Keysat
536358093f
The intake bot now accepts a photo of a business card in the intake room and turns it into the same new-investor proposal a typed note would. The only new step is image -> text; everything downstream (parse, fuzzy match, in-thread approval, log-communication write) is reused unchanged. M3 was deferred only because Spark Control had no vision model. That blocker is gone: the daily-driver Qwen is vision-capable under the same model id, and the gateway forwards OpenAI multimodal content untouched, so no gateway/server/s9pk change is needed -- this ships bot-only (git pull + rebuild on the Spark). Transcribe-then-reuse (not vision-straight-to-JSON) is deliberate: the transcription becomes the source text the email-integrity rule checks against, so a mis-read address can't reach the CRM unapproved -- same guarantee as the text path. Card commits tag source="matrix_card" for the audit log. - llm.chat_vision: multimodal /v1/chat/completions, same model, same gateway - spark.transcribe_card: faithful card->text, "" on a non-card (NONE sentinel) - bot.on_image/handle_card: download image, transcribe, hand to handle_intake - crm_client: source provenance overridable via the proposal's _source key - tests: test_spark.py + a provenance case; 41/41 suite green
65 lines
3.0 KiB
Python
65 lines
3.0 KiB
Python
"""Local Qwen chat client via Spark Control /v1/chat/completions.
|
|
|
|
Used for the privacy-sensitive, high-volume reasoning that must stay on Ten31
|
|
infra (entity-resolution adjudication, triage). Frontier reasoning still goes to
|
|
Claude; this is the local leg. Thinking is disabled for fast structured output.
|
|
"""
|
|
import json
|
|
import re
|
|
|
|
import config
|
|
import http_util
|
|
|
|
|
|
def chat(prompt, system=None, max_tokens=200, temperature=0.0):
|
|
messages = []
|
|
if system:
|
|
messages.append({"role": "system", "content": system})
|
|
messages.append({"role": "user", "content": prompt})
|
|
body = {"model": config.CHAT_MODEL, "messages": messages,
|
|
"temperature": temperature, "max_tokens": max_tokens,
|
|
"chat_template_kwargs": {"enable_thinking": False}}
|
|
status, data = http_util.request("POST", f"{config.SPARK_CONTROL_URL}/v1/chat/completions",
|
|
body, verify=config.SPARK_VERIFY_TLS)
|
|
if status != 200:
|
|
raise RuntimeError(f"/v1/chat/completions -> {status}: {data}")
|
|
return (data["choices"][0]["message"].get("content") or "").strip()
|
|
|
|
|
|
def chat_vision(prompt, image_b64, mime="image/jpeg", system=None, max_tokens=600, temperature=0.0):
|
|
"""Multimodal chat: a text prompt + one base64 image to the local VL model via Spark Control.
|
|
|
|
Same endpoint and model as chat() — the daily-driver Qwen is vision-capable (capabilities
|
|
[vision, reasoning]); the only difference is the user message's `content` is the OpenAI
|
|
multimodal array (a text part + an image_url data-URI), which Spark Control forwards to vLLM
|
|
unchanged (it's a dumb passthrough). The server downscales to its max_pixels cap, so a
|
|
full-res phone photo is fine. Thinking stays off for fast, literal output."""
|
|
messages = []
|
|
if system:
|
|
messages.append({"role": "system", "content": system})
|
|
messages.append({"role": "user", "content": [
|
|
{"type": "text", "text": prompt},
|
|
{"type": "image_url", "image_url": {"url": f"data:{mime};base64,{image_b64}"}},
|
|
]})
|
|
body = {"model": config.CHAT_MODEL, "messages": messages,
|
|
"temperature": temperature, "max_tokens": max_tokens,
|
|
"chat_template_kwargs": {"enable_thinking": False}}
|
|
status, data = http_util.request("POST", f"{config.SPARK_CONTROL_URL}/v1/chat/completions",
|
|
body, verify=config.SPARK_VERIFY_TLS)
|
|
if status != 200:
|
|
raise RuntimeError(f"/v1/chat/completions (vision) -> {status}: {data}")
|
|
return (data["choices"][0]["message"].get("content") or "").strip()
|
|
|
|
|
|
def chat_json(prompt, system=None, max_tokens=200):
|
|
"""Chat and parse the first JSON object from the reply (tolerant of fences)."""
|
|
raw = chat(prompt, system=system, max_tokens=max_tokens)
|
|
raw = re.sub(r"^```(json)?|```$", "", raw.strip(), flags=re.MULTILINE).strip()
|
|
m = re.search(r"\{.*\}", raw, re.DOTALL)
|
|
if not m:
|
|
return None
|
|
try:
|
|
return json.loads(m.group(0))
|
|
except json.JSONDecodeError:
|
|
return None
|