phidata

Phidata adds memory, knowledge and tools to LLMs

Why phidata

Problem: LLMs have limited context and cannot take actions.
Solution: Add memory, knowledge and tools.

• Memory: Enables LLMs to have long-term conversations by storing chat history in a database.
• Knowledge: Provides LLMs with business context by storing information in a vector database.
• Tools: Enable LLMs to take actions like pulling data from an API, sending emails or querying a database.

Memory & knowledge make LLMs smarter while tools make them autonomous.

How it works

• Step 1: Create an Assistant
• Step 2: Add Tools (functions), Knowledge (vectordb) and Storage (database)
• Step 3: Serve using Streamlit, FastApi or Django to build your AI application

Installation

pip install -U phidata

Example: Assistant that can search the web

Create a file assistant.py

fromphi.assistantimportAssistantfromphi.tools.duckduckgoimportDuckDuckGoassistant=Assistant(tools=[DuckDuckGo()], show_tool_calls=True)
assistant.print_response("Whats happening in France?", markdown=True)

Install libraries

pip install openai duckduckgo-search

Export your OPENAI_API_KEY

export OPENAI_API_KEY=sk-xxxx

Run the Assistant and let it search the web using DuckDuckGo

python assistant.py

Next Steps

1. Read the basics to learn more about phidata.
2. Read about Assistants and how to customize them.
3. Checkout the cookbook for in-depth examples and code.

Documentation

• You can find the full documentation here
• You can also chat with us on discord

Demos

Checkout the following AI Applications built using phidata:

• PDF AI that summarizes and answers questions from PDFs.
• ArXiv AI that answers questions about ArXiv papers using the ArXiv API.
• HackerNews AI summarize stories, users and shares what's new on HackerNews.

More Examples

Assistant that can write and run python code

Show details

The PythonAssistant can achieve tasks by writing and running python code.

• Create a file python_assistant.py

fromphi.assistant.pythonimportPythonAssistantfromphi.file.local.csvimportCsvFilepython_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?", markdown=True)

• Install pandas and run the python_assistant.py

pip install pandas
python python_assistant.py

Assistant that can analyze data using SQL

Show details

The DuckDbAssistant can perform data analysis using SQL.

• Create a file data_assistant.py

importjsonfromphi.assistant.duckdbimportDuckDbAssistantduckdb_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.", markdown=True)

• Install duckdb and run the data_assistant.py file

pip install duckdb
python data_assistant.py

Assistant that can generate pydantic models

Show details

One of our favorite LLM features is generating structured data (i.e. a pydantic model) from text. Use this feature to extract features, generate movie scripts, produce fake data etc.

Let's create an Movie Assistant to write a MovieScript for us.

• Create a file movie_assistant.py

fromtypingimportListfrompydanticimportBaseModel, Fieldfromrich.prettyimportpprintfromphi.assistantimportAssistantclassMovieScript(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 write movie scripts.",
output_model=MovieScript,
)
pprint(movie_assistant.run("New York"))

• Run the movie_assistant.py file

python movie_assistant.py

• The output is an object of the MovieScript class, here's how it looks:

MovieScript(
│ setting='A bustling and vibrant New York City',
│ ending='The protagonist saves the city and reconciles with their estranged family.',
│ genre='action',
│ name='City Pulse',
│ characters=['Alex Mercer', 'Nina Castillo', 'Detective Mike Johnson'],
│ storyline='In the heart of New York City, a former cop turned vigilante, Alex Mercer, teams up with a street-smart activist, Nina Castillo, to take down a corrupt political figure who threatens to destroy the city. As they navigate through the intricate web of power and deception, they uncover shocking truths that push them to the brink of their abilities. With time running out, they must race against the clock to save New York and confront their own demons.'
)

PDF Assistant with Knowledge & Storage

Show details

Lets create a PDF Assistant that can answer questions from a PDF. We'll use PgVector for knowledge and storage.

Knowledge Base: information that the Assistant can search to improve its responses (uses a vector db).

Storage: provides long term memory for Assistants (uses a database).

1. Run PgVector

Install docker desktop and run PgVector on port 5532 using:

docker run -d \
-e POSTGRES_DB=ai \
-e POSTGRES_USER=ai \
-e POSTGRES_PASSWORD=ai \
-e PGDATA=/var/lib/postgresql/data/pgdata \
-v pgvolume:/var/lib/postgresql/data \
-p 5532:5432 \
--name pgvector \
phidata/pgvector:16

2. Create PDF Assistant

• Create a file pdf_assistant.py

importtyperfromrich.promptimportPromptfromtypingimportOptional, Listfromphi.assistantimportAssistantfromphi.storage.assistant.postgresimportPgAssistantStoragefromphi.knowledge.pdfimportPDFUrlKnowledgeBasefromphi.vectordb.pgvectorimportPgVector2db_url="postgresql+psycopg://ai:ai@localhost:5532/ai"knowledge_base=PDFUrlKnowledgeBase(
urls=["https://phi-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
vector_db=PgVector2(collection="recipes", db_url=db_url),
)
# Comment out after first runknowledge_base.load()
storage=PgAssistantStorage(table_name="pdf_assistant", db_url=db_url)
defpdf_assistant(new: bool=False, user: str="user"):
run_id: Optional[str] =Noneifnotnew:
existing_run_ids: List[str] =storage.get_all_run_ids(user)
iflen(existing_run_ids) >0:
run_id=existing_run_ids[0]
assistant=Assistant(
run_id=run_id,
user_id=user,
knowledge_base=knowledge_base,
storage=storage,
# Show tool calls in the responseshow_tool_calls=True,
# Enable the assistant to search the knowledge basesearch_knowledge=True,
# Enable the assistant to read the chat historyread_chat_history=True,
)
ifrun_idisNone:
run_id=assistant.run_idprint(f"Started Run: {run_id}\n")
else:
print(f"Continuing Run: {run_id}\n")
# Runs the assistant as a cli appassistant.cli_app(markdown=True)
if__name__=="__main__":
typer.run(pdf_assistant)

3. Install libraries

pip install -U pgvector pypdf "psycopg[binary]" sqlalchemy

4. Run PDF Assistant

python pdf_assistant.py

• Ask a question:

How do I make pad thai?

• See how the Assistant searches the knowledge base and returns a response.

• Message bye to exit, start the assistant again using python pdf_assistant.py and ask:

What was my last message?

See how the assistant now maintains storage across sessions.

• Run the pdf_assistant.py file with the --new flag to start a new run.

python pdf_assistant.py --new

Checkout the cookbook for more examples.

Looking to build an AI product?

We've helped many companies build AI products, the general workflow is:

1. Build an Assistant with proprietary data to perform tasks specific to your product.
2. Connect your product to the Assistant via an API.
3. Monitor and Improve your AI product.

We also provide dedicated support and development, book a call to get started.

Contributions

We're an open-source project and welcome contributions, please read the contributing guide for more information.

Request a feature

• If you have a feature request, please open an issue or make a pull request.
• If you have ideas on how we can improve, please create a discussion.

Roadmap

Our roadmap is available here. If you have a feature request, please open an issue/discussion.