diff options
Diffstat (limited to 'assistant.py')
| -rw-r--r-- | assistant.py | 13 |
1 files changed, 11 insertions, 2 deletions
diff --git a/assistant.py b/assistant.py index 8ccc6ff..bf6049a 100644 --- a/assistant.py +++ b/assistant.py @@ -51,10 +51,12 @@ DEFAULTS = { "system": ("You are a voice assistant. Your replies are spoken aloud, so answer " "briefly in plain sentences: no markdown, no lists, no emoji. " "Reply in the language the user speaks, Italian or English. " + "Write numbers, times and dates in digits, never spelled out. " "Facts about the user's computer, devices, accounts, mail, calendar " "or money come only from a tool: call one, and if none can tell, " "say you do not know. Never guess them."), "tool_rounds": 3, + "temperature": None, # None: the llama-server preset's "whisper": {"model": "/data/voice-models/whisper/ggml-large-v3-turbo-q5_0.bin", "device": 0, "port": 8182}, "kokoro": {"model": "/data/voice-models/kokoro/kokoro-v1.0.onnx", @@ -374,6 +376,8 @@ def ask(messages, calls, tools=None): "chat_template_kwargs": {"enable_thinking": False}} if tools: body["tools"] = tools + if CFG["temperature"] is not None: + body["temperature"] = CFG["temperature"] req = urllib.request.Request(CFG["llm"] + "/chat/completions", json.dumps(body).encode(), {"Content-Type": "application/json"}) with urllib.request.urlopen(req) as r: @@ -542,8 +546,13 @@ def reply(history, q, mine): question = {"role": "user", "content": text} # ponytail: last 20 messages, summarise if long sessions need memory # The model has no clock: without the date it makes one up for tools. - now = time.strftime("It is %A %d %B %Y, %H:%M.") - msgs = [{"role": "system", "content": f"{CFG['system']} {now}"}] + history[-20:] + [question] + # Also stamped on the question itself, which history does not keep: with + # the time only in the system prompt, "what time is it?" asked again an + # hour later copied the old answer from history. Stamping every message + # in history fixed that but lost tool arguments (account filter 0/6). + now = time.strftime("%A %d %B %Y, %H:%M") + msgs = ([{"role": "system", "content": f"{CFG['system']} It is {now}."}] + history[-20:] + + [{"role": "user", "content": f"[{now}] {text}"}]) t, said, voice, announced = time.perf_counter(), [], lang, False def say(s): |