Add cookbooks

CONTRIBUTING.md

@@ -33,7 +33,8 @@ Please run this script before submitting a pull request.
 2. Create a new directory in `phi/vectordb` with the name of the vector database.
 3. Implement the `VectorDb` interface in `phi/vectordb/<your_db>/<your_db>.py`.
 4. Import your `VectorDb` implementation in `phi/vectordb/<your_db>/__init__.py`.
-5. Add a recipe for using your `VectorDb` in `cookbook/<your_db>/<your_db>.py`.
+5. Add a recipe for using your `VectorDb` in `cookbook/<your_db>/assistant.py`.
+6. Format and validate your code by running `./scripts/format.sh`.
 6. Submit a pull request.
 
 ## 📚 Resources

cookbook/auto/README.md

@@ -0,0 +1,25 @@
+## Autonomous Assistant
+
+1. Run pgvector
+
+```shell
+phi start cookbook/auto/resources.py -y
+```
+
+2. Install libraries
+
+```shell
+pip install -U pgvector pypdf psycopg sqlalchemy
+```
+
+3. Run RAG Assistant
+
+```shell
+python cookbook/auto/auto_assistant.py
+```
+
+4. Turn off pgvector
+
+```shell
+phi stop cookbook/auto/resources.py -y
+```

cookbook/auto/auto_assistant.py

@@ -0,0 +1,20 @@
+from phi.assistant import Assistant
+from phi.knowledge.pdf import PDFUrlKnowledgeBase
+from phi.vectordb.pgvector import PgVector
+
+from .resources import vector_db
+
+knowledge_base = PDFUrlKnowledgeBase(
+    urls=["https://www.family-action.org.uk/content/uploads/2019/07/meals-more-recipes.pdf"],
+    vector_db=PgVector(collection="recipes", db_url=vector_db.get_db_connection_local()),
+)
+knowledge_base.load(recreate=False)
+
+assistant = Assistant(
+    knowledge_base=knowledge_base,
+    use_tools=True,
+    show_tool_calls=True,
+)
+
+assistant.print_response("How do I make chicken tikka salad?")
+assistant.print_response("What was my last question?")

cookbook/auto/resources.py

@@ -0,0 +1,13 @@
+from phi.docker.app.postgres import PgVectorDb
+from phi.docker.resources import DockerResources
+
+# -*- PgVector running on port 5432:5432
+vector_db = PgVectorDb(
+    pg_user="ai",
+    pg_password="ai",
+    pg_database="ai",
+    debug_mode=True,
+)
+
+# -*- DockerResources
+dev_docker_resources = DockerResources(apps=[vector_db])

cookbook/data_assistant.py

@@ -0,0 +1,18 @@
+import json
+from phi.assistant.duckdb import DuckDbAssistant
+
+duckdb_assistant = DuckDbAssistant(
+    semantic_model=json.dumps(
+        {
+            "tables": [
+                {
+                    "name": "movies",
+                    "description": "Contains information about movies from IMDB.",
+                    "path": "https://phidata-public.s3.amazonaws.com/demo_data/IMDB-Movie-Data.csv",
+                }
+            ]
+        }
+    ),
+)
+
+duckdb_assistant.print_response("What is the average rating of movies? Show me the SQL.")

cookbook/movie_assistant.py

@@ -0,0 +1,23 @@
+from typing import List
+from pydantic import BaseModel, Field
+from rich.pretty import pprint
+from phi.assistant import Assistant
+
+
+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(
+    description="You help people write movie ideas.",
+    output_model=MovieScript,
+)
+
+pprint(movie_assistant.run("New York"))

cookbook/python_assistant.py

@@ -0,0 +1,15 @@
+from phi.assistant.python import PythonAssistant
+from phi.file.local.csv import CsvFile
+
+python_assistant = PythonAssistant(
+    files=[
+        CsvFile(
+            path="https://phidata-public.s3.amazonaws.com/demo_data/IMDB-Movie-Data.csv",
+            description="Contains information about movies from IMDB.",
+        )
+    ],
+    pip_install=True,
+    show_tool_calls=True,
+)
+
+python_assistant.print_response("What is the average rating of movies?")

cookbook/rag/README.md

@@ -0,0 +1,25 @@
+## RAG Assistant
+
+1. Run pgvector
+
+```shell
+phi start cookbook/rag/resources.py -y
+```
+
+2. Install libraries
+
+```shell
+pip install -U pgvector pypdf psycopg sqlalchemy
+```
+
+3. Run RAG Assistant
+
+```shell
+python cookbook/rag/rag_assistant.py
+```
+
+4. Turn off pgvector
+
+```shell
+phi stop cookbook/rag/resources.py -y
+```

cookbook/rag/rag_assistant.py

@@ -0,0 +1,18 @@
+from phi.assistant import Assistant
+from phi.knowledge.pdf import PDFUrlKnowledgeBase
+from phi.vectordb.pgvector import PgVector
+
+from .resources import vector_db
+
+knowledge_base = PDFUrlKnowledgeBase(
+    urls=["https://www.family-action.org.uk/content/uploads/2019/07/meals-more-recipes.pdf"],
+    vector_db=PgVector(collection="recipes", db_url=vector_db.get_db_connection_local()),
+)
+knowledge_base.load(recreate=False)
+
+assistant = Assistant(
+    knowledge_base=knowledge_base,
+    add_references_to_prompt=True,
+)
+
+assistant.print_response("How do I make chicken tikka salad?")

cookbook/rag/resources.py

@@ -0,0 +1,13 @@
+from phi.docker.app.postgres import PgVectorDb
+from phi.docker.resources import DockerResources
+
+# -*- PgVector running on port 5432:5432
+vector_db = PgVectorDb(
+    pg_user="ai",
+    pg_password="ai",
+    pg_database="ai",
+    debug_mode=True,
+)
+
+# -*- DockerResources
+dev_docker_resources = DockerResources(apps=[vector_db])

cookbook/simple_assistant.py

@@ -0,0 +1,4 @@
+from phi.assistant import Assistant
+
+assistant = Assistant(description="You help people with their health and fitness goals.")
+assistant.print_response("Share a quick healthy breakfast recipe.")

cookbook/story_assistant.py

@@ -0,0 +1,31 @@
+from phi.llm.openai import OpenAIChat
+from phi.task.llm import LLMTask
+from phi.assistant import Assistant
+from pydantic import BaseModel, Field
+
+
+class StoryTheme(BaseModel):
+    setting: str = Field(
+        ...,
+        description="This is the context of the story. If not available, provide a random setting.",
+    )
+    genre: str = Field(..., description="This is the genre of the story. If not provided, select horror.")
+
+
+get_story_theme = LLMTask(
+    system_prompt="Generate a theme for a story.",
+    output_model=StoryTheme,
+    show_output=False,
+)
+
+write_story = LLMTask(
+    llm=OpenAIChat(model="gpt-4"),
+    system_prompt="Write a 2 sentence story for a given theme. It should be less than 30 words.",
+)
+
+give_story_a_name = LLMTask(
+    system_prompt="Give this story a 2 word name. Format output as `Name: {name}`. Don't surround with quotes.",
+)
+
+story_assistant = Assistant(tasks=[get_story_theme, write_story, give_story_a_name])
+story_assistant.cli_app(user="Theme")

cookbook/trending_on_hn.py

@@ -0,0 +1,33 @@
+import json
+import httpx
+
+from phi.assistant import Assistant
+
+
+def get_top_hackernews_stories(num_stories: int = 10) -> str:
+    """Use this function to get top stories from Hacker News.
+
+    Args:
+        num_stories (int): Number of stories to return. Defaults to 10.
+
+    Returns:
+        str: JSON string of top stories.
+    """
+
+    # Fetch top story IDs
+    response = httpx.get("https://hacker-news.firebaseio.com/v0/topstories.json")
+    story_ids = response.json()
+
+    # Fetch story details
+    stories = []
+    for story_id in story_ids[:num_stories]:
+        story_response = httpx.get(f"https://hacker-news.firebaseio.com/v0/item/{story_id}.json")
+        story = story_response.json()
+        if "text" in story:
+            story.pop("text", None)
+        stories.append(story)
+    return json.dumps(stories)
+
+
+assistant = Assistant(tools=[get_top_hackernews_stories], show_tool_calls=True)
+assistant.print_response("Summarize the top stories on hackernews?")

cookbook/vision.py

@@ -0,0 +1,34 @@
+from phi.assistant import Assistant
+from phi.llm.openai import OpenAIChat
+
+
+assistant = Assistant(llm=OpenAIChat(model="gpt-4-vision-preview"))
+
+# Single Image
+assistant.print_response(
+    [
+        {"type": "text", "text": "What's in this image, describe in 1 sentence"},
+        {
+            "type": "image_url",
+            "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
+        },
+    ]
+)
+
+# Multiple Images
+assistant.print_response(
+    [
+        {
+            "type": "text",
+            "text": "Is there any difference between these. Describe them in 1 sentence.",
+        },
+        {
+            "type": "image_url",
+            "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
+        },
+        {
+            "type": "image_url",
+            "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
+        },
+    ]
+)