Skip to main content

No project description provided

Project description

python3 main.py

usage: examples:
        # 初始化配置信息 
        ylz_langchain reset 

        # 启动大语言模型对话
        ylz_langchain start --mode chat
        
        # 测试neo4j
        ylz_langchain neo4j start
       [-h] --mode {llm,chat,prompt,loader,runnable,tools,rag,outputParser,graph,agent,info} [--llm_key LLM_KEY] [--embedding_key EMBEDDING_KEY]
       [--llm_model LLM_MODEL] [--embedding_model EMBEDDING_MODEL] [--message MESSAGE] [--user_id USER_ID] [--conversation_id CONVERSATION_ID] [--url URL]
       [--depth DEPTH] [--rag_indexname RAG_INDEXNAME] [--chat_dbname CHAT_DBNAME] [--query_dbname QUERY_DBNAME] [--docx DOCX] [--pptx PPTX] [--pdf PDF]
       [--glob GLOB] [--websearch {tavily,duckduckgo,serpapi}] [--size SIZE] [--graph {stand,life,engineer,db,selfrag,test,stock}] [--fake_size FAKE_SIZE]
       [--batch BATCH]

options:
  -h, --help            show this help message and exit
  --mode {llm,chat,prompt,loader,runnable,tools,rag,outputParser,graph,agent,info}
                        测试内容
  --llm_key LLM_KEY     语言模型标识,例如:LLM.DEEPSEEK
  --embedding_key EMBEDDING_KEY
                        嵌入模型标识,例如:EMBEDDING.TOGETHER
  --llm_model LLM_MODEL
                        语言模型model
  --embedding_model EMBEDDING_MODEL
                        嵌入模型model
  --message MESSAGE     input message
  --user_id USER_ID     user_id,example: alice
  --conversation_id CONVERSATION_ID
                        conversation_id,example: 123
  --url URL             仅rag,loader使用,下载的URL地址
  --depth DEPTH         仅rag使用,下载的深度,默认为1
  --rag_indexname RAG_INDEXNAME
                        保存的向量索引表,格式为<es|faiss|chroma>:<indexname>
  --chat_dbname CHAT_DBNAME
                        保存的对话数据库
  --query_dbname QUERY_DBNAME
                        测试查询的数据库,默认Chinook.db
  --docx DOCX           docx文档文件名
  --pptx PPTX           pptx文档文件名
  --pdf PDF             pdf文档文件名
  --glob GLOB           当前目录下的glob匹配的文件
  --websearch {tavily,duckduckgo,serpapi}
                        websearch的工具
  --size SIZE           文档分隔的size
  --graph {stand,life,engineer,db,selfrag,test,stock}
                        内置graph的类型
  --fake_size FAKE_SIZE
                        使用fake embeding的size,当fake_size>0是使用fake embeding,并且维度为fake_size
  --batch BATCH         使用生成embeding时的以batch为度量显示进度,默认分隔为10批

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ylz_langchain-0.1.0.tar.gz (94.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

ylz_langchain-0.1.0-py3-none-any.whl (130.7 kB view details)

Uploaded Python 3

File details

Details for the file ylz_langchain-0.1.0.tar.gz.

File metadata

  • Download URL: ylz_langchain-0.1.0.tar.gz
  • Upload date:
  • Size: 94.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.4 CPython/3.13.0 Darwin/21.6.0

File hashes

Hashes for ylz_langchain-0.1.0.tar.gz
Algorithm Hash digest
SHA256 a295a11244d9ca4830169d3b0cf4568ee98cc7c5c6dec5ac280234e30e9d0651
MD5 93f6619293ab7d44896e49f04b6c0401
BLAKE2b-256 79c219b14e10f66cfe8a1ed8476752258b720e787eaaf6a5016cad477ec4c8f4

See more details on using hashes here.

File details

Details for the file ylz_langchain-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: ylz_langchain-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 130.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.4 CPython/3.13.0 Darwin/21.6.0

File hashes

Hashes for ylz_langchain-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 a5a9f4577acf22e2efb7f317641a13b655475e046d5e8d2f8c771a7a200dd398
MD5 37e6951693b9c30856299d477f04793e
BLAKE2b-256 fe3b46b69e8674707b4ff0bba7e5fa93283ebfbd94db1e9edbe77d0c6a4e1eeb

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page