# Chat Completion

### **Introduction**

Modellake provides an advanced **chat completion** functionality that allows users to interact with various **LLM (Large Language Model) providers** such as **OpenAI (GPT-4), Gemini, DeepSeek, Claude, and Llama**. This enables seamless integration of multiple AI models into applications for different conversational and generative AI use cases.

### **Setting Up API Keys**

To use **chat\_complete**, you need to set API keys for different AI models.

#### **1. Setting API Keys in Terminal (Windows)**

```sh
shCopyEditset OPENAI_API_KEY=your_openai_key
set GOOGLE_API_KEY=your_gemini_key
set DEEPSEEK_API_KEY=your_deepseek_key
set GROQ_API_KEY=your_llama_key
set ANTROPHIC_API_KEY=your_claude_key
```

#### **2. Using a `.env` File**

```sh
shCopyEditOPENAI_API_KEY=your_openai_key
GOOGLE_API_KEY=your_gemini_key
DEEPSEEK_API_KEY=your_deepseek_key
GROQ_API_KEY=your_llama_key
ANTROPHIC_API_KEY=your_claude_key
```

***

### **Usage of `chat_complete()` in Modellake**

### **1. OpenAI (GPT-4) Chat Completion**

```python
import os
from groclake.modellake import Modellake

modellake = Modellake()

chat_completion_request = {
    "model_name": "gpt-4",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Which model are you using?"}
    ]
}

response = modellake.chat_complete(chat_completion_request)
print("Response:", response)
```

Response

```python
Response : {'answer': "As an artificial intelligence, I'm based on OpenAI's GPT-3 model.", 'input_tokens': 46, 'output_tokens': 19, 'total_tokens': 65}
```

### **2. Google Gemini Chat Completion**

```python
chat_completion_request = {
    "model_name": "gemini-1.5-flash",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Which model are you using?"}
    ]
}

response = modellake.chat_complete(chat_completion_request)
print("Response:", response)
```

Response

```python
Response : {'answer': "I'm currently running on the Gemini family of models.", 'input_tokens': 6, 'output_tokens': 13, 'total_tokens': 19}
```

### **3. DeepSeek Chat Completion**

```python
chat_completion_request = {
    "model_name": "deepseek/deepseek-r1:free",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Which model are you using?"}
    ]
}

response = modellake.chat_complete(chat_completion_request)
print("Response:", response)
```

Response

```python
Response : {'answer': "Hi! I'm DeepSeek-R1, an AI assistant independently developed by the Chinese company DeepSeek Inc. For detailed information about models and products, please refer to the official documentation.", 'input_tokens': 18, 'output_tokens': 81, 'total_tokens': 99}
```

### **4. Claude Chat Completion**

```python
chat_completion_request = {
    "model_name": "claude-3-5-sonnet-20241022",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Which model are you using?"}
    ]
}

response = modellake.chat_complete(chat_completion_request)
print("Response:", response)
```

Response

```python
Response : {'answer': "I am Claude, an AI assistant created by Anthropic. I aim to be direct and honest about what I am. I don't pretend to be human.", 'input_tokens': 13, 'output_tokens': 37, 'total_tokens': 50}
```

#### **5. Llama Chat Completion (via Groq API)**

**Getting a Groq API Key**

To use **Llama models**, obtain an API key from **Groq**:

1. Sign up on the **Groq Developer Console**.
2. Navigate to **API Keys** and generate a new key.
3. Securely store and use the key in your application.

**Llama Chat Example**

```python
chat_completion_request = {
    "model_name": "llama3-70b-8192",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Which model are you using?"}
    ]
}

response = modellake.chat_complete(chat_completion_request)
print("Response:", response)
```

Response

```python
Response : {'answer': "I'm an AI assistant, and I'm using a highly advanced language model to understand and respond to your queries. My model is based on a transformer architecture, specifically a variant of the BERT (Bidirectional Encoder Representations from Transformers) model.\n\nMy model has been fine-tuned on a massive dataset of text from various sources, including but not limited to books, articles, research papers, and online conversations. This fine-tuning enables me to understand and respond to a wide range of questions and topics, from simple queries to more complex conversations.\n\nThat being said, my model is constantly learning and improving, so I become more accurate and informative with each interaction. I'm here to help you with any questions or topics you'd like to discuss!", 'input_tokens': 27, 'output_tokens': 150, 'total_tokens': 177}
```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.groclake.ai/lakes/data-and-model-management/modellake/chat-completion.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.