LlamaIndex

export VENICE_API_KEY=your-venice-api-key

import os

from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="venice-uncensored",
    api_base="https://api.venice.ai/api/v1",
    api_key=os.environ["VENICE_API_KEY"],
    is_chat_model=True,
    is_function_calling_model=True,
    context_window=32768,
    temperature=0.7,
)

response = llm.complete("Explain zero data retention in two sentences.")
print(str(response))

from llama_index.core.llms import ChatMessage

messages = [
    ChatMessage(role="system", content="You are a concise, privacy-respecting assistant."),
    ChatMessage(role="user", content="Why does uncensored inference matter for research?"),
]

response = llm.chat(messages)
print(response.message.content)

for chunk in llm.stream_complete("Write a haiku about decentralization."):
    print(chunk.delta, end="", flush=True)

import os

from llama_index.core import Settings
from llama_index.llms.openai_like import OpenAILike
from llama_index.embeddings.openai_like import OpenAILikeEmbedding

Settings.llm = OpenAILike(
    model="zai-org-glm-5-1",
    api_base="https://api.venice.ai/api/v1",
    api_key=os.environ["VENICE_API_KEY"],
    is_chat_model=True,
    is_function_calling_model=True,
    context_window=32768,
)

Settings.embed_model = OpenAILikeEmbedding(
    model_name="text-embedding-bge-m3",
    api_base="https://api.venice.ai/api/v1",
    api_key=os.environ["VENICE_API_KEY"],
)

import os

from llama_index.embeddings.openai_like import OpenAILikeEmbedding

embed_model = OpenAILikeEmbedding(
    model_name="text-embedding-bge-m3",
    api_base="https://api.venice.ai/api/v1",
    api_key=os.environ["VENICE_API_KEY"],
)

vector = embed_model.get_text_embedding("Venice AI provides private inference.")
print(f"Embedding dimension: {len(vector)}")

from llama_index.core import Document, VectorStoreIndex

documents = [
    Document(text="Venice AI provides private, uncensored AI inference with zero data retention."),
    Document(text="The Venice API is OpenAI-compatible, supporting chat, images, audio, video, and embeddings."),
    Document(text="Venice supports function calling, structured outputs, web search, and reasoning models."),
    Document(text="Privacy tiers include Private (zero retention) and Anonymized (third-party processed)."),
]

index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine(similarity_top_k=2)

response = query_engine.query("What privacy tiers does Venice offer?")
print(str(response))

from llama_index.core import SimpleDirectoryReader, VectorStoreIndex

documents = SimpleDirectoryReader("./data").load_data()
index = VectorStoreIndex.from_documents(documents)

import asyncio
import os

from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai_like import OpenAILike


def get_venice_model_price(model_id: str) -> str:
    """Get the pricing for a Venice AI model."""
    prices = {
        "venice-uncensored": "Input: $0.20/1M, Output: $0.90/1M",
        "zai-org-glm-5-1": "Input: $1.75/1M, Output: $5.50/1M",
        "qwen3-5-9b": "Input: $0.10/1M, Output: $0.15/1M",
    }
    return prices.get(model_id, f"Model {model_id} not found in price list.")


llm = OpenAILike(
    model="zai-org-glm-5-1",
    api_base="https://api.venice.ai/api/v1",
    api_key=os.environ["VENICE_API_KEY"],
    is_chat_model=True,
    is_function_calling_model=True,
    context_window=32768,
)

agent = FunctionAgent(
    tools=[get_venice_model_price],
    llm=llm,
    system_prompt="You help users find the right Venice AI model. Use tools when needed.",
)


async def main() -> None:
    response = await agent.run("How much does zai-org-glm-5-1 cost?")
    print(str(response))


asyncio.run(main())

import os

from pydantic import BaseModel, Field
from llama_index.core.llms import ChatMessage
from llama_index.llms.openai_like import OpenAILike


class PrivacySummary(BaseModel):
    summary: str = Field(description="One-sentence overview")
    benefits: list[str] = Field(description="Key privacy benefits")
    recommendation: str = Field(description="When to choose this approach")


llm = OpenAILike(
    model="zai-org-glm-5-1",
    api_base="https://api.venice.ai/api/v1",
    api_key=os.environ["VENICE_API_KEY"],
    is_chat_model=True,
    is_function_calling_model=True,
    context_window=32768,
)

structured_llm = llm.as_structured_llm(PrivacySummary)
result = structured_llm.chat([
    ChatMessage(role="user", content="Summarize why private inference beats providers that retain chat logs."),
])

summary = result.raw
print(summary.summary)
print(summary.benefits)

import os

from llama_index.llms.openai_like import OpenAILike

llm = OpenAILike(
    model="venice-uncensored",
    api_base="https://api.venice.ai/api/v1",
    api_key=os.environ["VENICE_API_KEY"],
    is_chat_model=True,
    context_window=32768,
    additional_kwargs={
        "extra_body": {
            "venice_parameters": {
                "enable_web_search": "auto",
            }
        }
    },
)

response = llm.complete("What are notable AI privacy developments this week?")
print(str(response))

response = llm.complete(
    "Summarize today's headlines about decentralized AI.",
    extra_body={"venice_parameters": {"enable_web_search": "on"}},
)