LLM Integrations

provider.generate(prompt: str, **kwargs) -> str
provider.generate_structured(prompt: str, **kwargs) -> dict
provider.is_available() -> bool

from semantica.llms import Groq

# api_key falls back to the GROQ_API_KEY environment variable
groq = Groq(model="llama-3.1-8b-instant", api_key="YOUR_GROQ_KEY")

# Always health-check before the first call in a long-running process
if not groq.is_available():
    raise RuntimeError("Groq provider unreachable — check GROQ_API_KEY")

# Plain generation
verdict = groq.generate(
    "Alert: 4200 LDAP objects enumerated in 8s from ws-finance-03. "
    "True positive or false positive? One sentence.",
    temperature=0.1,    # low temperature for deterministic triage verdicts
)
print(verdict)
# "True positive — volume and speed are consistent with T1087.002 domain enumeration."

# Structured extraction — returns a parsed dict
entities = groq.generate_structured(
    "Extract threat actors and CVEs from: "
    "APT29 exploited CVE-2024-3400 in PAN-OS GlobalProtect."
)
# {"threat_actors": ["APT29"], "cves": ["CVE-2024-3400"], "products": ["PAN-OS GlobalProtect"]}

from semantica.llms import OpenAI

oai = OpenAI(model="gpt-4o", api_key="YOUR_OAI_KEY")
# api_key falls back to OPENAI_API_KEY environment variable

response = oai.generate(
    "Under CRR2 Article 92, what is the minimum total capital ratio "
    "for a G-SIB subject to a 2% GSIB buffer surcharge?"
)
print(response)

# Structured output — useful for deterministic data extraction
risk_data = oai.generate_structured(
    "Extract all counterparty names and exposure amounts from: "
    "Counterparty A: 45M EUR notional, Counterparty B: 12M EUR notional, "
    "Counterparty C: 89M EUR notional."
)
# {"counterparties": [{"name": "Counterparty A", "exposure_eur": 45000000}, ...]}

from semantica.llms import LiteLLM

# Anthropic Claude — highest accuracy for complex reasoning
llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
# Reads ANTHROPIC_API_KEY from environment

# Azure OpenAI — compliance and data-residency requirements
llm = LiteLLM(model="azure/gpt-4o", api_key="YOUR_AZURE_KEY")

# AWS Bedrock — existing cloud agreement, no new vendor
llm = LiteLLM(model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0")

# Google Vertex AI
llm = LiteLLM(model="vertex_ai/gemini-1.5-pro")

# Ollama — fully local, no network calls
llm = LiteLLM(model="ollama/llama3.2")

# All of them: same call
response = llm.generate("Summarise the ICH E6(R2) GCP guideline key requirements.")

import os

PROVIDER_MAP = {
    "prod":    "anthropic/claude-sonnet-4-20250514",
    "staging": "openai/gpt-4o-mini",
    "local":   "ollama/llama3.2",
    "azure":   "azure/gpt-4o",
}

env = os.getenv("DEPLOY_ENV", "local")
llm = LiteLLM(model=PROVIDER_MAP[env])
# The rest of the application never touches provider names

from semantica.llms import HuggingFaceLLM

# HuggingFace Hub — authentication via HF_TOKEN environment variable
hf = HuggingFaceLLM(model="mistralai/Mistral-7B-Instruct-v0.3")

# Biomedical fine-tuned model for clinical entity extraction
bio_llm = HuggingFaceLLM(model="aaditya/Llama3-OpenBioLLM-70B")

# Air-gapped deployment — model on local NFS share or mounted volume
# Both `model` and `model_name` are accepted as constructor parameters
air_gapped_llm = HuggingFaceLLM(model="/opt/models/llama-3.1-70b-instruct")

response = air_gapped_llm.generate(
    "Summarise SIGINT collection window 2024-Q3 for APT29 C2 infrastructure.",
    max_length=512,
)

from semantica.context import AgentContext, ContextGraph
from semantica.vector_store import VectorStore
from semantica.llms import Groq, LiteLLM

vs    = VectorStore(backend="faiss", dimension=768)
graph = ContextGraph(advanced_analytics=True)
context = AgentContext(vector_store=vs, knowledge_graph=graph, graph_expansion=True)

# Load your knowledge base once
context.store(
    [
        {"content": "APT29 exploits CVE-2024-3400 in PAN-OS GlobalProtect — CVSS 10.0",
         "metadata": {"source": "nvd", "actor": "APT29"}},
        {"content": "NOBELIUM (APT29) leverages OAuth token theft against Azure AD tenants",
         "metadata": {"source": "msft_blog_2023", "actor": "APT29", "technique": "T1528"}},
    ],
    extract_entities=True,
    extract_relationships=True,
)

query = "What is APT29's current exploitation methodology and what cloud services are targeted?"

# Tier 1: fast answer with Groq (< 300ms)
fast_llm = Groq(model="llama-3.1-8b-instant", api_key="YOUR_GROQ_KEY")
fast_result = context.query_with_reasoning(query, llm_provider=fast_llm, max_results=5)
print("FAST: {}  (conf={:.0%})".format(fast_result["response"], fast_result["confidence"]))

# Tier 2: deep answer with Claude if confidence is below threshold
if fast_result["confidence"] < 0.85:
    deep_llm = LiteLLM(model="anthropic/claude-sonnet-4-20250514")
    deep_result = context.query_with_reasoning(
        query, llm_provider=deep_llm, max_results=15, max_hops=3
    )
    print("DEEP: {}  (conf={:.0%})".format(deep_result["response"], deep_result["confidence"]))

from semantica.semantic_extract import NamedEntityRecognizer, EventDetector
from semantica.semantic_extract.methods import (
    extract_entities_llm,
    extract_relations_llm,
    extract_triplets_llm,
)

# NER with Groq — provider name as a string
ner = NamedEntityRecognizer(
    methods=["llm"],
    provider="groq",
    llm_model="llama-3.1-8b-instant",
)
entities = ner.extract_entities(
    "APT29 exploited CVE-2024-3400 in PAN-OS GlobalProtect to compromise NATO member networks."
)
for e in entities:
    # Entity fields: .text, .label, .confidence
    print("{} ({}) — conf={:.2f}".format(e.text, e.label, e.confidence))
# APT29 (THREAT_ACTOR) — conf=0.96
# CVE-2024-3400 (CVE) — conf=0.99
# PAN-OS GlobalProtect (PRODUCT) — conf=0.94
# NATO (ORGANIZATION) — conf=0.91

# Event detection with the same provider pattern
detector = EventDetector(method="llm", provider="groq")
events = detector.detect_events(
    "ENISA published the Threat Landscape 2024 report on October 22nd, "
    "covering 11 primary threat categories including ransomware and supply-chain attacks."
)

# Triplet extraction — returns (subject, predicate, object) triples
text = "Warfarin inhibits VKORC1 enzyme activity, reducing vitamin K-dependent clotting factor synthesis."
triplets = extract_triplets_llm(text, provider="groq", model="llama-3.1-8b-instant")
for t in triplets:
    print("{} -> {} -> {}".format(t.subject, t.predicate, t.object))
# warfarin -> inhibits -> VKORC1 enzyme activity
# warfarin -> reduces -> vitamin K-dependent clotting factor synthesis

from semantica.semantic_extract.providers import create_provider
from semantica.semantic_extract import NamedEntityRecognizer

# create_provider pools instances — same key reuses the same object
provider = create_provider(
    "novita",
    api_key="YOUR_NOVITA_KEY",       # or set NOVITA_API_KEY env var
    model="deepseek/deepseek-v3.2",  # default model
)

if provider.is_available():
    # Plain generation
    response = provider.generate("Summarise the Basel III leverage ratio requirement.")

    # Structured extraction — returns parsed dict
    data = provider.generate_structured(
        "Extract drug names and dosages from: "
        "Patient received warfarin 5mg daily, aspirin 75mg daily, metformin 500mg twice daily."
    )

# Use Novita through the NER interface — provider name as string
ner = NamedEntityRecognizer(
    methods=["llm"],
    provider="novita",
    llm_model="deepseek/deepseek-v3.2",
)
entities = ner.extract_entities(
    "CVE-2024-3400 is exploited by UNC3886 targeting PAN-OS GlobalProtect."
)
for e in entities:
    print("{} ({}) — conf={:.2f}".format(e.text, e.label, e.confidence))