How to run Llama model locally on MacBook Pro and Function calling in LLM -Llama web search agent breakdown

(venv) admin@admins-MacBook-Pro selvapal % ollama run llama3
>>> list the climate chnage reasons
Here are some of the main reasons contributing to climate change:

1. **Greenhouse gases**: The burning of fossil fuels such as coal, oil, and gas releases carbon dioxide (CO2), methane (CH4), and other greenhouse gases into the atmosphere, trapping heat
and leading to global warming.
2. **Deforestation**: The clearance of forests for agriculture, urbanization, and logging reduces the ability of trees to absorb CO2, a key greenhouse gas, contributing to climate change.
3. **Land use changes**: Changes in land use, such as the conversion of natural habitats into agricultural lands or cities, can lead to increased emissions of greenhouse gases and loss of
carbon sequestration capabilities.
4. **Agriculture**: The production of meat, especially beef, and other animal products leads to increased methane emissions and deforestation for livestock grazing and feed crop
production.
5. **Industrial processes**: Industrial activities such as cement production, steel manufacturing, and chemical processing release large amounts of greenhouse gases into the atmosphere.
6. **Population growth**: As the global population grows, so does the demand for energy, food, and resources, leading to increased emissions and consumption.
7. **Consumption patterns**: The way we live our daily lives, including transportation, diet, and consumer choices, contributes to climate change through energy use, waste generation, and
resource depletion.
8. **Waste management**: Inadequate waste management practices, such as the disposal of plastic waste in landfills or oceans, can lead to methane emissions and contribute to climate
change.
9. **Fugitive emissions**: The extraction, processing, and transportation of fossil fuels can release large amounts of greenhouse gases into the atmosphere, often unnoticed or unreported.
10. **Aerosol emissions**: The burning of biomass, such as wood or agricultural waste, releases aerosols that can trap heat and contribute to climate change.
11. **Nitrous oxide (N2O) emissions**: Agricultural practices, such as fertilizer use and manure management, release N2O, a potent greenhouse gas.
12. **Chlorofluorocarbons (CFCs)**: The use of CFC-containing products, such as refrigerants and propellants, can lead to the destruction of stratospheric ozone and contribute to climate
change.
13. **Methane emissions from natural sources**: Natural sources, such as wetlands, rice paddies, and termites, release methane into the atmosphere, which contributes to climate change.
14. **Ocean fertilization**: The addition of nutrients to the ocean to stimulate phytoplankton growth can lead to increased CO2 absorption but also releases other greenhouse gases and
alters marine ecosystems.
15. **Geoengineering**: Large-scale engineering projects aimed at mitigating climate change, such as solar radiation management or carbon capture and storage, can have unintended
consequences and potentially exacerbate climate change.

These are some of the main reasons contributing to climate change. It’s essential to understand these factors to develop effective strategies for reducing greenhouse gas emissions and
mitigating the impacts of climate change.

>>> Send a message (/? for help)

Verbose: True
Skip models: []
Prompts: [‘how to do organioc farming’]
Evaluating models: [‘llama3:latest’, ‘gemma:latest’]

Benchmarking: llama3:latest
Prompt: how to do organioc farming
Organic farming is a type of agriculture that avoids the use of synthetic fertilizers, pesticides, and genetically modified organisms (GMOs). Instead, organic farmers rely on natural methods to control pests and diseases, and use compost and other natural amendments to improve soil fertility. Here are some key principles and practices of organic farming:

1. **Soil conservation**: Organic farmers focus on building healthy soil through the use of crop rotations, cover crops, and organic amendments like compost.
2. **Crop rotation**: Rotating crops helps to break disease cycles, improves soil structure, and increases biodiversity.
3. **Composting**: Composting is a key process in organic farming that turns waste into nutrient-rich fertilizer.
4. **Manure management**: Organic farmers use animal manure as a natural fertilizer and to improve soil health.
5. **Integrated pest management (IPM)**: Instead of relying on pesticides, organic farmers use IPM techniques like crop rotation, biological control, and cultural controls to manage pests.
6. **Cover cropping**: Planting cover crops in the off-season helps to prevent erosion, adds nutrients to the soil, and provides habitat for beneficial insects.
7. **Biodiversity conservation**: Organic farming aims to conserve biodiversity by promoting ecosystem services and supporting beneficial insects and microorganisms.
8. **Minimum tillage or no-till**: Reducing soil disturbance helps to preserve soil structure, reduce erosion, and promote soil biota.
9. **Organic amendments**: Using natural amendments like compost, manure, or green manure instead of synthetic fertilizers.
10. **Record keeping**: Organic farmers keep detailed records of their farming practices, including crop rotations, pest management, and soil health.

Some specific techniques used in organic farming include:

1. **Biodynamic agriculture**: A holistic approach that considers the moon’s cycles and uses natural preparations to promote soil fertility and plant growth.
2. **Permaculture**: A design system that aims to create self-sustaining ecosystems by mimicking nature’s patterns and relationships.
3. **Agroforestry**: Integrating trees into agricultural landscapes to improve soil health, reduce erosion, and increase biodiversity.
4. **Green manure**: Planting legumes or other cover crops to fix nitrogen in the soil and add organic matter.
5. **Crop rotation with legumes**: Incorporating legume crops like beans or peas into crop rotations to improve soil fertility.

To get started with organic farming, you can:

1. **Research local regulations**: Familiarize yourself with national and regional laws regarding organic farming practices and certifications.
2. **Start small**: Begin by converting a small portion of your land to organic methods and gradually scale up as you gain experience.
3. **Join an organic farm network**: Connect with other organic farmers, attend workshops, and share knowledge to learn from their experiences.
4. **Develop a business plan**: Create a plan for marketing and selling your organic products, including pricing and target markets.
5. **Monitor and adjust**: Continuously monitor your soil health, crop yields, and pest management strategies, and make adjustments as needed.

Remember that transitioning to organic farming takes time, patience, and dedication. Start by making small changes and gradually build up your knowledge and skills.Response:

—————————————————-
llama3:latest
Prompt eval: 13.14 t/s
Response: 6.23 t/s
Total: 6.31 t/s

Stats:
Prompt tokens: 16
Response tokens: 654
Model load time: 2.06s
Prompt eval time: 1.22s
Response time: 105.04s
Total time: 108.32s
—————————————————-

Benchmarking: gemma:latest
Prompt: how to do organioc farming

wrapper = DuckDuckGoSearchAPIWrapper(max_results=25)
web_search_tool = DuckDuckGoSearchRun(api_wrapper=wrapper)

generate_prompt = PromptTemplate(
template=”””

<|begin_of_text|>

<|start_header_id|>system<|end_header_id|>

You are an AI assistant for Research Question Tasks, that synthesizes web search results.
Strictly use the following pieces of web search context to answer the question. If you don’t know the answer, just say that you don’t know.
keep the answer concise, but provide all of the details you can in the form of a research report.
Only make direct references to material if provided in the context.

<|eot_id|>

<|start_header_id|>user<|end_header_id|>

Question: {question}
Web Search Context: {context}
Answer:

<|eot_id|>

<|start_header_id|>assistant<|end_header_id|>”””,
input_variables=[“question”, “context”],
)

# Chain
generate_chain = generate_prompt | llama3 | StrOutputParser()

router_prompt = PromptTemplate(
template=”””

<|begin_of_text|>

<|start_header_id|>system<|end_header_id|>

You are an expert at routing a user question to either the generation stage or web search.
Use the web search for questions that require more context for a better answer, or recent events.
Otherwise, you can skip and go straight to the generation phase to respond.
You do not need to be stringent with the keywords in the question related to these topics.
Give a binary choice ‘web_search’ or ‘generate’ based on the question.
Return the JSON with a single key ‘choice’ with no premable or explanation.

Question to route: {question}

<|eot_id|>

<|start_header_id|>assistant<|end_header_id|>

“””,
input_variables=[“question”],
)

# Chain
question_router = router_prompt | llama3_json | JsonOutputParser()

# Test Run
question = “What’s up?”
print(question_router.invoke({“question”: question}))

query_prompt = PromptTemplate(
template=”””

<|begin_of_text|>

<|start_header_id|>system<|end_header_id|>

You are an expert at crafting web search queries for research questions.
More often than not, a user will ask a basic question that they wish to learn more about, however it might not be in the best format.
Reword their query to be the most effective web search string possible.
Return the JSON with a single key ‘query’ with no premable or explanation.

Question to transform: {question}

<|eot_id|>

<|start_header_id|>assistant<|end_header_id|>

“””,
input_variables=[“question”],
)

# Chain
query_chain = query_prompt | llama3_json | JsonOutputParser()

# Test Run
question = “What’s happened recently with Tesla?”
print(query_chain.invoke({“question”: question}))

Attributes:
question: question
generation: LLM generation
search_query: revised question for web search
context: web_search result
“””
question : str
generation : str
search_query : str
context : str

# Node – Generate

def generate(state):
“””
Generate answer

Args:
state (dict): The current graph state

Returns:
state (dict): New key added to state, generation, that contains LLM generation
“””

print(“Step: Generating Final Response”)
question = state[“question”]
context = state[“context”]

# Answer Generation
generation = generate_chain.invoke({“context”: context, “question”: question})
return {“generation”: generation}

# Node – Query Transformation

def transform_query(state):
“””
Transform user question to web search

Args:
state (dict): The current graph state

Returns:
state (dict): Appended search query
“””

print(“Step: Optimizing Query for Web Search”)
question = state[‘question’]
gen_query = query_chain.invoke({“question”: question})
search_query = gen_query[“query”]
return {“search_query”: search_query}

# Node – Web Search

def web_search(state):
“””
Web search based on the question

Args:
state (dict): The current graph state

Returns:
state (dict): Appended web results to context
“””

search_query = state[‘search_query’]
print(f’Step: Searching the Web for: “{search_query}”‘)

# Web search tool call
search_result = web_search_tool.invoke(search_query)
return {“context”: search_result}

# Conditional Edge, Routing

def route_question(state):
“””
route question to web search or generation.

Args:
state (dict): The current graph state

Returns:
str: Next node to call
“””

print(“Step: Routing Query”)
question = state[‘question’]
output = question_router.invoke({“question”: question})
if output[‘choice’] == “web_search”:
print(“Step: Routing Query to Web Search”)
return “websearch”
elif output[‘choice’] == ‘generate’:
print(“Step: Routing Query to Generation”)
return “generate”

# Build the edges
workflow.set_conditional_entry_point(
route_question,
{
“websearch”: “transform_query”,
“generate”: “generate”,
},
)
workflow.add_edge(“transform_query”, “websearch”)
workflow.add_edge(“websearch”, “generate”)
workflow.add_edge(“generate”, END)

# Compile the workflow
local_agent = workflow.compile()

# Test it out!
run_agent(“How are you doing today?”)