intro to gen ai, llm

code/llm/llama3.1_local_rag/llama3.1_local_rag.py

@@ -0,0 +1,52 @@
+import ollama
+import streamlit as st
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders import WebBaseLoader
+from langchain_community.embeddings import OllamaEmbeddings
+from langchain_community.vectorstores import Chroma
+
+st.title("Chat with Webpage 🌐")
+st.caption("This app allows you to chat with a webpage using local llama3 and RAG")
+
+# Get the webpage URL from the user
+webpage_url = st.text_input("Enter Webpage URL", type="default")
+
+if webpage_url:
+    # 1. Load the data
+    loader = WebBaseLoader(webpage_url)
+    docs = loader.load()
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=10)
+    splits = text_splitter.split_documents(docs)
+
+    # 2. Create Ollama embeddings and vector store
+    embeddings = OllamaEmbeddings(model="llama3.1")
+    vectorstore = Chroma.from_documents(documents=splits, embedding=embeddings)
+
+    # 3. Call Ollama Llama3 model
+    def ollama_llm(question, context):
+        formatted_prompt = f"Question: {question}\n\nContext: {context}"
+        response = ollama.chat(
+            model="llama3.1", messages=[{"role": "user", "content": formatted_prompt}]
+        )
+        return response["message"]["content"]
+
+    # 4. RAG Setup
+    retriever = vectorstore.as_retriever()
+
+    def combine_docs(docs):
+        return "\n\n".join(doc.page_content for doc in docs)
+
+    def rag_chain(question):
+        retrieved_docs = retriever.invoke(question)
+        formatted_context = combine_docs(retrieved_docs)
+        return ollama_llm(question, formatted_context)
+
+    st.success(f"Loaded {webpage_url} successfully!")
+
+    # Ask a question about the webpage
+    prompt = st.text_input("Ask any question about the webpage")
+
+    # Chat with the webpage
+    if prompt:
+        result = rag_chain(prompt)
+        st.write(result)

code/llm/ollama/assistant.py

@@ -0,0 +1,11 @@
+from phi.assistant import Assistant
+from phi.llm.ollama import Ollama
+from rich.pretty import pprint
+
+assistant = Assistant(
+    llm=Ollama(model="llama3.1"),
+    description="You help people with their health and fitness goals.",
+)
+assistant.print_response("Share a quick healthy breakfast recipe.", markdown=True)
+print("\n-*- Metrics:")
+pprint(assistant.llm.metrics)  # type: ignore

code/llm/ollama/embedding.py

@@ -0,0 +1,7 @@
+from phi.embedder.ollama import OllamaEmbedder
+
+embedder = OllamaEmbedder(model="llama3.1")
+embeddings = embedder.get_embedding("Embed me")
+
+print(f"Embeddings: {embeddings}")
+print(f"Dimensions: {len(embeddings)}")

code/llm/openai/assistant.py

@@ -0,0 +1,10 @@
+from phi.assistant import Assistant
+from phi.llm.openai import OpenAIChat
+from phi.tools.duckduckgo import DuckDuckGo
+
+assistant = Assistant(
+    llm=OpenAIChat(model="gpt-4o", max_tokens=500, temperature=0.3),
+    tools=[DuckDuckGo()],
+    show_tool_calls=True,
+)
+assistant.print_response("Whats happening in Indonesia?", markdown=True)

code/llm/openrouter/assistant.py

@@ -0,0 +1,10 @@
+from phi.assistant import Assistant
+from phi.llm.openrouter import OpenRouter
+
+assistant = Assistant(
+    llm=OpenRouter(model="mistralai/mistral-7b-instruct:free"),
+    description="You help people with their health and fitness goals.",
+)
+assistant.print_response(
+    "Share a 2 sentence quick and healthy breakfast recipe.", markdown=True
+)

code/llm/openrouter/pydantic_output.py

@@ -0,0 +1,34 @@
+from typing import List
+
+from phi.assistant import Assistant
+from phi.llm.openrouter import OpenRouter
+from pydantic import BaseModel, Field
+from rich.pretty import pprint
+
+
+class MovieScript(BaseModel):
+    setting: str = Field(
+        ..., description="Provide a nice setting for a blockbuster movie."
+    )
+    ending: str = Field(
+        ...,
+        description="Ending of the movie. If not available, provide a happy ending.",
+    )
+    genre: str = Field(
+        ...,
+        description="Genre of the movie. If not available, select action, thriller or romantic comedy.",
+    )
+    name: str = Field(..., description="Give a name to this movie")
+    characters: List[str] = Field(..., description="Name of characters for this movie.")
+    storyline: str = Field(
+        ..., description="3 sentence storyline for the movie. Make it exciting!"
+    )
+
+
+movie_assistant = Assistant(
+    llm=OpenRouter(model="mistralai/mistral-7b-instruct:free"),
+    description="You help people write movie ideas.",
+    output_model=MovieScript,
+)
+
+pprint(movie_assistant.run("New York"))

docs/_toc.yml

@@ -113,9 +113,11 @@ parts:
       - file: deep_learning/keras_tuner
       - file: deep_learning/transfer_learning
 
-  - caption: LLM
+  - caption: Generative AI
     chapters:
-      - file: llm/intro_to_llm
+      - file: gen_ai/intro_to_gen_ai
+      - file: gen_ai/intro_to_llm
+      - file: gen_ai/local_llms
 
   - caption: Reference
     chapters: