Merge branch 'main' of https://github.com/phidatahq/phidata into rele…

…ase/2.7.0

cookbook/examples/agents/02_movie_recommedation.py

@@ -0,0 +1,29 @@
+from phi.agent import Agent
+from phi.model.openai import OpenAIChat
+from phi.tools.exa import ExaTools
+
+movie_recommendation_agent = Agent(
+    name="PopcornPal",
+    tools=[
+        ExaTools(),
+    ],
+    model=OpenAIChat(id="gpt-4o"),
+    description=(
+        "You are PopcornPal, a movie recommendation agent that searches and scrapes movie websites to provide detailed recommendations, "
+        "including ratings, genres, descriptions, trailers, and upcoming releases."
+    ),
+    instructions=[
+        "Use Exa to search for the movies.",
+        "Provide results with the following details: movie title, genre, movies with good ratings, description, recommended viewing age, primary language,runtime, imdb rating and release date.",
+        "Include trailers for movies similar to the recommendations and upcoming movies of the same genre or from related directors/actors.",
+        "Give atleast 5 movie recommendations for each query",
+        "Present the output in a well-structured markdown table for readability.",
+        "Ensure all movie data is correct, especially for recent or upcoming releases.",
+    ],
+    markdown=True,
+)
+
+movie_recommendation_agent.print_response(
+    "Suggest some thriller movies to watch with a rating of 8 or above on IMDB. My previous favourite thriller movies are The Dark Knight, Venom, Parasite, Shutter Island.",
+    stream=True,
+)

cookbook/examples/agents/03_itinerary_planner.py

@@ -0,0 +1,24 @@
+from phi.model.openai import OpenAIChat
+from phi.agent import Agent
+from phi.tools.exa import ExaTools
+
+itinerary_agent = Agent(
+    name="GlobeHopper",
+    model=OpenAIChat(id="gpt-4o"),
+    tools=[ExaTools()],
+    markdown=True,
+    description="You are an expert itinerary planning agent. Your role is to assist users in creating detailed, customized travel plans tailored to their preferences and needs.",
+    instructions=[
+        "Use Exa to search and extract relevant data from reputable travel platforms.",
+        "Collect information on flights, accommodations, local attractions, and estimated costs from these sources.",
+        "Ensure that the gathered data is accurate and tailored to the user's preferences, such as destination, group size, and budget constraints.",
+        "Create a clear and concise itinerary that includes: detailed day-by-day travel plan, suggested transportation and accommodation options, activity recommendations (e.g., sightseeing, dining, events), an estimated cost breakdown (covering transportation, accommodation, food, and activities).",
+        "If a particular website or travel option is unavailable, provide alternatives from other trusted sources.",
+        "Do not include direct links to external websites or booking platforms in the response."
+    ],
+)
+
+itinerary_agent.print_response(
+    "I want to plan an offsite for 14 people for 3 days (28th-30th March) in London within 10k dollars. Please suggest options for places to stay, activities, and co working spaces and a detailed itinerary for the 3 days with transportation and activities",
+    stream=True,
+)

cookbook/vectordb/qdrant_db.py

@@ -0,0 +1,30 @@
+# pip install qdrant-client 
+from phi.vectordb.qdrant import Qdrant
+from phi.agent import Agent
+from phi.knowledge.pdf import PDFUrlKnowledgeBase
+
+# run qdrant client locally
+"""
+- Run the docker image: docker pull qdrant/qdrant
+- Then, run the service:
+docker run -p 6333:6333 -p 6334:6334 \
+    -v $(pwd)/qdrant_storage:/qdrant/storage:z \
+    qdrant/qdrant
+"""
+COLLECTION_NAME = "thai-recipes"
+
+vector_db = Qdrant(
+    collection=COLLECTION_NAME,
+    url="http://localhost:6333"
+)
+
+knowledge_base = PDFUrlKnowledgeBase(
+    urls=["https://phi-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
+    vector_db=vector_db,
+)
+
+knowledge_base.load(recreate=False)  # Comment out after first run
+
+# Create and use the agent
+agent = Agent(knowledge_base=knowledge_base, use_tools=True, show_tool_calls=True)
+agent.print_response("List down the ingredients to make Massaman Gai", markdown=True)