> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Ollama Streamlit UI

> Create interactive chat interfaces with Ollama models using Streamlit

```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
flowchart LR
    In[Input] --> UI[("Streamlit UI")]
    VDB[(Vector DB)] --> Agent
    Ollama[("Ollama")] --> Agent
    UI --> Agent[("Knowledge Agent")]
    Agent --> |Query| VDB
    Agent --> Out[Output]
    Out --> UI
    
    style In fill:#8B0000,color:#fff
    style UI fill:#FF4B4B,color:#fff,shape:circle
    style Ollama fill:#4169E1,color:#fff,shape:circle
    style Agent fill:#2E8B57,color:#fff,shape:circle
    style VDB fill:#4169E1,color:#fff,shape:cylinder
    style Out fill:#8B0000,color:#fff
```

## Prerequisites

<Steps>
  <Step title="Install Package">
    Install required packages:

    ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    pip install "praisonaiagents[knowledge]" streamlit ollama
    ```

    <Note>
      streamlit for UI
      ollama for model hosting
      praisonaiagents\[knowledge] for RAG capabilities
    </Note>
  </Step>

  <Step title="Setup Model">
    Pull Ollama models:

    ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    # Large Language Model
    ollama pull deepseek-r1

    # Embedding Model
    ollama pull nomic-embed-text
    ```
  </Step>

  <Step title="Setup Environment">
    Configure environment:

    ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    export OPENAI_BASE_URL=http://localhost:11434/v1
    export OPENAI_API_KEY=fake-key
    ```
  </Step>

  <Step title="Create File">
    Create a new file called `app.py` and add the following code:
  </Step>

  <Step title="Run Application">
    Start the Streamlit application:

    ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
    streamlit run app.py
    ```
  </Step>
</Steps>

## Code

```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
import streamlit as st
from praisonaiagents import Agent

def init_agent():
    config = {
        "vector_store": {
            "provider": "chroma",
            "config": {
                "collection_name": "praison",
                "path": ".praison"
            }
        },
        "llm": {
            "provider": "ollama",
            "config": {
                "model": "deepseek-r1:latest",
                "temperature": 0,
                "max_tokens": 8000,
                "ollama_base_url": "http://localhost:11434",
            },
        },
        "embedder": {
            "provider": "ollama",
            "config": {
                "model": "nomic-embed-text:latest",
                "ollama_base_url": "http://localhost:11434",
                "embedding_dims": 1536
            },
        },
    }
    
    return Agent(
        name="Knowledge Agent",
        instructions="You answer questions based on the provided knowledge.",
        knowledge=["kag-research-paper.pdf"],
        memory={"embedder": config["embedder"]},
        llm="deepseek-r1"
    )

st.title("Knowledge Agent Chat")

if "agent" not in st.session_state:
    st.session_state.agent = init_agent()
    st.session_state.messages = []

if "messages" in st.session_state:
    for message in st.session_state.messages:
        with st.chat_message(message["role"]):
            st.markdown(message["content"])

prompt = st.chat_input("Ask a question...")

if prompt:
    st.session_state.messages.append({"role": "user", "content": prompt})
    with st.chat_message("user"):
        st.markdown(prompt)

    with st.chat_message("assistant"):
        response = st.session_state.agent.start(prompt)
        st.markdown(response)
        st.session_state.messages.append({"role": "assistant", "content": response}) 
```

## Features

<CardGroup cols={2}>
  <Card title="Interactive Chat" icon="comments">
    Real-time chat interface with message history.
  </Card>

  <Card title="Knowledge Base" icon="database">
    RAG capabilities with ChromaDB integration.
  </Card>

  <Card title="Model Integration" icon="server">
    Uses Ollama for local model hosting.
  </Card>

  <Card title="Session Management" icon="clock-rotate-left">
    Maintains chat history in session state.
  </Card>
</CardGroup>

<Note>
  Make sure your system meets the requirements for running models locally through Ollama.
</Note>