jandres/GenAIExamples
1
0
Fork 0
Code Issues Pull Requests Actions 5 Packages Projects Releases Wiki Activity

remove examples gateway. (#1243)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
This commit is contained in:
lkk
2024-12-13 15:16:11 +08:00
committed by GitHub
parent c760cac2f4
commit 2af1ea0f8e
4 changed files with 120 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
ChatQnA/chatqna.py
View File

@@ -6,7 +6,8 @@ import json
import os
import re
from comps import Gateway, MegaServiceEndpoint, MicroService, ServiceOrchestrator, ServiceType
from comps import MegaServiceEndpoint, MicroService, ServiceOrchestrator, ServiceRoleType, ServiceType
from comps.cores.mega.utils import handle_message
from comps.cores.proto.api_protocol import (
ChatCompletionRequest,
ChatCompletionResponse,
@@ -187,15 +188,15 @@ def align_generator(self, gen, **kwargs):
yield "data: [DONE]\n\n"
class ChatQnAService(Gateway):
class ChatQnAService:
def __init__(self, host="0.0.0.0", port=8000):
self.host = host
self.port = port
ServiceOrchestrator.align_inputs = align_inputs
ServiceOrchestrator.align_outputs = align_outputs
ServiceOrchestrator.align_generator = align_generator
self.megaservice = ServiceOrchestrator()
self.endpoint = str(MegaServiceEndpoint.CHAT_QNA)
def add_remote_service(self):
@@ -332,7 +333,7 @@ class ChatQnAService(Gateway):
data = await request.json()
stream_opt = data.get("stream", True)
chat_request = ChatCompletionRequest.parse_obj(data)
prompt = self._handle_message(chat_request.messages)
prompt = handle_message(chat_request.messages)
parameters = LLMParams(
max_tokens=chat_request.max_tokens if chat_request.max_tokens else 1024,
top_k=chat_request.top_k if chat_request.top_k else 10,
@@ -379,15 +380,20 @@ class ChatQnAService(Gateway):
def start(self):
super().__init__(
megaservice=self.megaservice,
self.service = MicroService(
self.__class__.__name__,
service_role=ServiceRoleType.MEGASERVICE,
host=self.host,
port=self.port,
endpoint=str(MegaServiceEndpoint.CHAT_QNA),
endpoint=self.endpoint,
input_datatype=ChatCompletionRequest,
output_datatype=ChatCompletionResponse,
)
self.service.add_route(self.endpoint, self.handle_request, methods=["POST"])
self.service.start()
if __name__ == "__main__":
parser = argparse.ArgumentParser()

18
ChatQnA/chatqna_wrapper.py
View File

@@ -3,7 +3,8 @@
import os
from comps import Gateway, MegaServiceEndpoint, MicroService, ServiceOrchestrator, ServiceType
from comps import MegaServiceEndpoint, MicroService, ServiceOrchestrator, ServiceRoleType, ServiceType
from comps.cores.mega.utils import handle_message
from comps.cores.proto.api_protocol import (
ChatCompletionRequest,
ChatCompletionResponse,
@@ -27,11 +28,12 @@ LLM_SERVICE_HOST_IP = os.getenv("LLM_SERVICE_HOST_IP", "0.0.0.0")
LLM_SERVICE_PORT = int(os.getenv("LLM_SERVICE_PORT", 9000))
class ChatQnAService(Gateway):
class ChatQnAService:
def __init__(self, host="0.0.0.0", port=8000):
self.host = host
self.port = port
self.megaservice = ServiceOrchestrator()
self.endpoint = str(MegaServiceEndpoint.CHAT_QNA)
def add_remote_service(self):
embedding = MicroService(
@@ -75,7 +77,7 @@ class ChatQnAService(Gateway):
data = await request.json()
stream_opt = data.get("stream", True)
chat_request = ChatCompletionRequest.parse_obj(data)
prompt = self._handle_message(chat_request.messages)
prompt = handle_message(chat_request.messages)
parameters = LLMParams(
max_tokens=chat_request.max_tokens if chat_request.max_tokens else 1024,
top_k=chat_request.top_k if chat_request.top_k else 10,
@@ -121,15 +123,17 @@ class ChatQnAService(Gateway):
return ChatCompletionResponse(model="chatqna", choices=choices, usage=usage)
def start(self):
super().__init__(
megaservice=self.megaservice,
self.service = MicroService(
self.__class__.__name__,
service_role=ServiceRoleType.MEGASERVICE,
host=self.host,
port=self.port,
endpoint=str(MegaServiceEndpoint.CHAT_QNA),
endpoint=self.endpoint,
input_datatype=ChatCompletionRequest,
output_datatype=ChatCompletionResponse,
)
self.service.add_route(self.endpoint, self.handle_request, methods=["POST"])
self.service.start()
if __name__ == "__main__":

58
DocSum/docsum.py
View File

@@ -5,8 +5,8 @@ import asyncio
import os
from typing import List
from comps import Gateway, MegaServiceEndpoint, MicroService, ServiceOrchestrator, ServiceType
from comps.cores.mega.gateway import read_text_from_file
from comps import MegaServiceEndpoint, MicroService, ServiceOrchestrator, ServiceRoleType, ServiceType
from comps.cores.mega.utils import handle_message
from comps.cores.proto.api_protocol import (
ChatCompletionRequest,
ChatCompletionResponse,
@@ -27,11 +27,47 @@ LLM_SERVICE_HOST_IP = os.getenv("LLM_SERVICE_HOST_IP", "0.0.0.0")
LLM_SERVICE_PORT = int(os.getenv("LLM_SERVICE_PORT", 9000))
class DocSumService(Gateway):
def read_pdf(file):
from langchain.document_loaders import PyPDFLoader
loader = PyPDFLoader(file)
docs = loader.load_and_split()
return docs
def read_text_from_file(file, save_file_name):
import docx2txt
from langchain.text_splitter import CharacterTextSplitter
# read text file
if file.headers["content-type"] == "text/plain":
file.file.seek(0)
content = file.file.read().decode("utf-8")
# Split text
text_splitter = CharacterTextSplitter()
texts = text_splitter.split_text(content)
# Create multiple documents
file_content = texts
# read pdf file
elif file.headers["content-type"] == "application/pdf":
documents = read_pdf(save_file_name)
file_content = [doc.page_content for doc in documents]
# read docx file
elif (
file.headers["content-type"] == "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
or file.headers["content-type"] == "application/octet-stream"
):
file_content = docx2txt.process(save_file_name)
return file_content
class DocSumService:
def __init__(self, host="0.0.0.0", port=8000):
self.host = host
self.port = port
self.megaservice = ServiceOrchestrator()
self.endpoint = str(MegaServiceEndpoint.DOC_SUMMARY)
def add_remote_service(self):
@@ -62,7 +98,7 @@ class DocSumService(Gateway):
data = await request.json()
stream_opt = data.get("stream", True)
chat_request = ChatCompletionRequest.model_validate(data)
prompt = self._handle_message(chat_request.messages)
prompt = handle_message(chat_request.messages)
initial_inputs_data = {data["type"]: prompt}
@@ -98,9 +134,9 @@ class DocSumService(Gateway):
file_summaries.append(docs)
if file_summaries:
prompt = self._handle_message(chat_request.messages) + "\n".join(file_summaries)
prompt = handle_message(chat_request.messages) + "\n".join(file_summaries)
else:
prompt = self._handle_message(chat_request.messages)
prompt = handle_message(chat_request.messages)
data_type = data.get("type")
if data_type is not None:
@@ -151,14 +187,18 @@ class DocSumService(Gateway):
return ChatCompletionResponse(model="docsum", choices=choices, usage=usage)
def start(self):
super().__init__(
megaservice=self.megaservice,
self.service = MicroService(
self.__class__.__name__,
service_role=ServiceRoleType.MEGASERVICE,
host=self.host,
port=self.port,
endpoint=str(MegaServiceEndpoint.DOC_SUMMARY),
endpoint=self.endpoint,
input_datatype=ChatCompletionRequest,
output_datatype=ChatCompletionResponse,
)
self.service.add_route(self.endpoint, self.handle_request, methods=["POST"])
self.service.start()
if __name__ == "__main__":

55
FaqGen/faqgen.py
View File

@@ -5,8 +5,8 @@ import asyncio
import os
from typing import List
from comps import Gateway, MegaServiceEndpoint, MicroService, ServiceOrchestrator, ServiceType
from comps.cores.mega.gateway import read_text_from_file
from comps import MegaServiceEndpoint, MicroService, ServiceOrchestrator, ServiceRoleType, ServiceType
from comps.cores.mega.utils import handle_message
from comps.cores.proto.api_protocol import (
ChatCompletionRequest,
ChatCompletionResponse,
@@ -23,11 +23,47 @@ LLM_SERVICE_HOST_IP = os.getenv("LLM_SERVICE_HOST_IP", "0.0.0.0")
LLM_SERVICE_PORT = int(os.getenv("LLM_SERVICE_PORT", 9000))
class FaqGenService(Gateway):
def read_pdf(file):
from langchain.document_loaders import PyPDFLoader
loader = PyPDFLoader(file)
docs = loader.load_and_split()
return docs
def read_text_from_file(file, save_file_name):
import docx2txt
from langchain.text_splitter import CharacterTextSplitter
# read text file
if file.headers["content-type"] == "text/plain":
file.file.seek(0)
content = file.file.read().decode("utf-8")
# Split text
text_splitter = CharacterTextSplitter()
texts = text_splitter.split_text(content)
# Create multiple documents
file_content = texts
# read pdf file
elif file.headers["content-type"] == "application/pdf":
documents = read_pdf(save_file_name)
file_content = [doc.page_content for doc in documents]
# read docx file
elif (
file.headers["content-type"] == "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
or file.headers["content-type"] == "application/octet-stream"
):
file_content = docx2txt.process(save_file_name)
return file_content
class FaqGenService:
def __init__(self, host="0.0.0.0", port=8000):
self.host = host
self.port = port
self.megaservice = ServiceOrchestrator()
self.endpoint = str(MegaServiceEndpoint.FAQ_GEN)
def add_remote_service(self):
llm = MicroService(
@@ -61,9 +97,9 @@ class FaqGenService(Gateway):
file_summaries.append(docs)
if file_summaries:
prompt = self._handle_message(chat_request.messages) + "\n".join(file_summaries)
prompt = handle_message(chat_request.messages) + "\n".join(file_summaries)
else:
prompt = self._handle_message(chat_request.messages)
prompt = handle_message(chat_request.messages)
parameters = LLMParams(
max_tokens=chat_request.max_tokens if chat_request.max_tokens else 1024,
@@ -101,14 +137,17 @@ class FaqGenService(Gateway):
return ChatCompletionResponse(model="faqgen", choices=choices, usage=usage)
def start(self):
super().__init__(
megaservice=self.megaservice,
self.service = MicroService(
self.__class__.__name__,
service_role=ServiceRoleType.MEGASERVICE,
host=self.host,
port=self.port,
endpoint=str(MegaServiceEndpoint.FAQ_GEN),
endpoint=self.endpoint,
input_datatype=ChatCompletionRequest,
output_datatype=ChatCompletionResponse,
)
self.service.add_route(self.endpoint, self.handle_request, methods=["POST"])
self.service.start()
if __name__ == "__main__":