feat(service): remove langchain to add multimodal embedder (#326)

* feat(service): add multimodal embedder
* feat(primitive): remove langchain and re-implement class

Author: tpoisonooo

.gitignore

@@ -56,3 +56,4 @@ evaluation/rejection/gt_bad.txt
 evaluation/rejection/gt_good.txt
 workdir832/
 workdir.bak/
+workdir-20240729-kg-included/

README.md

@@ -9,7 +9,7 @@ work_dir = "workdir"
 
 [web_search]
 engine = "serper"
-# web search engine support `ddgs` and `serper`
+# web search engine support ddgs and serper
 # For ddgs, see https://pypi.org/project/duckduckgo-search
 # For serper, check https://serper.dev/api-key to get a free API key
 serper_x_api_key = "YOUR-API-KEY-HERE"
@@ -20,7 +20,7 @@ save_dir = "logs/web_search_result"
 enable_local = 0
 enable_remote = 1
 # hybrid llm service address
-client_url = "http://127.0.0.1:7777/inference"
+client_url = "http://127.0.0.1:8888/inference"
 
 [llm.server]
 # local LLM configuration
@@ -30,33 +30,44 @@ client_url = "http://127.0.0.1:7777/inference"
 
 local_llm_path = "internlm/internlm2-chat-7b"
 local_llm_max_text_length = 3000
-local_llm_bind_port = 7777
+# llm server listen port
+local_llm_bind_port = 8888
 
 # remote LLM service configuration
-# support "gpt", "kimi", "deepseek", "zhipuai", "step", "xi-api" and "alles-apin"
+# support "gpt", "kimi", "deepseek", "zhipuai", "step", "internlm", "xi-api" and "alles-apin"
+# support "siliconcloud", see https://siliconflow.cn/zh-cn/siliconcloud
 # xi-api and alles-apin is chinese gpt proxy
+# for internlm, see https://internlm.intern-ai.org.cn/api/document
 
-remote_type = "kimi"
+remote_type = "siliconcloud"
 remote_api_key = "YOUR-API-KEY-HERE"
 # max text length for remote LLM.
-# use 128000 for kimi, 192000 for gpt/xi-api, 16000 for deepseek, 128000 for zhipuai
-remote_llm_max_text_length = 128000
+# use 128000 for kimi, 192000 for gpt/xi-api, 16000 for deepseek, 128000 for zhipuai, 40000 for internlm2
+remote_llm_max_text_length = 40000
 # openai API model type, support model list:
 # "auto" for kimi. To save money, we auto select model name by prompt length.
-# "auto" for step to save money, see https://platform.stepfun.com
+# "auto" for step to save money, see https://platform.stepfun.com/
 # "gpt-4-0613" for gpt/xi-api,
 # "deepseek-chat" for deepseek,
 # "glm-4" for zhipuai,
 # "gpt-4-1106-preview" for alles-apin or OpenAOE
-remote_llm_model = "auto"
+# "internlm2-latest" for internlm
+# for example "alibaba/Qwen1.5-110B-Chat", see https://siliconflow.readme.io/reference/chat-completions-1
+remote_llm_model = "alibaba/Qwen1.5-110B-Chat"
 # request per minute
 rpm = 500
 
+[coreference_resolution]
+base_url = 'http://127.0.0.1:9999/v1'
+api_key = 'token-abc123'
+
 [worker]
 # enable web search or not
 enable_web_search = 1
 # enable search enhancement or not
 enable_sg_search = 0
+# enable coreference resolution in `PreprocNode`
+enable_cr = 0
 save_path = "logs/work.txt"
 
 [worker.time]
@@ -68,7 +79,7 @@ has_weekday = 1
 [sg_search]
 # download `src` from https://github.com/sourcegraph/src-cli#installation
 binary_src_path = "/usr/local/bin/src"
-src_access_token = "${YOUR-SRC-ACCESS-TOKEN}"
+src_access_token = "YOUR-SRC-ACCESS-TOKEN"
 
 # add your repo here, we just take opencompass and lmdeploy as example
 [sg_search.opencompass]
@@ -80,12 +91,41 @@ introduction = "用于评测大型语言模型（LLM）. 它提供了完整的
 github_repo_id = "internlm/lmdeploy"
 introduction = "lmdeploy 是一个用于压缩、部署和服务 LLM（Large Language Model）的工具包。是一个服务端场景下，transformer 结构 LLM 部署工具，支持 GPU 服务端部署，速度有保障，支持 Tensor Parallel，多并发优化，功能全面，包括模型转换、缓存历史会话的 cache feature 等. 它还提供了 WebUI、命令行和 gRPC 客户端接入。"
 # introduction = "lmdeploy is a toolkit for compressing, deploying, and servicing Large Language Models (LLMs). It is a deployment tool for transformer-structured LLMs in server-side scenarios, supporting GPU server-side deployment, ensuring speed, and supporting Tensor Parallel along with optimizations for multiple concurrent processes. It offers comprehensive features including model conversion, cache features for caching historical sessions and more. Additionally, it provides access via WebUI, command line, and gRPC clients."
+# add your repo here, we just take opencompass and lmdeploy as example
+
+[sg_search.mmpose]
+github_repo_id = "open-mmlab/mmpose"
+introduction = "MMPose is an open-source toolbox for pose estimation based on PyTorch"
+
+[sg_search.mmdetection]
+github_repo_id = "open-mmlab/mmdetection"
+introduction = "MMDetection is an open source object detection toolbox based on PyTorch."
+
+[sg_search.huixiangdou]
+github_repo_id = "internlm/huixiangdou"
+introduction = "茴香豆是一个基于 LLM 的群聊知识助手。设计拒答、响应两阶段 pipeline 应对群聊场景，解答问题同时不会消息泛滥。"
+
+[sg_search.xtuner]
+github_repo_id = "internlm/xtuner"
+introduction = "XTuner is an efficient, flexible and full-featured toolkit for fine-tuning large models."
+
+[sg_search.mmyolo]
+github_repo_id = "open-mmlab/mmyolo"
+introduction = "OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc."
+
+[sg_search.Amphion]
+github_repo_id = "open-mmlab/Amphion"
+introduction = "Amphion is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development."
+
+[sg_search.mmcv]
+github_repo_id = "open-mmlab/mmcv"
+introduction = "MMCV is a foundational library for computer vision research and it provides image/video processing, image and annotation visualization, image transformation, various CNN architectures and high-quality implementation of common CPU and CUDA ops"
 
 [frontend]
-# chat group assistant type, support "lark", "lark_group", "wechat_personal" and "none"
-# for "lark", open https://open.feishu.cn/document/client-docs/bot-v3/add-custom-bot to add bot, **only send, cannot receive**
+# chat group assistant type, support "lark_group", "wechat_personal", "wechat_wkteam" and "none"
 # for "lark_group", open https://open.feishu.cn/document/home/introduction-to-custom-app-development/self-built-application-development-process to create one
 # for "wechat_personal", read ./docs/add_wechat_group_zh.md to setup gateway
+# for "wkteam", see https://wkteam.cn/
 type = "none"
 
 # for "lark", it is chat group webhook url, send reply to group, for example "https://open.feishu.cn/open-apis/bot/v2/hook/xxxxxxxxxxxxxxx"
@@ -107,3 +147,54 @@ verification_token = "def"
 [frontend.wechat_personal]
 # "wechat_personal" listen port
 bind_port = 9527
+
+[frontend.wechat_wkteam]
+# wechat message callback server ip
+callback_ip = "101.133.161.11"
+callback_port = 9528
+
+# public redis config
+redis_host = "101.133.161.11"
+redis_port = "6380"
+redis_passwd = "hxd123"
+
+# wkteam
+account = ""
+password = ""
+# !!! `proxy` is very import parameter, it's your account location
+# 1：北京 2：天津 3：上海 4：重庆 5：河北
+# 6：山西 7：江苏 8：浙江 9：安徽 10：福建
+# 11：江西 12：山东 13：河南 14：湖北 15：湖南
+# 16：广东 17：海南 18：四川 20：陕西
+# bad proxy would cause account deactivation !!!
+proxy = -1
+
+# save dir
+dir = "wkteam"
+
+# 群号和介绍
+# 茴香豆相关
+[frontend.wechat_wkteam.43925126702]
+name = "茴香豆群（大暑）"
+introduction = "github https://github.com/InternLM/HuixiangDou 用户体验群"
+
+[frontend.wechat_wkteam.44546611710]
+name = "茴香豆群（立夏）"
+introduction = "github https://github.com/InternLM/HuixiangDou 用户体验群"
+
+[frontend.wechat_wkteam.38720590618]
+name = "茴香豆群（惊蛰）"
+introduction = "github https://github.com/InternLM/HuixiangDou 用户体验群"
+
+[frontend.wechat_wkteam.48437885473]
+name = "茴香豆群（谷雨）"
+introduction = "github https://github.com/InternLM/HuixiangDou 用户体验群"
+
+[frontend.wechat_wkteam.34744063953]
+name = "茴香豆群（雨水）"
+introduction = "github https://github.com/InternLM/HuixiangDou 用户体验群"
+
+# github.com/tencent/ncnn contributors
+[frontend.wechat_wkteam.18356748488]
+name = "卷卷群"
+introduction = "ncnn contributors group"

README_zh.md

@@ -0,0 +1,109 @@
+[feature_store]
+# `feature_store.py` use this throttle to distinct `good_questions` and `bad_questions`
+reject_throttle = -1.0
+# text2vec model path, support local relative path and huggingface model format.
+# also support local path, model_path = "/path/to/your/text2vec-model"
+embedding_model_path = "BAAI/bge-m3"
+reranker_model_path = "BAAI/bge-reranker-v2-minicpm-layerwise"
+work_dir = "workdir"
+
+[web_search]
+engine = "serper"
+# web search engine support `ddgs` and `serper`
+# For ddgs, see https://pypi.org/project/duckduckgo-search
+# For serper, check https://serper.dev/api-key to get a free API key
+serper_x_api_key = "YOUR-API-KEY-HERE"
+domain_partial_order = ["openai.com", "pytorch.org", "readthedocs.io", "nvidia.com", "stackoverflow.com", "juejin.cn", "zhuanlan.zhihu.com", "www.cnblogs.com"]
+save_dir = "logs/web_search_result"
+
+[llm]
+enable_local = 0
+enable_remote = 1
+# hybrid llm service address
+client_url = "http://127.0.0.1:7777/inference"
+
+[llm.server]
+# local LLM configuration
+# support "internlm/internlm2-chat-7b" and "qwen/qwen-7b-chat-int8"
+# support local path, for example
+# local_llm_path = "/path/to/your/internlm2"
+
+local_llm_path = "internlm/internlm2-chat-7b"
+local_llm_max_text_length = 3000
+local_llm_bind_port = 7777
+
+# remote LLM service configuration
+# support "gpt", "kimi", "deepseek", "zhipuai", "step", "xi-api" and "alles-apin"
+# xi-api and alles-apin is chinese gpt proxy
+
+remote_type = "kimi"
+remote_api_key = "YOUR-API-KEY-HERE"
+# max text length for remote LLM.
+# use 128000 for kimi, 192000 for gpt/xi-api, 16000 for deepseek, 128000 for zhipuai
+remote_llm_max_text_length = 128000
+# openai API model type, support model list:
+# "auto" for kimi. To save money, we auto select model name by prompt length.
+# "auto" for step to save money, see https://platform.stepfun.com
+# "gpt-4-0613" for gpt/xi-api,
+# "deepseek-chat" for deepseek,
+# "glm-4" for zhipuai,
+# "gpt-4-1106-preview" for alles-apin or OpenAOE
+remote_llm_model = "auto"
+# request per minute
+rpm = 500
+
+[worker]
+# enable web search or not
+enable_web_search = 1
+# enable search enhancement or not
+enable_sg_search = 0
+save_path = "logs/work.txt"
+
+[worker.time]
+enable = 0
+start = "00:00:00"
+end = "23:59:59"
+has_weekday = 1
+
+[sg_search]
+# download `src` from https://github.com/sourcegraph/src-cli#installation
+binary_src_path = "/usr/local/bin/src"
+src_access_token = "${YOUR-SRC-ACCESS-TOKEN}"
+
+# add your repo here, we just take opencompass and lmdeploy as example
+[sg_search.opencompass]
+github_repo_id = "open-compass/opencompass"
+introduction = "用于评测大型语言模型（LLM）. 它提供了完整的开源可复现的评测框架，支持大语言模型、多模态模型的一站式评测，基于分布式技术，对大参数量模型亦能实现高效评测。评测方向汇总为知识、语言、理解、推理、考试五大能力维度，整合集纳了超过70个评测数据集，合计提供了超过40万个模型评测问题，并提供长文本、安全、代码3类大模型特色技术能力评测。"
+# introduction = "For evaluating Large Language Models (LLMs). It provides a fully open-source, reproducible evaluation framework, supporting one-stop evaluation for large language models and multimodal models. Based on distributed technology, it can efficiently evaluate models with a large number of parameters. The evaluation directions are summarized in five capability dimensions: knowledge, language, understanding, reasoning, and examination. It integrates and collects more than 70 evaluation datasets, providing in total over 400,000 model evaluation questions. Additionally, it offers evaluations for three types of capabilities specific to large models: long text, security, and coding."
+
+[sg_search.lmdeploy]
+github_repo_id = "internlm/lmdeploy"
+introduction = "lmdeploy 是一个用于压缩、部署和服务 LLM（Large Language Model）的工具包。是一个服务端场景下，transformer 结构 LLM 部署工具，支持 GPU 服务端部署，速度有保障，支持 Tensor Parallel，多并发优化，功能全面，包括模型转换、缓存历史会话的 cache feature 等. 它还提供了 WebUI、命令行和 gRPC 客户端接入。"
+# introduction = "lmdeploy is a toolkit for compressing, deploying, and servicing Large Language Models (LLMs). It is a deployment tool for transformer-structured LLMs in server-side scenarios, supporting GPU server-side deployment, ensuring speed, and supporting Tensor Parallel along with optimizations for multiple concurrent processes. It offers comprehensive features including model conversion, cache features for caching historical sessions and more. Additionally, it provides access via WebUI, command line, and gRPC clients."
+
+[frontend]
+# chat group assistant type, support "lark", "lark_group", "wechat_personal" and "none"
+# for "lark", open https://open.feishu.cn/document/client-docs/bot-v3/add-custom-bot to add bot, **only send, cannot receive**
+# for "lark_group", open https://open.feishu.cn/document/home/introduction-to-custom-app-development/self-built-application-development-process to create one
+# for "wechat_personal", read ./docs/add_wechat_group_zh.md to setup gateway
+type = "none"
+
+# for "lark", it is chat group webhook url, send reply to group, for example "https://open.feishu.cn/open-apis/bot/v2/hook/xxxxxxxxxxxxxxx"
+# for "lark_group", it is the url to fetch chat group message, for example "http://101.133.161.20:6666/fetch", `101.133.161.20` is your own public IPv4 addr
+# for "wechat_personal", it is useless
+webhook_url = "https://open.feishu.cn/open-apis/bot/v2/hook/xxxxxxxxxxxxxxx"
+
+# when a new group chat message is received, should it be processed immediately or wait for 18 seconds in case the user hasn't finished speaking?
+# support "immediate"
+message_process_policy = "immediate"
+
+[frontend.lark_group]
+# "lark_group" configuration examples, use your own app_id and secret !!!
+app_id = "cli_a53a34dcb778500e"
+app_secret = "2ajhg1ixSvlNm1bJkH4tJhPfTCsGGHT1"
+encrypt_key = "abc"
+verification_token = "def"
+
+[frontend.wechat_personal]
+# "wechat_personal" listen port
+bind_port = 9527

config-2G.ini

@@ -1,6 +1,6 @@
 # 混合知识图谱和稠密检索
 
-通过混合知识图谱和稠密检索，拒答 F1 提升约 2 个点，它的本质是**给高频词加权**。介绍已同步到[飞书](https://aicarrier.feishu.cn/docx/F51pduYyMof8syxKe5RchiU1nIN)。
+通过混合知识图谱和稠密检索，拒答 F1 提升约 2 个点，它的本质是**给高频词加权**。介绍已同步到[飞书](https://aicarrier.feishu.cn/docx/F51pduYyMof8syxKe5RchiU1nIN) 和[知乎](https://zhuanlan.zhihu.com/p/709589834)。
 
 本方案对老版本完美兼容，以下是完整操作步骤。
 

config-multimodal.ini

@@ -0,0 +1,22 @@
+# 单向发到飞书群
+
+这个功能，主要是测试 pipeline 全流程畅通。单向发送的实用意义有限。
+
+点击[创建飞书自定义机器人](https://open.feishu.cn/document/client-docs/bot-v3/add-custom-bot)，获取回调 WEBHOOK_URL，填写到 config.ini
+
+```ini
+# config.ini
+..
+[frontend]
+type = "lark"
+webhook_url = "${YOUR-LARK-WEBHOOK-URL}"
+```
+
+运行。结束后，技术助手的答复将**单向**发送到飞书群。
+
+```shell
+python3 -m huixiangdou.main --standalone # 非 docker 用户
+python3 -m huixiangdou.main # docker 用户
+```
+
+<img src="../resource/figures/lark-example.png" width="400">

docs/knowledge_graph_zh.md

@@ -116,7 +116,7 @@ def calculate(chunk_size: int):
     # 按不同 chunk_size 和 chunk_size，构建特征库
     # 读 input.jsonl 计算 F1
     cache = CacheRetriever(config_path=config_path)
-    fs_init = FeatureStore(embeddings=cache.embeddings,
+    fs_init = FeatureStore(embedder=cache.embedder,
                            config_path=config_path,
                            chunk_size=chunk_size,
                            analyze_reject=True,
@@ -126,8 +126,7 @@ def calculate(chunk_size: int):
     file_opr = FileOperation()
     files = file_opr.scan_dir(repo_dir=repo_dir)
     # fs_init.preprocess(files=files, work_dir=work_dir)
-    # fs_init.build_dense_response(files=files, work_dir=work_dir)
-    # fs_init.build_dense_reject(files=files, work_dir=work_dir)
+    # fs_init.build_dense(files=files, work_dir=work_dir)
     # del fs_init
 
     retriever = CacheRetriever(config_path=config_path).get(

docs/send_only_lark_group_zh.md

@@ -98,8 +98,7 @@ def process(param: tuple):
     config_path = 'config.ini'
     cache = CacheRetriever(config_path=config_path)
 
-    fs_init = FeatureStore(embeddings=cache.embeddings,
-                           config_path=config_path)
+    fs_init = FeatureStore(embedder=cache.embedder, config_path=config_path)
 
     file_opr = FileOperation()
     files = file_opr.scan_dir(repo_dir=filedir)