
+  <Icon icon="CheckCircle" />
+</Row>
+```
+
+<Row cols={2}>
+  <Icon icon="FileText" />
+  <Icon icon="CheckCircle" />
+</Row>
+
+<br />
+
+#### Columns
+
+```mdx
+<Col>
+  <Icon icon="FileText" />
+  <Icon icon="FileText" />
+</Col>
+```
+
+<Col>
+  <Icon icon="FileText" />
+  <Icon icon="FileText" />
+</Col>
+
+<br />
+<br />
+<br />
+
+### Latex
+
+```mdx
+<Latex>
+E = mc^2
+</Latex>
+```
+
+<Latex>
+E = mc^2
+</Latex>
+
+<br />
+<br />
+<br />
+
+### Tables
+
+```mdx
+| Property | Description                           |
+| -------- | ------------------------------------- |
+| Name     | Full name of user                     |
+| Age      | Reported age                          |
+| Joined   | Whether the user joined the community |
+```
+
+| Property | Description                           |
+| -------- | ------------------------------------- |
+| Name     | Full name of user                     |
+| Age      | Reported age                          |
+| Joined   | Whether the user joined the community |
+
+
+### Steps
+
+```mdx
+<Steps>
+  <Step title="First Step">
+  This is the first step in the process.
+  </Step>
+  <Step title="Second Step">
+  This is the second step in the process.
+  </Step>
+</Steps>
+```
+
+<Steps>
+  <Step title="First Step">
+  This is the first step in the process.
+  </Step>
+  <Step title="Second Step">
+  This is the second step in the process.
+  </Step>
+</Steps>
+
+### Icons
+
+```mdx
+<Col rows={2}>
+  <Icon icon="Code" />
+  <Icon icon="FileText" />
+  <Icon icon="CheckCircle" />
+</Col>
+```
+
+<Row cols={3}>
+<Icon icon="Code" />
+<Icon icon="FileText" />
+<Icon icon="CheckCircle" />
+</Row>

package/k8s/Dockerfile

@@ -7,8 +7,7 @@ RUN apk add --no-cache git
 
 COPY ./k8s/config/nginx-default.conf /app/k8s/config/nginx-default.conf
 
-# Install dory globally
-RUN npm install -g @clidey/dory@latest
+RUN npm install -g @clidey/dory@0.15.0
 EXPOSE 3000
 
 CMD ["dory", "preview"]

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@clidey/dory",
   "private": false,
-  "version": "0.14.0",
+  "version": "0.16.0",
   "type": "module",
   "description": "A CLI tool for building and previewing documentation sites",
   "keywords": [