Alchemyst AI

https://getalchemystai.com/docs
Admin
Alchemyst AI is an AI-native context and memory layer that enables developers to store, index, and...
Tokens:86,621
Snippets:801
Trust Score:7.4
Update:1 month ago
Show doc for...
Tokens:
Raw
### Initialize Zendocs Project

Source: https://getalchemystai.com/docs/example-projects/team/zendocs

Commands to clone the repository, install dependencies, configure environment variables, and start the development server.

```bash
git clone https://github.com/Alchemyst-ai/zendocs.git
cd zendocs
npm install
cp .env.example .env
npm run dev   # app starts at http://localhost:4163
```

--------------------------------

### Initialize SyllabAI Project

Source: https://getalchemystai.com/docs/example-projects/team/syllabai

Commands to clone the repository, install dependencies, configure environment variables, and start the development server.

```bash
git clone https://github.com/Alchemyst-ai/SyllabAI.git
cd SyllabAI
npm install       # or: pnpm install
cp .env.example .env
npm run dev       # app starts at http://localhost:3000 (default)
```

--------------------------------

### Run and Deploy SyllabAI

Source: https://getalchemystai.com/docs/example-projects/team/syllabai

Commands for installing dependencies, starting the development server, and building for production.

```bash
npm install
npm run dev       # development server
npm run build
npm run start     # production
```

--------------------------------

### Initialize and Quickstart

Source: https://getalchemystai.com/docs/integrations/sdk/typescript-sdk

Basic client initialization and retrieval of context.

```ts
import AlchemystAI from '@alchemystai/sdk';

const client = new AlchemystAI({
    apiKey: process.env.ALCHEMYST_AI_API_KEY,
});

async function main() {
  const res = await client.v1.context.view.retrieve();
  console.log(res);
}

main().catch(console.error);
```

--------------------------------

### Install Mintlify CLI

Source: https://getalchemystai.com/docs/contribution/contributing

Global installation of the Mintlify CLI tool required for local development.

```bash
npm i -g mint
```

--------------------------------

### Local Installation for Testing

Source: https://getalchemystai.com/docs/integrations/third-party/pi

Manual installation by cloning the repository into the Pi extensions directory for development or testing purposes.

```bash
git clone https://github.com/AlchemystAI/pi-alchemyst ~/.pi/agent/extensions/pi-alchemyst
```

--------------------------------

### Install Project Dependencies

Source: https://getalchemystai.com/docs/example-projects/community/b2b-newsletter-writer

Install the required packages based on your chosen runtime environment.

```bash
pip install -r requirements.txt
```

```bash
npm install
```

--------------------------------

### Install Required Packages

Source: https://getalchemystai.com/docs/integrations/third-party/agnoagi

Install the necessary libraries for AgnoAGI, Alchemyst AI, and the Anthropic provider.

```bash
pip install agno alchemystai anthropic
```

--------------------------------

### Install LiveKit Plugin

Source: https://getalchemystai.com/docs/integrations/third-party/livekit

Install the core plugin package via npm.

```bash
npm install livekit-plugin-alchemyst
```

--------------------------------

### PostgreSQL Connection String Examples

Source: https://getalchemystai.com/docs/integrations/data-sources/databases/Postgresql

Examples of connection strings for local, AWS RDS, and Google Cloud SQL environments.

```text
postgresql://myuser:mypassword@localhost:5432/mydb
```

```text
postgresql://admin:password@mydb.abc123.us-east-1.rds.amazonaws.com:5432/production
```

```text
postgresql://user:password@/database?host=/cloudsql/project:region:instance
```

--------------------------------

### Install Dependencies

Source: https://getalchemystai.com/docs/example-projects/team/cli-chatbot

Install the necessary SDKs and environment variable management package via npm.

```bash
npm install @alchemystai/sdk @google/generative-ai dotenv
```

--------------------------------

### Install the SDK

Source: https://getalchemystai.com/docs/integrations/sdk/typescript-sdk

Commands to install the Alchemyst SDK using various package managers.

```bash
npm install @alchemystai/sdk
```

```bash
yarn add @alchemystai/sdk
```

```bash
pnpm add @alchemystai/sdk
```

```bash
bun add @alchemystai/sdk
```

--------------------------------

### Start Development Server

Source: https://getalchemystai.com/docs/contribution/contributing

Commands to enter the documentation directory and launch the local preview server.

```bash
cd developer-docs
mint dev
```

--------------------------------

### Install dependencies

Source: https://getalchemystai.com/docs/example-projects/community/company_research

Install the required Python packages listed in the requirements file.

```bash
pip install -r requirements.txt
```

--------------------------------

### Start Development Server

Source: https://getalchemystai.com/docs/example-projects/community/prompt-evaluator

Launch the local development server to view the application at http://localhost:3000.

```bash
npm run dev
# or
yarn dev
# or
pnpm dev
# or
bun dev
```

--------------------------------

### Run the application

Source: https://getalchemystai.com/docs/example-projects/community/company_research

Launch the Streamlit web interface to start the research agent.

```bash
streamlit run app.py
```

--------------------------------

### Install OpenCode Plugin

Source: https://getalchemystai.com/docs/integrations/third-party/opencode-plugin

Install the required npm package for the OpenCode plugin.

```bash
npm install opencode-alchemyst-context
```

--------------------------------

### Install Peer Dependencies

Source: https://getalchemystai.com/docs/integrations/third-party/livekit

Install required peer dependencies for the plugin.

```bash
npm install @livekit/agents zod
```

--------------------------------

### Install Pi Alchemyst via Git

Source: https://getalchemystai.com/docs/integrations/third-party/pi

Recommended method for installing the integration directly from the GitHub repository.

```bash
pi install git:github.com/AlchemystAI/pi-alchemyst
```

--------------------------------

### Start Docker Service

Source: https://getalchemystai.com/docs/mcps/claude-desktop

Command to initiate the Docker service when it fails to start or lacks privileges.

```shell
net start com.docker.service
```

--------------------------------

### Complete Working Example

Source: https://getalchemystai.com/docs/getting-started/quickstart

A full implementation demonstrating document storage, context searching, and LLM response generation.

```typescript
import AlchemystAI from '@alchemystai/sdk';
import OpenAI from 'openai';

const alchemyst = new AlchemystAI({
  apiKey: process.env.ALCHEMYST_AI_API_KEY,
});

const openai = new OpenAI();

async function main() {
  // 1. Store document
  await alchemyst.v1.context.add({
    documents: [{
      content: "Our refund policy: We offer a 30-day money back guarantee. Contact support@example.com to request a refund."
    }],
    context_type: 'resource',
    source: 'docs',
    scope: 'internal'
  });
  console.log("✅ Document stored");

  // 2. Search for context
  const userQuestion = "What's your refund policy?";
  const { contexts } = await alchemyst.v1.context.search({
    query: userQuestion,
    similarity_threshold: 0.7,
    scope: 'internal'
  });
  console.log(`Found ${contexts?.length} relevant chunks`);

  // 3. Generate answer with context
  const prompt = contexts?.length
    ? `Context:
${contexts.map(c => c.content).join('

')}

Question: ${userQuestion}`
    : userQuestion;

  const response = await openai.chat.completions.create({
    model: "gpt-4",
    messages: [{ role: "user", content: prompt }]
  });

  console.log("AI Response:", response.choices[0].message.content);
}

main();
```

```text
✅ Document stored
Found 1 relevant chunks
AI Response: We offer a 30-day money back guarantee. To request a refund, contact support@example.com.
```

```python
import os
from alchemyst_ai import AlchemystAI
import openai

alchemyst = AlchemystAI(api_key=os.environ.get("ALCHEMYST_AI_API_KEY"))

def main():
    # 1. Store document
    alchemyst.v1.context.add(
        documents=[{
            "content": "Our refund policy: We offer a 30-day money back guarantee. Contact support@example.com to request a refund."
        }],
        context_type="resource",
        source="docs",
        scope="internal"
    )
    print("✅ Document stored")

    # 2. Search for context
    user_question = "What's your refund policy?"
    result = alchemyst.v1.context.search(
        query=user_question,
        similarity_threshold=0.7,
        scope="internal"
    )

    contexts = result.contexts or []
    print(f"Found {len(contexts)} relevant chunks")

    # 3. Generate answer with context
    if contexts:
        context_text = "

".join([ctx.content for ctx in contexts])
        prompt = f"Context:
{context_text}

Question: {user_question}"
    else:
        prompt = user_question

    response = openai.chat.completions.create(
        model="gpt-4",
        messages=[{"role": "user", "content": prompt}]
    )

    print("AI Response:", response.choices[0].message.content)

if __name__ == "__main__":
    main()
```

```text
✅ Document stored
Found 1 relevant chunks
AI Response: We offer a 30-day money back guarantee. To request a refund, contact support@example.com.
```

--------------------------------

### Install Alchemyst AI SDK

Source: https://getalchemystai.com/docs

Install the required SDK package for your specific development environment.

```javascript
npm install @alchemystai/sdk
```

```python
pip install alchemystai
```

--------------------------------

### Install aiohttp for Async Performance

Source: https://getalchemystai.com/docs/integrations/sdk/python-sdk

Installs the necessary dependency to enable aiohttp as the HTTP backend for the async client.

```sh
# install from PyPI
pip install alchemystai[aiohttp]
```

--------------------------------

### MongoDB Connection String Examples

Source: https://getalchemystai.com/docs/integrations/data-sources/databases

Common connection string configurations for different MongoDB deployment types.

```text
mongodb+srv://user:password@cluster0.abc123.mongodb.net/mydb?retryWrites=true&w=majority
```

```text
mongodb://admin:password@localhost:27017/database?authSource=admin
```

```text
mongodb://user:password@host1:27017,host2:27017,host3:27017/database?replicaSet=myReplicaSet
```

--------------------------------

### Verify Setup with TypeScript SDK

Source: https://getalchemystai.com/docs/getting-started/quickstart

Executes a full document storage, search, and cleanup cycle to validate the integration.

```typescript
// Test the complete flow
async function testSetup() {
  // 1. Store a test document
  console.log("Step 1: Storing test document...");
  await client.v1.context.add({
    documents: [{
      content: "Test document: The answer is 42",
      metadata: { file_name: "test.txt" }
    }],
    scope: 'internal'
  });
  
  // 2. Search for it
  console.log("Step 2: Searching for test document...");
  const { contexts } = await client.v1.context.search({
    query: "What is the answer?",
    scope: 'internal',
    similarity_threshold: 0.5
  });
  
  // 3. Verify results
  const found = contexts?.some(c => c.content.includes("42"));
  console.log("✅ Test passed:", found);
  
  // 4. Cleanup
  console.log("Step 3: Cleaning up...");
  await client.v1.context.delete({
    metadata: { fileName: "test.txt" }
  });
}

testSetup();
```

--------------------------------

### Install OpenClaw Plugin

Source: https://getalchemystai.com/docs/integrations/third-party/openclaw

Copy the plugin files to the required OpenClaw extensions directory.

```bash
cp -r /path/to/openclaw-alchemyst ~/.openclaw/extensions/alchemyst-memory
```

--------------------------------

### Install Pi Alchemyst via NPM

Source: https://getalchemystai.com/docs/integrations/third-party/pi

Alternative installation method using the npm package manager.

```bash
pi install npm:@alchemystai/pi
```

--------------------------------

### Install Project Dependencies

Source: https://getalchemystai.com/docs/example-projects/community/prompt-evaluator

Install required packages using your preferred Node.js package manager.

```bash
npm install
# or
yarn install
# or
pnpm install
```

--------------------------------

### Starter Template for Metadata

Source: https://getalchemystai.com/docs/advanced/usage-patterns

A recommended starting point for metadata structure, adhering to the 5-field rule for optimal performance.

```javascript
// Starter template - covers 90% of use cases
{
  groupName: ["domain", "category"],
  metadata: {
    id: "unique-identifier",        // For updates/deletes
    status: "active",                // For filtering
    lastModified: "2024-12-29",      // For freshness
    owner: "team-name",              // For access control
    priority: "high"                 // For ranking (optional)
  },
  content: "..." // Everything else goes here
}
```

--------------------------------

### Run Zendocs Locally

Source: https://getalchemystai.com/docs/example-projects/team/zendocs

Commands to install dependencies and manage the development or production build process.

```bash
npm install
npm run dev     # Start dev server
npm run build   # Production build
```

--------------------------------

### Perform Grounded Q&A

Source: https://getalchemystai.com/docs/integrations/third-party/opencode-plugin

Example query and steering prompt for the alchemyst_context_ask tool.

```text
query: "What's our policy on dependency versions?"
steeringPrompt: "answer in one sentence"
```

--------------------------------

### Install LLM provider dependencies

Source: https://getalchemystai.com/docs/integrations/third-party/langchain/python

Install additional dependencies for LLM providers and environment variable management.

```sh
pip install langchain-openai python-dotenv
```

--------------------------------

### Handle port conflicts

Source: https://getalchemystai.com/docs/contribution/contributing

Example output when the default port is occupied and the CLI selects an alternative.

```text
Port 3000 is already in use. Trying 3001 instead.
```

--------------------------------

### Verify Plugin Installation

Source: https://getalchemystai.com/docs/integrations/third-party/openclaw

Command to list plugins and verify the Alchemyst integration is active.

```bash
openclaw plugins list
```

--------------------------------

### Steer Request Examples

Source: https://getalchemystai.com/docs/api-reference/endpoint/api/v1/context/search/steer/post

Examples of JSON request bodies for the steer endpoint, including a basic request and one with metadata filters.

```json
{
  "query": "What did the customer ask about pricing for the Scale plan?",
  "similarity_threshold": 0.8,
  "minimum_similarity_threshold": 0.5,
  "scope": "internal"
}
```

```json
{
  "query": "What did the customer ask about pricing for the Scale plan?",
  "similarity_threshold": 0.8,
  "minimum_similarity_threshold": 0.5,
  "scope": "internal",
  "body_metadata": {
    "fileName": "support_thread_TCK-1234.txt",
    "groupName": [
      "support",
      "pricing"
    ],
    "lastModifiedAt": "2025-01-10T12:34:56.000Z"
  }
}
```

--------------------------------

### Verify search output

Source: https://getalchemystai.com/docs/getting-started/quickstart

Example of expected output when viewing stored documents.

```json
Total documents: 1
Documents: [{ id: "doc_123", content: "Our refund policy...", ... }]
```

--------------------------------

### Initialize Alchemyst Client

Source: https://getalchemystai.com/docs/getting-started/quickstart

Configure the client with your API key to start making requests.

```typescript
import AlchemystAI from '@alchemystai/sdk';

const client = new AlchemystAI({
  apiKey: process.env.ALCHEMYST_AI_API_KEY,
});
```

```python
import os
from alchemyst_ai import AlchemystAI

client = AlchemystAI(
  api_key=os.environ.get("ALCHEMYST_AI_API_KEY")
)
```

--------------------------------

### Verify Package Installation

Source: https://getalchemystai.com/docs/integrations/third-party/langchain/python

Check if the alchemyst package is installed in the current environment.

```bash
pip list | grep alchemyst
```

--------------------------------

### Install Alchemyst LangChain package

Source: https://getalchemystai.com/docs/integrations/third-party/langchain/python

Install the required package via pip.

```sh
pip install alchemyst-langchain
```

--------------------------------

### Implement a CLI-based QnA Agent with Memory

Source: https://getalchemystai.com/docs/integrations/third-party/agnoagi

This example demonstrates a complete CLI loop including conversation history tracking, memory searching via the Alchemyst client, and basic command handling.

```python
    def show_history(self):
        """Display conversation history"""
        if not self.conversation_history:
            print("\nNo conversation history yet.")
            return

        print("\n" + "=" * 60)
        print("CONVERSATION HISTORY")
        print("=" * 60)

        for i, msg in enumerate(self.conversation_history, 1):
            role = "You" if msg["role"] == "user" else "Agent"
            print(f"\n[{i}] {role}: {msg['content']}")

        print("\n" + "=" * 60)

    def search_memory(self, query: str):
        """Search through all saved memories"""
        try:
            results = self.alchemyst_client.v1.context.search(
                query=query,
                similarity_threshold=0.5,
                scope="internal",
                minimum_similarity_threshold=0.2,
                body_metadata=None,  # {"groupName": [self.context_group]},
            )

            print("🔍 Searching memory...")
            print(results.contexts)

            if results.contexts:
                print(f"\n🔍 Found {len(results.contexts)} relevant memories:")
                print("=" * 60)
                for i, result in enumerate(results.contexts[:5], 1):
                    content =  getattr(result, "content", "")
                    print(f"\n[{i}] {content}")
                print("\n" + "=" * 60)
            else:
                print("\n🔍 No relevant memories found.")
        except Exception as e:
            print(f"Error searching memory: {e}")


def print_welcome():
    """Print welcome message"""
    print("\n" + "=" * 60)
    print("       CLI QnA AGENT WITH MEMORY")
    print("       Powered by OpenAI + Alchemyst AI")
    print("=" * 60)
    print("\nCommands:")
    print("  - Type your question to get an answer")
    print("  - 'history' - Show conversation history")
    print("  - 'search <query>' - Search through saved memories")
    print("  - 'exit' or 'quit' - Exit the program")
    print("\n" + "=" * 60 + "\n")


def main():
    """Main CLI loop"""

    # Print welcome message
    print_welcome()

    # Initialize agent
    try:
        agent = QnAAgent()
    except Exception as e:
        print(f"\n❌ Failed to initialize agent: {e}")
        print("\nPlease ensure you have set the following environment variables:")
        print("  - OPENAI_API_KEY")
        print("  - ALCHEMYST_AI_API_KEY")
        return

    # Main interaction loop
    while True:
        try:
            # Get user input
            user_input = input("\n💬 You: ").strip()

            # Handle empty input
            if not user_input:
                continue

            # Handle exit commands
            if user_input.lower() in ["exit", "quit", "q"]:
                print("\n👋 Goodbye! Your conversation has been saved to memory.")
                break

            # Handle history command
            if user_input.lower() == "history":
                agent.show_history()
                continue

            # Handle search command
            if user_input.lower().startswith("search "):
                query = user_input[7:].strip()
                if query:
                    agent.search_memory(query)
                else:
                    print("\n⚠️  Please provide a search query: search <query>")
                continue

            # Process question
            print("\n🤖 Agent: ", end="", flush=True)
            answer = agent.ask(user_input)
            print(answer)

        except KeyboardInterrupt:
            print("\n\n👋 Goodbye! Your conversation has been saved to memory.")
            break
        except Exception as e:
            print(f"\n❌ Error: {e}")


if __name__ == "__main__":
    main()
```

--------------------------------

### Install Dependencies for Memory-Enabled Agents

Source: https://getalchemystai.com/docs/getting-started/quickstart-memory

Commands to install the necessary packages for TypeScript and Python projects.

```bash
npm install ai @alchemystai/aisdk
```

```bash
pip install alchemystai openai
```

--------------------------------

### CLI Interface and Initialization

Source: https://getalchemystai.com/docs/integrations/third-party/agnoagi

Functions for displaying the welcome message and initializing the agent with required environment variables.

```python
def print_welcome():
    """Print welcome message"""
    print("\n" + "=" * 60)
    print("       CLI Knowledge Agent WITH MEMORY")
    print("       Powered by OpenAI + Alchemyst AI")
    print("=" * 60)
    print("\nCommands:")
    print("  - Type your question to get an answer")
    print("  - 'history' - Show conversation history")
    print("  - 'search <query>' - Search through saved memories")
    print("  - 'addkb <text>' - Add text to knowledge base")
    print("  - 'exit' or 'quit' - Exit the program")
    print("\n" + "=" * 60 + "\n")


def main():
    """Main CLI loop"""

    print_welcome()

    try:
        agent = AlchemystKnowledgeAgent()
    except Exception as e:
        print(f"\n❌ Failed to initialize agent: {e}")
        print("\nPlease ensure you have set the following environment variables:")
        print("  - OPENAI_API_KEY")
        print("  - ALCHEMYST_AI_API_KEY")
        return
```

--------------------------------

### Clone the repository

Source: https://getalchemystai.com/docs/example-projects/community/company_research

Initial step to download the project source code and navigate to the directory.

```bash
git clone <repository-url>
cd company_research
```

--------------------------------

### Example Query Patterns

Source: https://getalchemystai.com/docs/integrations/data-sources/databases/Postgresql

Examples of how natural language queries are mapped to database filters and semantic searches.

```text
"Show me all high-priority support tickets from last month"
→ Filters: groupName includes "support_tickets", metadata.priority="high"

"Find customer payment issues"
→ Semantic search across content for payment-related problems

"What's the resolution pattern for login errors?"
→ Retrieves similar resolved tickets and identifies common solutions
```

--------------------------------

### Add context with nested parameters

Source: https://getalchemystai.com/docs/integrations/sdk/python-sdk

Demonstrates initializing the client and adding context using nested metadata parameters.

```python
from alchemyst_ai import AlchemystAI

client = AlchemystAI()

response = client.v1.context.add(
    metadata={},
)
print(response.metadata)
```

--------------------------------

### Install Alchemyst LangChain Package

Source: https://getalchemystai.com/docs/integrations/third-party/langchain/js

Commands to install the required package using various Node.js package managers.

```sh
npm i @alchemystai/langchain-js
```

```sh
yarn add @alchemystai/langchain-js
```

```sh
pnpm add @alchemystai/langchain-js
```

```sh
bun add @alchemystai/langchain-js
```

--------------------------------

### Configure Environment Variables

Source: https://getalchemystai.com/docs/example-projects/community/prompt-evaluator

Create a .env.local file in the project root to store necessary API keys.

```text
GOOGLE_API_KEY=your-google-generative-ai-key
ALCHEMYST_API_KEY=your-alchemystai-sdk-key
```

--------------------------------

### Set up an MCP Client with Vercel AI SDK

Source: https://getalchemystai.com/docs/integrations/third-party/aisdk

Initializes an MCP client using SSE transport and custom authentication headers.

```ts
import { experimental_createMCPClient as createMCPClient } from 'ai';

const mcpClient = await createMCPClient({
  transport: {
    type: 'sse',
    url: 'https://mcp.getalchemystai.com/sse',

    // Configure HTTP headers, e.g. for authentication
    headers: {
      Authorization: 'Bearer YOUR_ALCHEMYST_AI_API_KEY',
    },
  },
});
```

--------------------------------

### GET /api/docs/list

Source: https://getalchemystai.com/docs/example-projects/team/zendocs

Retrieves a list of all available documents.

```APIDOC
## GET /api/docs/list

### Description
List all documents stored in the system.

### Method
GET

### Endpoint
/api/docs/list
```

--------------------------------

### GET /api/v1/context/view

Source: https://getalchemystai.com/docs/api-reference/endpoint/api/v1/context/view/get

Retrieves the context information for the authenticated user.

```APIDOC
## GET /api/v1/context/view

### Description
Gets the context information for the authenticated user.

### Method
GET

### Endpoint
/api/v1/context/view

### Parameters
#### Query Parameters
- **file_name** (string) - Optional - Name of the file to retrieve context for
- **magic_key** (string) - Optional - Magic key for context retrieval

### Response
#### Success Response (200)
- **success** (boolean) - Indicates if the request was successful
- **contexts** (array) - List of context items

#### Response Example
{
  "success": true,
  "contexts": [
    {
      "content": "Customer asked about pricing for the Scale plan.",
      "metadata": {
        "fileName": "support_thread_TCK-1234.txt",
        "fileType": "text/plain",
        "groupName": ["support", "pricing"],
        "lastModified": "2025-01-10T12:34:56.000Z",
        "fileSize": 2048
      }
    }
  ]
}
```

--------------------------------

### Handle unauthorized error

Source: https://getalchemystai.com/docs/getting-started/quickstart

Example of a 401 unauthorized error response.

```json
{
  "error": "Invalid API key",
  "code": "UNAUTHORIZED",
  "status": 401
}
```

--------------------------------

### Complete Memory Integration Example

Source: https://getalchemystai.com/docs/getting-started/quickstart-memory

A full implementation showing initialization and usage of memory-enabled text generation across multiple sessions.

```typescript
import { generateText } from 'ai';
import { withAlchemyst } from '@alchemystai/aisdk';

const generateTextWithMemory = withAlchemyst(generateText, {
  apiKey: process.env.ALCHEMYST_AI_API_KEY,
});

async function main() {
  // Day 1: Learn preference
  const response1 = await generateTextWithMemory({
    model: "openai:gpt-4",
    prompt: "I love science fiction movies",
    userId: "bob",
    sessionId: "preferences"
  });
  console.log("AI:", response1.text);
  // Output: "Great! I'll remember you enjoy sci-fi films."

  // Day 2: Use preference
  const response2 = await generateTextWithMemory({
    model: "openai:gpt-4",
    prompt: "Recommend a movie",
    userId: "bob",
    sessionId: "movie_night"
  });
  console.log("AI:", response2.text);
  // Output: "How about Interstellar? You mentioned you love sci-fi."
}

main();
```

--------------------------------

### Initialize Alchemyst AI Client

Source: https://getalchemystai.com/docs/integrations/third-party/agnoagi

Sets up the Alchemyst AI client using an API key from environment variables.

```python
import os
from alchemystai import AlchemystAI

# Initialize Alchemyst AI client for memory management
alchemyst_client = AlchemystAI(
    api_key=os.getenv("ALCHEMYST_AI_API_KEY")
)
```

--------------------------------

### GET /api/docs/[docSlug]/chat/history

Source: https://getalchemystai.com/docs/example-projects/team/zendocs

Retrieves the chat history for a specific document.

```APIDOC
## GET /api/docs/[docSlug]/chat/history

### Description
Get the chat history associated with a specific document.

### Method
GET

### Endpoint
/api/docs/[docSlug]/chat/history

### Parameters
#### Path Parameters
- **docSlug** (string) - Required - The unique identifier for the document.
```

--------------------------------

### GET /api/docs/[docSlug]

Source: https://getalchemystai.com/docs/example-projects/team/zendocs

Retrieves the details of a specific document using its slug.

```APIDOC
## GET /api/docs/[docSlug]

### Description
Get a specific document by its unique slug.

### Method
GET

### Endpoint
/api/docs/[docSlug]

### Parameters
#### Path Parameters
- **docSlug** (string) - Required - The unique identifier for the document.
```

--------------------------------

### Complete Alchemyst-LangChain Integration Example

Source: https://getalchemystai.com/docs/integrations/third-party/langchain/python

Demonstrates initializing AlchemystMemory, configuring a LangChain ConversationChain, and persisting conversation context across messages.

```python
from dotenv import load_dotenv
import os
from langchain_openai import ChatOpenAI
from langchain.chains import ConversationChain
from alchemyst_langchain import AlchemystMemory
import uuid

load_dotenv()


def main():
    print("Alchemyst-LangChain Integration Demo")
    print("=" * 50)

    # Use a consistent session_id to continue previous conversations
    # or generate a new one for a fresh start
    session_id = str(uuid.uuid4())
    print(f"Session ID: {session_id}\n")

    # Initialize Alchemyst Memory
    memory = AlchemystMemory(
        api_key=os.getenv("ALCHEMYST_AI_API_KEY"),
        session_id=session_id
    )

    # Initialize your preferred LLM
    model = ChatOpenAI(
        model="gpt-4o-mini",
        temperature=0,
    )

    # Create conversation chain
    chain = ConversationChain(llm=model, memory=memory)

    # Test conversation with context persistence
    test_messages = [
        "Hi, my name is Alice and I'm from New York.",
        "I'm a software engineer working on AI applications.",
        "What do you remember about me?"
    ]

    for i, message in enumerate(test_messages, 1):
        print(f"[Message {i}] User: {message}")
        response = chain.invoke({"input": message})
        print(f"Assistant: {response.get('response', response)}\n")

    print("=" * 50)
    print(f"Session {session_id} completed!")
    print("Use the same session_id to continue this conversation later.")

    # Optional: Clear memory when done
    # memory.clear()


if __name__ == "__main__":
    main()
```

--------------------------------

### GET /api/v1/context/traces

Source: https://getalchemystai.com/docs/api-reference/endpoint/api/v1/context/traces/get

Retrieves a list of traces for the authenticated user within their organization.

```APIDOC
## GET /api/v1/context/traces

### Description
Returns paginated traces for the authenticated user within their organization.

### Method
GET

### Endpoint
/api/v1/context/traces

### Parameters
#### Query Parameters
- **page** (integer) - Optional - Page number for pagination (default: 1)
- **limit** (integer) - Optional - Number of traces per page (default: 10)

### Response
#### Success Response (200)
- **traces** (array) - List of trace objects
- **pagination** (object) - Pagination metadata

#### Response Example
{
  "traces": [
    {
      "_id": "trace_123",
      "userId": "user_123",
      "organizationId": "org_123",
      "type": "context.search",
      "data": {
        "query": "What did the customer ask about pricing for the Scale plan?",
        "source": "support-inbox",
        "fileName": "support_thread_TCK-1234.txt"
      },
      "createdAt": "2025-01-10T12:35:10.000Z",
      "updatedAt": "2025-01-10T12:35:10.000Z"
    }
  ],
  "pagination": {
    "page": 1,
    "limit": 10,
    "total": 1,
    "totalPages": 1,
    "hasNextPage": false,
    "hasPrevPage": false
  }
}
```

--------------------------------

### Clone the Repository

Source: https://getalchemystai.com/docs/contribution/contributing

Commands to clone the documentation repository and navigate into the directory.

```bash
git clone https://github.com/YOUR-USERNAME/docs.git
cd docs
```

--------------------------------

### Required Memory Parameters

Source: https://getalchemystai.com/docs/getting-started/quickstart-memory

Example of providing the mandatory userId and sessionId in a memory-enabled request.

```typescript
await generateTextWithMemory({
  model: "openai:gpt-4",
  prompt: "Hello",
  userId: "user_123",    // ✅ Required
  sessionId: "chat_456"  // ✅ Required
});
```

--------------------------------

### GET /api/v1/context/view/docs

Source: https://getalchemystai.com/docs/api-reference/endpoint/api/v1/context/view/docs/get

Fetches documents view for authenticated user with optional organization context.

```APIDOC
## GET /api/v1/context/view/docs

### Description
Fetches documents view for authenticated user with optional organization context.

### Method
GET

### Endpoint
/api/v1/context/view/docs

### Parameters
#### Query Parameters
- **magic_key** (string) - Optional - Optional magic key for special access or filtering

### Response
#### Success Response (200)
- **documents** (array) - List of documents
  - **fileName** (string) - Name of the file
  - **fileType** (string) - Type/MIME of the file
  - **groupName** (array) - Array of group names to which the file belongs
  - **lastModified** (string) - Last modified timestamp (ISO format)
  - **fileSize** (number) - Size of the file in bytes

#### Response Example
{
  "documents": [
    {
      "fileName": "support_thread_TCK-1234.txt",
      "fileType": "text/plain",
      "groupName": ["support", "pricing"],
      "lastModified": "2025-01-10T12:34:56.000Z",
      "fileSize": 2048
    }
  ]
}
```

--------------------------------

### Configure Environment Variables

Source: https://getalchemystai.com/docs/example-projects/team/syllabai

Required environment variables for connecting the frontend to the backend service.

```bash
NEXT_PUBLIC_BACKEND_URL=https://your-backend.example.com
NEXT_PUBLIC_API_KEY=your_api_key_here
# Optional: configure timeouts, storage endpoints, and dev ports
```
Tokens:
Raw