File size: 3,288 Bytes
6175374 035821c 6211d74 6175374 035821c 6175374 fa853aa 6211d74 6175374 6211d74 f2030ec 6211d74 f2030ec 6211d74 035821c f2030ec 6175374 6211d74 6175374 6211d74 f2030ec 6211d74 6175374 6211d74 fa853aa 0b2483c 6211d74 0b2483c 6211d74 0b2483c 6175374 6211d74 fa853aa 6211d74 0b2483c 6211d74 6f93da3 6211d74 bd514cd 6211d74 6175374 6211d74 fa853aa f2030ec |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 |
import os
import hydra
import aiflows
from aiflows.backends.api_info import ApiInfo
from aiflows.utils.general_helpers import read_yaml_file, quick_load_api_keys
from aiflows import logging
from aiflows.flow_cache import CACHING_PARAMETERS, clear_cache
from aiflows.utils import serving
from aiflows.workers import run_dispatch_worker_thread
from aiflows.messages import FlowMessage
from aiflows.interfaces import KeyInterface
from aiflows.utils.colink_utils import start_colink_server
from aiflows.workers import run_dispatch_worker_thread
CACHING_PARAMETERS.do_caching = False # Set to True in order to disable caching
# clear_cache() # Uncomment this line to clear the cache
logging.set_verbosity_debug()
dependencies = [
{"url": "aiflows/ChatInteractiveFlowModule", "revision": os.getcwd()}
]
from aiflows import flow_verse
flow_verse.sync_dependencies(dependencies)
if __name__ == "__main__":
#1. ~~~~~ Set up a colink server ~~~~
cl = start_colink_server()
#2. ~~~~~Load flow config~~~~~~
root_dir = "."
cfg_path = os.path.join(root_dir, "demo.yaml")
cfg = read_yaml_file(cfg_path)
#2.1 ~~~ Set the API information ~~~
# OpenAI backend
api_information = [ApiInfo(backend_used="openai",
api_key = os.getenv("OPENAI_API_KEY"))]
# # Azure backend
# api_information = ApiInfo(backend_used = "azure",
# api_base = os.getenv("AZURE_API_BASE"),
# api_key = os.getenv("AZURE_OPENAI_KEY"),
# api_version = os.getenv("AZURE_API_VERSION") )
quick_load_api_keys(cfg, api_information, key="api_infos")
#3. ~~~~ Serve The Flow ~~~~
serving.recursive_serve_flow(
cl=cl,
flow_class_name="flow_modules.aiflows.ChatInteractiveFlowModule.ChatHumanFlowModule",
flow_endpoint="ChatHumanFlowModule",
)
#4. ~~~~~Start A Worker Thread~~~~~
run_dispatch_worker_thread(cl)
#5. ~~~~~Mount the flow and get its proxy~~~~~~
proxy_flow= serving.get_flow_instance(
cl=cl,
flow_endpoint="ChatHumanFlowModule",
user_id="local",
config_overrides= cfg
)
#6. ~~~ Get the data ~~~
data = {"id": 0, "query": "I want to ask you a few questions"} # This can be a list of samples
# data = {"id": 0, "question": "Who was the NBA champion in 2023?"} # This can be a list of samples
input_message = proxy_flow.package_input_message(data = data)
#7. ~~~ Run inference ~~~
future = proxy_flow.get_reply_future(input_message)
#uncomment this line if you would like to get the full message back
#reply_message = future.get_message()
reply_data = future.get_data()
# ~~~ Print the output ~~~
print("~~~~~~Reply~~~~~~")
print(reply_data)
#8. ~~~~ (Optional) apply output interface on reply ~~~~
# output_interface = KeyInterface(
# keys_to_rename={"api_output": "answer"},
# )
# print("Output: ", output_interface(reply_data))
#9. ~~~~~Optional: Unserve Flow~~~~~~
# serving.delete_served_flow(cl, "ChatWithDemonstrationFlowModule") o_caching = False # Set to True to enable caching
|