from cyllama import complete

# One line is all you need
response = complete(
    "Explain quantum computing in simple terms",
    model_path="models/llama.gguf",
    temperature=0.7,
    max_tokens=200
)
print(response)

from cyllama import complete, chat, LLM

# One-shot completion
response = complete("What is Python?", model_path="model.gguf")

# Multi-turn chat
messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "What is machine learning?"}
]
response = chat(messages, model_path="model.gguf")

# Reusable LLM instance (faster for multiple prompts)
llm = LLM("model.gguf")
response1 = llm("Question 1")
response2 = llm("Question 2")  # Model stays loaded!

for chunk in complete("Tell me a story", model_path="model.gguf", stream=True):
    print(chunk, end="", flush=True)

from cyllama import batch_generate

prompts = ["What is 2+2?", "What is 3+3?", "What is 4+4?"]
responses = batch_generate(prompts, model_path="model.gguf")

from cyllama.llama.llama_cpp import Speculative, SpeculativeParams

spec = Speculative(ctx_target, ctx_draft)
params = SpeculativeParams(n_draft=16, p_min=0.75)
draft_tokens = spec.gen_draft(params, prompt_tokens, last_token)

from cyllama import estimate_gpu_layers

estimate = estimate_gpu_layers(
    model_path="model.gguf",
    available_vram_mb=8000
)
print(f"Recommended GPU layers: {estimate.n_gpu_layers}")

from cyllama.llama.llama_cpp import NgramCache

cache = NgramCache()
cache.update(tokens, ngram_min=2, ngram_max=4)
draft = cache.draft(input_tokens, n_draft=16)

from cyllama.integrations import OpenAIClient

client = OpenAIClient(model_path="model.gguf")

response = client.chat.completions.create(
    messages=[{"role": "user", "content": "Hello!"}],
    temperature=0.7
)
print(response.choices[0].message.content)

from cyllama.integrations import CyllamaLLM
from langchain.chains import LLMChain

llm = CyllamaLLM(model_path="model.gguf", temperature=0.7)
chain = LLMChain(llm=llm, prompt=prompt_template)
result = chain.run(topic="AI")

from cyllama import LLM
from cyllama.agents import ReActAgent, tool
from simpleeval import simple_eval

@tool
def calculate(expression: str) -> str:
    """Evaluate a math expression safely."""
    return str(simple_eval(expression))

llm = LLM("model.gguf")
agent = ReActAgent(llm=llm, tools=[calculate])
result = agent.run("What is 25 * 4?")
print(result.answer)

from cyllama.agents import ConstrainedAgent

agent = ConstrainedAgent(llm=llm, tools=[calculate])
result = agent.run("Calculate 100 / 4")  # Guaranteed valid tool calls

from cyllama.agents import ContractAgent, tool, pre, post, ContractPolicy

@tool
@pre(lambda args: args['x'] != 0, "cannot divide by zero")
@post(lambda r: r is not None, "result must not be None")
def divide(a: float, x: float) -> float:
    """Divide a by x."""
    return a / x

agent = ContractAgent(
    llm=llm,
    tools=[divide],
    policy=ContractPolicy.ENFORCE,
    task_precondition=lambda task: len(task) > 10,
    answer_postcondition=lambda ans: len(ans) > 0,
)
result = agent.run("What is 100 divided by 4?")

from cyllama.whisper import WhisperContext, WhisperFullParams
import numpy as np

# Load model and audio
ctx = WhisperContext("models/ggml-base.en.bin")
samples = load_audio_as_16khz_float32("audio.wav")  # Your audio loading function

# Transcribe
params = WhisperFullParams()
ctx.full(samples, params)

# Get results
for i in range(ctx.full_n_segments()):
    start = ctx.full_get_segment_t0(i) / 100.0
    end = ctx.full_get_segment_t1(i) / 100.0
    text = ctx.full_get_segment_text(i)
    print(f"[{start:.2f}s - {end:.2f}s] {text}")

from cyllama.sd import text_to_image

# Simple text-to-image
images = text_to_image(
    model_path="models/sd_xl_turbo_1.0.q8_0.gguf",
    prompt="a photo of a cute cat",
    width=512,
    height=512,
    sample_steps=4,
    cfg_scale=1.0
)
images[0].save("output.png")

from cyllama.sd import SDContext, SDContextParams, SampleMethod, Scheduler

params = SDContextParams()
params.model_path = "models/sd_xl_turbo_1.0.q8_0.gguf"
params.n_threads = 4

ctx = SDContext(params)
images = ctx.generate(
    prompt="a beautiful mountain landscape",
    negative_prompt="blurry, ugly",
    width=512,
    height=512,
    sample_method=SampleMethod.EULER,
    scheduler=Scheduler.DISCRETE
)

from cyllama.rag import RAG

# Create RAG instance with embedding and generation models
rag = RAG(
    embedding_model="models/bge-small-en-v1.5-q8_0.gguf",
    generation_model="models/llama.gguf"
)

# Add documents
rag.add_texts([
    "Python is a high-level programming language.",
    "Machine learning is a subset of artificial intelligence.",
    "Neural networks are inspired by biological neurons."
])

# Query
response = rag.query("What is Python?")
print(response.text)

from cyllama.rag import RAG, load_directory

rag = RAG(
    embedding_model="models/bge-small-en-v1.5-q8_0.gguf",
    generation_model="models/llama.gguf"
)

# Load all documents from a directory
documents = load_directory("docs/", glob="**/*.md")
rag.add_documents(documents)

response = rag.query("How do I configure the system?")

from cyllama.rag import RAG, HybridStore, Embedder

embedder = Embedder("models/bge-small-en-v1.5-q8_0.gguf")
store = HybridStore("knowledge.db", embedder)

store.add_texts(["Document content..."])

# Hybrid search with configurable weights
results = store.search("query", k=5, vector_weight=0.7, fts_weight=0.3)

from cyllama import LLM
from cyllama.agents import ReActAgent
from cyllama.rag import RAG, create_rag_tool

rag = RAG(
    embedding_model="models/bge-small-en-v1.5-q8_0.gguf",
    generation_model="models/llama.gguf"
)
rag.add_texts(["Your knowledge base..."])

# Create a tool from the RAG instance
search_tool = create_rag_tool(rag)

llm = LLM("models/llama.gguf")
agent = ReActAgent(llm=llm, tools=[search_tool])
result = agent.run("Find information about X in the knowledge base")

from cyllama.llama.llama_cpp import GGUFContext

ctx = GGUFContext.from_file("model.gguf")
metadata = ctx.get_all_metadata()
print(f"Model: {metadata['general.name']}")

from cyllama.llama.llama_cpp import json_schema_to_grammar

schema = {"type": "object", "properties": {"name": {"type": "string"}}}
grammar = json_schema_to_grammar(schema)

from cyllama.llama.llama_cpp import download_model, list_cached_models, get_hf_file

# Download from HuggingFace (saves to ~/.cache/llama.cpp/)
download_model("bartowski/Llama-3.2-1B-Instruct-GGUF:latest")

# Or with explicit parameters
download_model(hf_repo="bartowski/Llama-3.2-1B-Instruct-GGUF:latest")

# Download specific file to custom path
download_model(
    hf_repo="bartowski/Llama-3.2-1B-Instruct-GGUF",
    hf_file="Llama-3.2-1B-Instruct-Q8_0.gguf",
    model_path="./models/my_model.gguf"
)

# Get file info without downloading
info = get_hf_file("bartowski/Llama-3.2-1B-Instruct-GGUF:latest")
print(info)  # {'repo': '...', 'gguf_file': '...', 'mmproj_file': '...'}

# List cached models
models = list_cached_models()

python3 -i scripts/start.py

>>> from cyllama import complete
>>> response = complete("What is 2+2?", model_path="models/Llama-3.2-1B-Instruct-Q8_0.gguf")
>>> print(response)