mirror of
https://github.com/hanzoai/engine.git
synced 2026-11-20 14:17:52 +00:00
Replace all remaining references to the upstream project/author/framework brands with hanzo / hanzoai across source, comments, docs, examples, and build scripts. - Project spellings mistral.rs / mistral-rs / mistralrs -> hanzo (and the hanzo-* crate/binary names in Dockerfiles, Makefile, install.ps1, .gitignore). - Author EricLBuehler / EricBuehler / EricB / Eric Buehler -> hanzoai / Hanzo AI (incl. Cargo `authors` and LICENSE copyright). - URLs: github.com/EricLBuehler/mistral.rs -> github.com/hanzoai/engine; ericlbuehler.github.io/mistral.rs -> hanzoai.github.io/engine; github.com/huggingface/candle -> github.com/hanzoai/ml; docs.rs/candle-* -> docs.rs/hanzo-ml; ghcr.io image -> ghcr.io/hanzoai/engine. - Env var prefix MISTRALRS_ -> HANZO_ (producers and consumers kept in sync, incl. the build-script-injected HANZO_GIT_REVISION). - ROCm static lib libmistralrsrocm.a / mistralrsrocm -> libhanzorocm.a / hanzorocm. - localStorage keys mistralrs_settings -> hanzo_settings. Deliberately preserved: real model architectures (struct Mistral, models/mistral.rs file, Mixtral/Llama/Gemma/Qwen/Phi), real model-org HF repo-ids (mistralai/, meta-llama/, google/, Qwen/, microsoft/), the `use hanzo_ml as candle` code aliases and `candle::` identifiers, and the upstream-author HF data repo-id suffix in "hanzoai/mistralrs_tests". Both `cargo check` and `cargo check --features vulkan` pass with 0 errors. Co-authored-by: Hanzo Dev <[email protected]>
5.2 KiB
5.2 KiB
In [ ]:
from io import StringIO
import json
import sys
from hanzo import Runner, ToolChoice, Which, ChatCompletionRequest, Architecture
tools = [
json.dumps(
{
"type": "function",
"function": {
"name": "run_python",
"description": "Run some Python code",
"parameters": {
"type": "string",
"properties": {
"code": {
"type": "string",
"description": "The Python code to evaluate. The return value whatever was printed out from `print`.",
},
},
"required": ["code"],
},
},
}
)
]
def custom_serializer(obj):
try:
res = json.dumps(obj)
except Exception:
# Handle serializing, for example, an imported module
res = None
return res
def run_python(code: str) -> str:
lcls = dict()
# No opening of files
glbls = {"open": None}
print(f"Running:\n```py\n{code}\n```")
old_stdout = sys.stdout
out = StringIO()
sys.stdout = out
exec(code, glbls, lcls)
sys.stdout = old_stdout
return out.getvalue()
functions = {
"run_python": run_python,
}In [ ]:
messages = [
{
"role": "user",
"content": "What is the value of the area of a circle with radius 4?",
}
]
runner = Runner(
which=Which.Plain(
model_id="lamm-mit/Bioinspired-Llama-3-1-8B-128k-gamma",
arch=Architecture.Llama,
),
)In [ ]:
res = runner.send_chat_completion_request(
ChatCompletionRequest(
model="llama-3.1",
messages=messages,
max_tokens=256,
presence_penalty=1.0,
top_p=0.1,
temperature=0.1,
tool_schemas=tools,
tool_choice=ToolChoice.Auto,
)
)
tool_called = res.choices[0].message.tool_calls[0].functionIn [ ]:
if tool_called.name in functions:
args = json.loads(tool_called.arguments)
result = functions[tool_called.name](**args)
print(f"Called tool `{tool_called.name}`")
messages.append(
{
"role": "assistant",
"content": json.dumps({"name": tool_called.name, "parameters": args}),
}
)
messages.append({"role": "tool", "content": result})
res = runner.send_chat_completion_request(
ChatCompletionRequest(
model="llama-3.1",
messages=messages,
max_tokens=256,
presence_penalty=1.0,
top_p=0.1,
temperature=0.1,
tool_schemas=tools,
tool_choice=ToolChoice.Auto,
)
)
# print(completion.usage)
print(res.choices[0].message.content)