RETRIEVER Archives - 3 중 3 번째 페이지

[PYTHON/LANGCHAIN] MultiQueryRetriever 클래스 : invoke 메소드 사용하기 1

■ MultiQueryRetriever 클래스의 invoke 메소드를 사용하는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ main.py


import logging

from dotenv import load_dotenv

from langchain_community.document_loaders import WebBaseLoader
from langchain_text_splitters             import RecursiveCharacterTextSplitter
from langchain_openai                     import OpenAIEmbeddings
from langchain_chroma                     import Chroma
from langchain_openai                     import ChatOpenAI
from langchain.retrievers.multi_query     import MultiQueryRetriever

logging.basicConfig()

logger = logging.getLogger("langchain.retrievers.multi_query")

logger.setLevel(logging.INFO)

load_dotenv()

webBaseLoader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")

documentList = webBaseLoader.load()

recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size = 500, chunk_overlap = 0)

splitDocumentList = recursiveCharacterTextSplitter.split_documents(documentList)

openAIEmbeddings = OpenAIEmbeddings()

chroma = Chroma.from_documents(documents = splitDocumentList, embedding = openAIEmbeddings)

vectorStoreRetriever = chroma.as_retriever()

chatOpenAI = ChatOpenAI(temperature = 0)

multiQueryRetriever = MultiQueryRetriever.from_llm(retriever = vectorStoreRetriever, llm = chatOpenAI)

question = "What are the approaches to Task Decomposition?"

responseDocumentList = multiQueryRetriever.invoke(question)

print(len(responseDocumentList))

print(responseDocumentList[0].page_content)

"""
5
Task decomposition can be done (1) by LLM with simple prompting like "Steps for XYZ.\n1.", "What are the subgoals for achieving XYZ?", (2) by using task-specific instructions; e.g. "Write a story outline." for writing a novel, or (3) with human inputs.
"""

import logging

from dotenv import load_dotenv

from langchain_community.document_loaders import WebBaseLoader

from langchain_text_splitters import RecursiveCharacterTextSplitter

from langchain_openai import OpenAIEmbeddings

from langchain_chroma import Chroma

from langchain_openai import ChatOpenAI

from langchain.retrievers.multi_query import MultiQueryRetriever

logging.basicConfig()

logger = logging.getLogger("langchain.retrievers.multi_query")

logger.setLevel(logging.INFO)

load_dotenv()

webBaseLoader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")

documentList = webBaseLoader.load()

recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size = 500, chunk_overlap = 0)

splitDocumentList = recursiveCharacterTextSplitter.split_documents(documentList)

openAIEmbeddings = OpenAIEmbeddings()

chroma = Chroma.from_documents(documents = splitDocumentList, embedding = openAIEmbeddings)

vectorStoreRetriever = chroma.as_retriever()

chatOpenAI = ChatOpenAI(temperature = 0)

multiQueryRetriever = MultiQueryRetriever.from_llm(retriever = vectorStoreRetriever, llm = chatOpenAI)

question = "What are the approaches to Task Decomposition?"

responseDocumentList = multiQueryRetriever.invoke(question)

print(len(responseDocumentList))

print(responseDocumentList[0].page_content)

"""

Task decomposition can be done (1) by LLM with simple prompting like "Steps for XYZ.\n1.", "What are the subgoals for achieving XYZ?", (2) by using task-specific instructions; e.g. "Write a story outline." for writing a novel, or (3) with human inputs.

"""

▶ requirements.txt


aiohappyeyeballs==2.3.5
aiohttp==3.10.3
aiosignal==1.3.1
annotated-types==0.7.0
anyio==4.4.0
asgiref==3.8.1
async-timeout==4.0.3
attrs==24.2.0
backoff==2.2.1
bcrypt==4.2.0
beautifulsoup4==4.12.3
bs4==0.0.2
build==1.2.1
cachetools==5.4.0
certifi==2024.7.4
charset-normalizer==3.3.2
chroma-hnswlib==0.7.6
chromadb==0.5.5
click==8.1.7
coloredlogs==15.0.1
dataclasses-json==0.6.7
Deprecated==1.2.14
distro==1.9.0
exceptiongroup==1.2.2
fastapi==0.112.0
filelock==3.15.4
flatbuffers==24.3.25
frozenlist==1.4.1
fsspec==2024.6.1
google-auth==2.33.0
googleapis-common-protos==1.63.2
greenlet==3.0.3
grpcio==1.65.4
h11==0.14.0
httpcore==1.0.5
httptools==0.6.1
httpx==0.27.0
huggingface-hub==0.24.5
humanfriendly==10.0
idna==3.7
importlib_metadata==8.0.0
importlib_resources==6.4.0
jiter==0.5.0
jsonpatch==1.33
jsonpointer==3.0.0
kubernetes==30.1.0
langchain==0.2.12
langchain-chroma==0.1.2
langchain-community==0.2.11
langchain-core==0.2.29
langchain-openai==0.1.21
langchain-text-splitters==0.2.2
langsmith==0.1.98
markdown-it-py==3.0.0
marshmallow==3.21.3
mdurl==0.1.2
mmh3==4.1.0
monotonic==1.6
mpmath==1.3.0
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
oauthlib==3.2.2
onnxruntime==1.18.1
openai==1.40.3
opentelemetry-api==1.26.0
opentelemetry-exporter-otlp-proto-common==1.26.0
opentelemetry-exporter-otlp-proto-grpc==1.26.0
opentelemetry-instrumentation==0.47b0
opentelemetry-instrumentation-asgi==0.47b0
opentelemetry-instrumentation-fastapi==0.47b0
opentelemetry-proto==1.26.0
opentelemetry-sdk==1.26.0
opentelemetry-semantic-conventions==0.47b0
opentelemetry-util-http==0.47b0
orjson==3.10.7
overrides==7.7.0
packaging==24.1
posthog==3.5.0
protobuf==4.25.4
pyasn1==0.6.0
pyasn1_modules==0.4.0
pydantic==2.8.2
pydantic_core==2.20.1
Pygments==2.18.0
PyPika==0.48.9
pyproject_hooks==1.1.0
python-dateutil==2.9.0.post0
python-dotenv==1.0.1
PyYAML==6.0.2
regex==2024.7.24
requests==2.32.3
requests-oauthlib==2.0.0
rich==13.7.1
rsa==4.9
shellingham==1.5.4
six==1.16.0
sniffio==1.3.1
soupsieve==2.5
SQLAlchemy==2.0.32
starlette==0.37.2
sympy==1.13.1
tenacity==8.5.0
tiktoken==0.7.0
tokenizers==0.20.0
tomli==2.0.1
tqdm==4.66.5
typer==0.12.3
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
uvicorn==0.30.5
uvloop==0.19.0
watchfiles==0.23.0
websocket-client==1.8.0
websockets==12.0
wrapt==1.16.0
yarl==1.9.4
zipp==3.19.2

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

aiohappyeyeballs==2.3.5

aiohttp==3.10.3

aiosignal==1.3.1

annotated-types==0.7.0

anyio==4.4.0

asgiref==3.8.1

async-timeout==4.0.3

attrs==24.2.0

backoff==2.2.1

bcrypt==4.2.0

beautifulsoup4==4.12.3

bs4==0.0.2

build==1.2.1

cachetools==5.4.0

certifi==2024.7.4

charset-normalizer==3.3.2

chroma-hnswlib==0.7.6

chromadb==0.5.5

click==8.1.7

coloredlogs==15.0.1

dataclasses-json==0.6.7

Deprecated==1.2.14

distro==1.9.0

exceptiongroup==1.2.2

fastapi==0.112.0

filelock==3.15.4

flatbuffers==24.3.25

frozenlist==1.4.1

fsspec==2024.6.1

google-auth==2.33.0

googleapis-common-protos==1.63.2

greenlet==3.0.3

grpcio==1.65.4

h11==0.14.0

httpcore==1.0.5

httptools==0.6.1

httpx==0.27.0

huggingface-hub==0.24.5

humanfriendly==10.0

idna==3.7

importlib_metadata==8.0.0

importlib_resources==6.4.0

jiter==0.5.0

jsonpatch==1.33

jsonpointer==3.0.0

kubernetes==30.1.0

langchain==0.2.12

langchain-chroma==0.1.2

langchain-community==0.2.11

langchain-core==0.2.29

langchain-openai==0.1.21

langchain-text-splitters==0.2.2

langsmith==0.1.98

markdown-it-py==3.0.0

marshmallow==3.21.3

mdurl==0.1.2

mmh3==4.1.0

monotonic==1.6

mpmath==1.3.0

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

oauthlib==3.2.2

onnxruntime==1.18.1

openai==1.40.3

opentelemetry-api==1.26.0

opentelemetry-exporter-otlp-proto-common==1.26.0

opentelemetry-exporter-otlp-proto-grpc==1.26.0

opentelemetry-instrumentation==0.47b0

opentelemetry-instrumentation-asgi==0.47b0

opentelemetry-instrumentation-fastapi==0.47b0

opentelemetry-proto==1.26.0

opentelemetry-sdk==1.26.0

opentelemetry-semantic-conventions==0.47b0

opentelemetry-util-http==0.47b0

orjson==3.10.7

overrides==7.7.0

packaging==24.1

posthog==3.5.0

protobuf==4.25.4

pyasn1==0.6.0

pyasn1_modules==0.4.0

pydantic==2.8.2

pydantic_core==2.20.1

Pygments==2.18.0

PyPika==0.48.9

pyproject_hooks==1.1.0

python-dateutil==2.9.0.post0

python-dotenv==1.0.1

PyYAML==6.0.2

regex==2024.7.24

requests==2.32.3

requests-oauthlib==2.0.0

rich==13.7.1

rsa==4.9

shellingham==1.5.4

six==1.16.0

sniffio==1.3.1

soupsieve==2.5

SQLAlchemy==2.0.32

starlette==0.37.2

sympy==1.13.1

tenacity==8.5.0

tiktoken==0.7.0

tokenizers==0.20.0

tomli==2.0.1

tqdm==4.66.5

typer==0.12.3

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

uvicorn==0.30.5

uvloop==0.19.0

watchfiles==0.23.0

websocket-client==1.8.0

websockets==12.0

wrapt==1.16.0

yarl==1.9.4

zipp==3.19.2

[PYTHON/LANGCHAIN] MultiQueryRetriever 클래스 : 생성자에서 retriever/llm_chain/parser_key 인자를 사용해 MultiQueryRetriever 객체 만들기

■ MultiQueryRetriever 클래스의 생성자에서 retriever/llm_chain/parser_key 인자를 사용해 MultiQueryRetriever 객체를 만드는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ 예제

[PYTHON/LANGCHAIN] from_llm 함수 : retriever/llm 인자를 사용해 multiQueryRetriever 객체 만들기

■ from_llm 함수의 retriever/llm 인자를 사용해 multiQueryRetriever 객체를 만드는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ 예제 코드

[PYTHON/LANGCHAIN] FAISS 클래스 : as_retriever 메소드에서 search_type/search_kwargs 인자를 사용해 벡터 스토어 검색기 구하기

■ FAISS 클래스의 as_retriever 메소드에서 search_type/search_kwargs 인자를 사용해 벡터 스토어 검색기를 구하는 방법을 보여준다. ※ 유사도 점수 임계값을 설정하여 해당 임계값보다 높은

[PYTHON/LANGCHAIN] FAISS 클래스 : as_retriever 메소드에서 search_type 인자를 사용해 벡터 스토어 검색기 구하기

■ FAISS 클래스의 as_retriever 메소드에서 search_type 인자를 사용해 벡터 스토어 검색기를 구하는 방법을 보여준다. ※ 기본적으로 벡터 스토어 검색기는 유사성 검색을 사용한다.

[PYTHON/LANGCHAIN] VectorStoreRetriever 클래스 : invoke 메소드 사용하기 1

■ VectorStoreRetriever 클래스의 invoke 메소드를 사용하는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ main.py


from dotenv import load_dotenv

from langchain_community.document_loaders import TextLoader
from langchain_text_splitters             import CharacterTextSplitter
from langchain_openai                     import OpenAIEmbeddings
from langchain_community.vectorstores     import FAISS

load_dotenv()

textLoader = TextLoader("state_of_the_union.txt")

documentList = textLoader.load()

characterTextSplitter = CharacterTextSplitter(chunk_size = 1000, chunk_overlap = 0)

splitDocumentList = characterTextSplitter.split_documents(documentList)

openAIEmbeddings = OpenAIEmbeddings()

faiss = FAISS.from_documents(splitDocumentList, openAIEmbeddings)

vectorStoreRetriever = faiss.as_retriever()

responseDocumentList = vectorStoreRetriever.invoke("what did the president say about ketanji brown jackson?")

print(len(responseDocumentList))

print(responseDocumentList[0].page_content)

"""
4
Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections.

Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.

One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.

And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.
"""

from dotenv import load_dotenv

from langchain_community.document_loaders import TextLoader

from langchain_text_splitters import CharacterTextSplitter

from langchain_openai import OpenAIEmbeddings

from langchain_community.vectorstores import FAISS

load_dotenv()

textLoader = TextLoader("state_of_the_union.txt")

documentList = textLoader.load()

characterTextSplitter = CharacterTextSplitter(chunk_size = 1000, chunk_overlap = 0)

splitDocumentList = characterTextSplitter.split_documents(documentList)

openAIEmbeddings = OpenAIEmbeddings()

faiss = FAISS.from_documents(splitDocumentList, openAIEmbeddings)

vectorStoreRetriever = faiss.as_retriever()

responseDocumentList = vectorStoreRetriever.invoke("what did the president say about ketanji brown jackson?")

print(len(responseDocumentList))

print(responseDocumentList[0].page_content)

"""

Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections.

Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.

One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.

And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.

"""

▶ requirements.txt


aiohappyeyeballs==2.3.5
aiohttp==3.10.3
aiosignal==1.3.1
annotated-types==0.7.0
anyio==4.4.0
async-timeout==4.0.3
attrs==24.2.0
certifi==2024.7.4
charset-normalizer==3.3.2
dataclasses-json==0.6.7
distro==1.9.0
exceptiongroup==1.2.2
faiss-gpu==1.7.2
frozenlist==1.4.1
greenlet==3.0.3
h11==0.14.0
httpcore==1.0.5
httpx==0.27.0
idna==3.7
jiter==0.5.0
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.12
langchain-community==0.2.11
langchain-core==0.2.29
langchain-openai==0.1.21
langchain-text-splitters==0.2.2
langsmith==0.1.98
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
openai==1.40.3
orjson==3.10.7
packaging==24.1
pydantic==2.8.2
pydantic_core==2.20.1
python-dotenv==1.0.1
PyYAML==6.0.2
regex==2024.7.24
requests==2.32.3
sniffio==1.3.1
SQLAlchemy==2.0.32
tenacity==8.5.0
tiktoken==0.7.0
tqdm==4.66.5
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.2
yarl==1.9.4

aiohappyeyeballs==2.3.5

aiohttp==3.10.3

aiosignal==1.3.1

annotated-types==0.7.0

anyio==4.4.0

async-timeout==4.0.3

attrs==24.2.0

certifi==2024.7.4

charset-normalizer==3.3.2

dataclasses-json==0.6.7

distro==1.9.0

exceptiongroup==1.2.2

faiss-gpu==1.7.2

frozenlist==1.4.1

greenlet==3.0.3

h11==0.14.0

httpcore==1.0.5

httpx==0.27.0

idna==3.7

jiter==0.5.0

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.12

langchain-community==0.2.11

langchain-core==0.2.29

langchain-openai==0.1.21

langchain-text-splitters==0.2.2

langsmith==0.1.98

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

openai==1.40.3

orjson==3.10.7

packaging==24.1

pydantic==2.8.2

pydantic_core==2.20.1

python-dotenv==1.0.1

PyYAML==6.0.2

regex==2024.7.24

requests==2.32.3

sniffio==1.3.1

SQLAlchemy==2.0.32

tenacity==8.5.0

tiktoken==0.7.0

tqdm==4.66.5

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.2

yarl==1.9.4

[PYTHON/LANGCHAIN] FAISS 클래스 : as_retriever 메소드를 사용해 벡터 스토어 검색기 구하기

■ FAISS 클래스의 as_retriever 메소드를 사용해 벡터 스토어 검색기를 구하는 방법을 보여준다. ※ OPENAI_API_KEY 환경 변수 값은 .env 파일에 정의한다. ▶ 예제

[PYTHON/LANGCHAIN] RunnableSequence 클래스 : 문서 검색 모듈과 질문/답변 생성 모듈 연결하기

■ RunnableSequence 클래스를 사용해 문서 검색 모듈과 질문/답변 생성 모듈을 연결하는 방법을 보여준다. ※ [create_retrieval_chain 함수 : 문서 검색 모듈과 질문/답변 생성

[PYTHON/LANGCHAIN] VectorStoreRetriever 클래스 : 사용자 질문에 따라 벡터 저장소에서 문서 자동 검색하기

■ VectorStoreRetriever 클래스 : 사용자 질문에 따라 벡터 저장소에서 문서 자동 검색하기 ▶ main.py


from langchain_community.document_loaders import WebBaseLoader
from langchain_text_splitters             import RecursiveCharacterTextSplitter
from langchain_huggingface                import HuggingFaceEmbeddings
from langchain_chroma                     import Chroma
from langchain_community.llms             import LlamaCpp
from langchain                            import hub
from langchain_core.output_parsers        import StrOutputParser
from langchain_core.runnables             import RunnablePassthrough

# 웹 문서를 로드한다.
webBaseLoader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")

documentList = webBaseLoader.load()

# 문서를 분할한다.
recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)

splitDocumentList = recursiveCharacterTextSplitter.split_documents(documentList)

# 임베딩 생성 및 유사도 검색을 위한 벡터 저장소를 설정한다.
chroma = Chroma.from_documents(documents = splitDocumentList, embedding = HuggingFaceEmbeddings())

# 벡터 저장소 검색기를 설정한다.
vectorStoreRetriever = chroma.as_retriever()

# LLM 모델을 설정한다.
gpuLayerCount = 1
batchSize     = 512 # 1에서 n_ctx 사이이어야 한다.

llamaCpp = LlamaCpp(
    model_path   = "./llama-2-13b-chat.Q4_0.gguf", # llama-2-13b-chat.Q4_0.gguf 파일 경로를 설정한다.
    n_gpu_layers = gpuLayerCount,
    n_batch      = batchSize,
    n_ctx        = 2048,
    f16_kv       = True, # 반드시 True로 설정해야 한다. 그렇지 않으면 몇 번의 호출 후에 문제가 발생하게 된다.
    verbose      = False
)

# 프롬프트 템플리트를 설정한다.
promptTemplate = hub.pull("rlm/rag-prompt")

# 문서 페이지 컨텐츠를 병합하는 함수를 정의한다.
def mergeDocumentPageContent(documentList):
    return "\n\n".join(doc.page_content for doc in documentList)

# 실행 체인을 설정한다.
runnableSequence = (
    {"context": vectorStoreRetriever | mergeDocumentPageContent, "question" : RunnablePassthrough()}
    | promptTemplate
    | llamaCpp
    | StrOutputParser()
)

# 질의 응답을 실행한다.
resultString = runnableSequence.invoke("What are the approaches to Task Decomposition?")

print(resultString)

"""
 The approaches to task decomposition include breaking down large tasks into smaller subgoals, using task-specific instructions, and using human inputs.
"""

from langchain_community.document_loaders import WebBaseLoader

from langchain_text_splitters import RecursiveCharacterTextSplitter

from langchain_huggingface import HuggingFaceEmbeddings

from langchain_chroma import Chroma

from langchain_community.llms import LlamaCpp

from langchain import hub

from langchain_core.output_parsers import StrOutputParser

from langchain_core.runnables import RunnablePassthrough

# 웹 문서를 로드한다.

webBaseLoader = WebBaseLoader("https://lilianweng.github.io/posts/2023-06-23-agent/")

documentList = webBaseLoader.load()

# 문서를 분할한다.

recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)

splitDocumentList = recursiveCharacterTextSplitter.split_documents(documentList)

# 임베딩 생성 및 유사도 검색을 위한 벡터 저장소를 설정한다.

chroma = Chroma.from_documents(documents = splitDocumentList, embedding = HuggingFaceEmbeddings())

# 벡터 저장소 검색기를 설정한다.

vectorStoreRetriever = chroma.as_retriever()

# LLM 모델을 설정한다.

gpuLayerCount = 1

batchSize = 512 # 1에서 n_ctx 사이이어야 한다.

llamaCpp = LlamaCpp(

model_path = "./llama-2-13b-chat.Q4_0.gguf", # llama-2-13b-chat.Q4_0.gguf 파일 경로를 설정한다.

n_gpu_layers = gpuLayerCount,

n_batch = batchSize,

n_ctx = 2048,

f16_kv = True, # 반드시 True로 설정해야 한다. 그렇지 않으면 몇 번의 호출 후에 문제가 발생하게 된다.

verbose = False

)

# 프롬프트 템플리트를 설정한다.

promptTemplate = hub.pull("rlm/rag-prompt")

# 문서 페이지 컨텐츠를 병합하는 함수를 정의한다.

def mergeDocumentPageContent(documentList):

return "\n\n".join(doc.page_content for doc in documentList)

# 실행 체인을 설정한다.

runnableSequence = (

{"context": vectorStoreRetriever | mergeDocumentPageContent, "question" : RunnablePassthrough()}

| promptTemplate

| llamaCpp

| StrOutputParser()

)

# 질의 응답을 실행한다.

resultString = runnableSequence.invoke("What are the approaches to Task Decomposition?")

print(resultString)

"""

The approaches to task decomposition include breaking down large tasks into smaller subgoals, using task-specific instructions, and using human inputs.

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
anyio==4.4.0
asgiref==3.8.1
async-timeout==4.0.3
attrs==23.2.0
backoff==2.2.1
bcrypt==4.1.3
beautifulsoup4==4.12.3
bs4==0.0.2
build==1.2.1
cachetools==5.3.3
certifi==2024.6.2
charset-normalizer==3.3.2
chroma-hnswlib==0.7.3
chromadb==0.5.0
click==8.1.7
coloredlogs==15.0.1
dataclasses-json==0.6.7
Deprecated==1.2.14
diskcache==5.6.3
dnspython==2.6.1
email_validator==2.1.1
exceptiongroup==1.2.1
fastapi==0.111.0
fastapi-cli==0.0.4
filelock==3.15.1
flatbuffers==24.3.25
frozenlist==1.4.1
fsspec==2024.6.0
google-auth==2.30.0
googleapis-common-protos==1.63.1
greenlet==3.0.3
grpcio==1.64.1
h11==0.14.0
httpcore==1.0.5
httptools==0.6.1
httpx==0.27.0
huggingface-hub==0.23.3
humanfriendly==10.0
idna==3.7
importlib_metadata==7.1.0
importlib_resources==6.4.0
Jinja2==3.1.4
joblib==1.4.2
jsonpatch==1.33
jsonpointer==3.0.0
kubernetes==30.1.0
langchain==0.2.4
langchain-chroma==0.1.1
langchain-community==0.2.4
langchain-core==0.2.6
langchain-huggingface==0.0.3
langchain-text-splitters==0.2.1
langsmith==0.1.77
llama_cpp_python==0.2.78
markdown-it-py==3.0.0
MarkupSafe==2.1.5
marshmallow==3.21.3
mdurl==0.1.2
mmh3==4.1.0
monotonic==1.6
mpmath==1.3.0
multidict==6.0.5
mypy-extensions==1.0.0
networkx==3.3
numpy==1.26.4
nvidia-cublas-cu12==12.1.3.1
nvidia-cuda-cupti-cu12==12.1.105
nvidia-cuda-nvrtc-cu12==12.1.105
nvidia-cuda-runtime-cu12==12.1.105
nvidia-cudnn-cu12==8.9.2.26
nvidia-cufft-cu12==11.0.2.54
nvidia-curand-cu12==10.3.2.106
nvidia-cusolver-cu12==11.4.5.107
nvidia-cusparse-cu12==12.1.0.106
nvidia-nccl-cu12==2.20.5
nvidia-nvjitlink-cu12==12.5.40
nvidia-nvtx-cu12==12.1.105
oauthlib==3.2.2
onnxruntime==1.18.0
opentelemetry-api==1.25.0
opentelemetry-exporter-otlp-proto-common==1.25.0
opentelemetry-exporter-otlp-proto-grpc==1.25.0
opentelemetry-instrumentation==0.46b0
opentelemetry-instrumentation-asgi==0.46b0
opentelemetry-instrumentation-fastapi==0.46b0
opentelemetry-proto==1.25.0
opentelemetry-sdk==1.25.0
opentelemetry-semantic-conventions==0.46b0
opentelemetry-util-http==0.46b0
orjson==3.10.5
overrides==7.7.0
packaging==24.1
pillow==10.3.0
posthog==3.5.0
protobuf==4.25.3
pyasn1==0.6.0
pyasn1_modules==0.4.0
pydantic==2.7.4
pydantic_core==2.18.4
Pygments==2.18.0
PyPika==0.48.9
pyproject_hooks==1.1.0
python-dateutil==2.9.0.post0
python-dotenv==1.0.1
python-multipart==0.0.9
PyYAML==6.0.1
regex==2024.5.15
requests==2.32.3
requests-oauthlib==2.0.0
rich==13.7.1
rsa==4.9
safetensors==0.4.3
scikit-learn==1.5.0
scipy==1.13.1
sentence-transformers==3.0.1
shellingham==1.5.4
six==1.16.0
sniffio==1.3.1
soupsieve==2.5
SQLAlchemy==2.0.30
starlette==0.37.2
sympy==1.12.1
tenacity==8.3.0
threadpoolctl==3.5.0
tokenizers==0.19.1
tomli==2.0.1
torch==2.3.1
tqdm==4.66.4
transformers==4.41.2
triton==2.3.1
typer==0.12.3
typing-inspect==0.9.0
typing_extensions==4.12.2
ujson==5.10.0
urllib3==2.2.1
uvicorn==0.30.1
uvloop==0.19.0
watchfiles==0.22.0
websocket-client==1.8.0
websockets==12.0
wrapt==1.16.0
yarl==1.9.4
zipp==3.19.2

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

128

129

130

131

132

133

134

135

136

137

138

139

140

141

142

143

144

145

146

147

148

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

anyio==4.4.0

asgiref==3.8.1

async-timeout==4.0.3

attrs==23.2.0

backoff==2.2.1

bcrypt==4.1.3

beautifulsoup4==4.12.3

bs4==0.0.2

build==1.2.1

cachetools==5.3.3

certifi==2024.6.2

charset-normalizer==3.3.2

chroma-hnswlib==0.7.3

chromadb==0.5.0

click==8.1.7

coloredlogs==15.0.1

dataclasses-json==0.6.7

Deprecated==1.2.14

diskcache==5.6.3

dnspython==2.6.1

email_validator==2.1.1

exceptiongroup==1.2.1

fastapi==0.111.0

fastapi-cli==0.0.4

filelock==3.15.1

flatbuffers==24.3.25

frozenlist==1.4.1

fsspec==2024.6.0

google-auth==2.30.0

googleapis-common-protos==1.63.1

greenlet==3.0.3

grpcio==1.64.1

h11==0.14.0

httpcore==1.0.5

httptools==0.6.1

httpx==0.27.0

huggingface-hub==0.23.3

humanfriendly==10.0

idna==3.7

importlib_metadata==7.1.0

importlib_resources==6.4.0

Jinja2==3.1.4

joblib==1.4.2

jsonpatch==1.33

jsonpointer==3.0.0

kubernetes==30.1.0

langchain==0.2.4

langchain-chroma==0.1.1

langchain-community==0.2.4

langchain-core==0.2.6

langchain-huggingface==0.0.3

langchain-text-splitters==0.2.1

langsmith==0.1.77

llama_cpp_python==0.2.78

markdown-it-py==3.0.0

MarkupSafe==2.1.5

marshmallow==3.21.3

mdurl==0.1.2

mmh3==4.1.0

monotonic==1.6

mpmath==1.3.0

multidict==6.0.5

mypy-extensions==1.0.0

networkx==3.3

numpy==1.26.4

nvidia-cublas-cu12==12.1.3.1

nvidia-cuda-cupti-cu12==12.1.105

nvidia-cuda-nvrtc-cu12==12.1.105

nvidia-cuda-runtime-cu12==12.1.105

nvidia-cudnn-cu12==8.9.2.26

nvidia-cufft-cu12==11.0.2.54

nvidia-curand-cu12==10.3.2.106

nvidia-cusolver-cu12==11.4.5.107

nvidia-cusparse-cu12==12.1.0.106

nvidia-nccl-cu12==2.20.5

nvidia-nvjitlink-cu12==12.5.40

nvidia-nvtx-cu12==12.1.105

oauthlib==3.2.2

onnxruntime==1.18.0

opentelemetry-api==1.25.0

opentelemetry-exporter-otlp-proto-common==1.25.0

opentelemetry-exporter-otlp-proto-grpc==1.25.0

opentelemetry-instrumentation==0.46b0

opentelemetry-instrumentation-asgi==0.46b0

opentelemetry-instrumentation-fastapi==0.46b0

opentelemetry-proto==1.25.0

opentelemetry-sdk==1.25.0

opentelemetry-semantic-conventions==0.46b0

opentelemetry-util-http==0.46b0

orjson==3.10.5

overrides==7.7.0

packaging==24.1

pillow==10.3.0

posthog==3.5.0

protobuf==4.25.3

pyasn1==0.6.0

pyasn1_modules==0.4.0

pydantic==2.7.4

pydantic_core==2.18.4

Pygments==2.18.0

PyPika==0.48.9

pyproject_hooks==1.1.0

python-dateutil==2.9.0.post0

python-dotenv==1.0.1

python-multipart==0.0.9

PyYAML==6.0.1

regex==2024.5.15

requests==2.32.3

requests-oauthlib==2.0.0

rich==13.7.1

rsa==4.9

safetensors==0.4.3

scikit-learn==1.5.0

scipy==1.13.1

sentence-transformers==3.0.1

shellingham==1.5.4

six==1.16.0

sniffio==1.3.1

soupsieve==2.5

SQLAlchemy==2.0.30

starlette==0.37.2

sympy==1.12.1

tenacity==8.3.0

threadpoolctl==3.5.0

tokenizers==0.19.1

tomli==2.0.1

torch==2.3.1

tqdm==4.66.4

transformers==4.41.2

triton==2.3.1

typer==0.12.3

typing-inspect==0.9.0

typing_extensions==4.12.2

ujson==5.10.0

urllib3==2.2.1

uvicorn==0.30.1

uvloop==0.19.0

watchfiles==0.22.0

websocket-client==1.8.0

websockets==12.0

wrapt==1.16.0

yarl==1.9.4

zipp==3.19.2

※ pip install langchain

[PYTHON/LANGCHAIN] create_retriever_tool 함수 : FAISS 벡터 스토어 검색 도구 만들기 1

■ create_retriever_tool 함수를 사용해 FAISS 벡터 스토어 검색 도구를 만드는 방법을 보여준다. ▶ main.py


import ast
import os
import re

from langchain_community.utilities    import SQLDatabase
from langchain_community.vectorstores import FAISS
from langchain_openai                 import OpenAIEmbeddings
from langchain.agents.agent_toolkits  import create_retriever_tool

os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>"

# SQLITE 데이터베이스를 초기화한다.
sqlDatabase = SQLDatabase.from_uri("sqlite:///chinook.db")

# SQLite 데이터를 가져오는 함수를 정의한다.
def getSQLiteData(sqlDatabase, sql):
    resultString    = sqlDatabase.run(sql)
    resultTupleList = ast.literal_eval(resultString)
    resultList1     = [element for resultTuple in resultTupleList for element in resultTuple if element]
    resultList2     = [re.sub(r"\b\d+\b", "", result).strip() for result in resultList1]
    return list(set(resultList2))

# 아티스트명, 앨범 타이틀 리스트를 구한다.
artistNameList = getSQLiteData(sqlDatabase, "SELECT Name  FROM artists")
albumTitleList = getSQLiteData(sqlDatabase, "SELECT Title FROM albums" )

# FAISS 벡터 스토어를 생성한다:
faiss = FAISS.from_texts(artistNameList + albumTitleList, OpenAIEmbeddings())

# FAISS 벡터 스토어 검색기를 설정한다.
faissVectorStoreRetriever = faiss.as_retriever(search_kwargs = {"k" : 5})

# FAISS 벡터 스토어 검색기 도구를 생성한다.
faissVectorStoreRetrieverTool = create_retriever_tool(
    faissVectorStoreRetriever,
    name        = "search_proper_nouns",
    description = "Use to look up values to filter on. Input is an approximate spelling of the proper noun, output is valid proper nouns. Use the noun most similar to the search."
)

# FAISS 벡터 스토어 검색기 도구를 실행한다.
resultString = faissVectorStoreRetrieverTool.invoke("Alice Chains")

print(resultString)

"""
Alice In Chains

Alanis Morissette

Pearl Jam

Pearl Jam

Audioslave
"""

import ast

import os

import re

from langchain_community.utilities import SQLDatabase

from langchain_community.vectorstores import FAISS

from langchain_openai import OpenAIEmbeddings

from langchain.agents.agent_toolkits import create_retriever_tool

os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>"

# SQLITE 데이터베이스를 초기화한다.

sqlDatabase = SQLDatabase.from_uri("sqlite:///chinook.db")

# SQLite 데이터를 가져오는 함수를 정의한다.

def getSQLiteData(sqlDatabase, sql):

resultString = sqlDatabase.run(sql)

resultTupleList = ast.literal_eval(resultString)

resultList1 = [element for resultTuple in resultTupleList for element in resultTuple if element]

resultList2 = [re.sub(r"\b\d+\b", "", result).strip() for result in resultList1]

return list(set(resultList2))

# 아티스트명, 앨범 타이틀 리스트를 구한다.

artistNameList = getSQLiteData(sqlDatabase, "SELECT Name FROM artists")

albumTitleList = getSQLiteData(sqlDatabase, "SELECT Title FROM albums" )

# FAISS 벡터 스토어를 생성한다:

faiss = FAISS.from_texts(artistNameList + albumTitleList, OpenAIEmbeddings())

# FAISS 벡터 스토어 검색기를 설정한다.

faissVectorStoreRetriever = faiss.as_retriever(search_kwargs = {"k" : 5})

# FAISS 벡터 스토어 검색기 도구를 생성한다.

faissVectorStoreRetrieverTool = create_retriever_tool(

faissVectorStoreRetriever,

name = "search_proper_nouns",

description = "Use to look up values to filter on. Input is an approximate spelling of the proper noun, output is valid proper nouns. Use the noun most similar to the search."

)

# FAISS 벡터 스토어 검색기 도구를 실행한다.

resultString = faissVectorStoreRetrieverTool.invoke("Alice Chains")

print(resultString)

"""

Alice In Chains

Alanis Morissette

Pearl Jam

Audioslave

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
anyio==4.4.0
async-timeout==4.0.3
attrs==23.2.0
certifi==2024.6.2
charset-normalizer==3.3.2
dataclasses-json==0.6.7
distro==1.9.0
exceptiongroup==1.2.1
faiss-gpu==1.7.2
frozenlist==1.4.1
greenlet==3.0.3
h11==0.14.0
httpcore==1.0.5
httpx==0.27.0
idna==3.7
jsonpatch==1.33
jsonpointer==3.0.0
langchain==0.2.3
langchain-community==0.2.4
langchain-core==0.2.5
langchain-openai==0.1.8
langchain-text-splitters==0.2.1
langsmith==0.1.77
marshmallow==3.21.3
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
openai==1.33.0
orjson==3.10.4
packaging==23.2
pydantic==2.7.4
pydantic_core==2.18.4
PyYAML==6.0.1
regex==2024.5.15
requests==2.32.3
sniffio==1.3.1
SQLAlchemy==2.0.30
tenacity==8.3.0
tiktoken==0.7.0
tqdm==4.66.4
typing-inspect==0.9.0
typing_extensions==4.12.2
urllib3==2.2.1
yarl==1.9.4

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

anyio==4.4.0

async-timeout==4.0.3

attrs==23.2.0

certifi==2024.6.2

charset-normalizer==3.3.2

dataclasses-json==0.6.7

distro==1.9.0

exceptiongroup==1.2.1

faiss-gpu==1.7.2

frozenlist==1.4.1

greenlet==3.0.3

h11==0.14.0

httpcore==1.0.5

httpx==0.27.0

idna==3.7

jsonpatch==1.33

jsonpointer==3.0.0

langchain==0.2.3

langchain-community==0.2.4

langchain-core==0.2.5

langchain-openai==0.1.8

langchain-text-splitters==0.2.1

langsmith==0.1.77

marshmallow==3.21.3

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

openai==1.33.0

orjson==3.10.4

packaging==23.2

pydantic==2.7.4

pydantic_core==2.18.4

PyYAML==6.0.1

regex==2024.5.15

requests==2.32.3

sniffio==1.3.1

SQLAlchemy==2.0.30

tenacity==8.3.0

tiktoken==0.7.0

tqdm==4.66.4

typing-inspect==0.9.0

typing_extensions==4.12.2

urllib3==2.2.1

yarl==1.9.4

※ pip install langchain

[PYTHON/LANGCHAIN] FAISS 클래스 : as_retriever 메소드에서 search_kwargs 인자를 사용해 벡터 스토어 검색기 구하기

■ FAISS 클래스의 as_retriever 메소드에서 search_kwargs 인자를 사용해 벡터 스토어 검색기를 구하는 방법을 보여준다. ※ 검색기가 반환하는 문서 수를 제한할 수도 있다.

[PYTHON/LANGCHAIN] create_retriever_tool 함수 : 웹 문서 검색 도구 만들기

■ create_retriever_tool 함수를 사용해 웹 문서 검색 도구를 만드는 방법을 보여준다. ▶ main.py


import os
import bs4

from langgraph.checkpoint.sqlite          import SqliteSaver
from langchain_openai                     import ChatOpenAI
from langchain_community.document_loaders import WebBaseLoader
from langchain_text_splitters             import RecursiveCharacterTextSplitter
from langchain_chroma                     import Chroma
from langchain_openai                     import OpenAIEmbeddings
from langchain.tools.retriever            import create_retriever_tool
from langgraph.prebuilt                   import create_react_agent
from langchain_core.messages              import HumanMessage

os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>"

# SQLITE를 사용해 상태를 저장한다.
sqliteSaver = SqliteSaver.from_conn_string(":memory:")

# OpenAI 채팅 모델을 설정한다.
chatOpenAI = ChatOpenAI(model = "gpt-3.5-turbo", temperature = 0)

# 웹 문서를 로드한다.
webBaseLoader = WebBaseLoader(
    web_paths = ("https://lilianweng.github.io/posts/2023-06-23-agent/",),
    bs_kwargs = dict(parse_only = bs4.SoupStrainer(class_ = ("post-content", "post-title", "post-header")))
)

documentList = webBaseLoader.load()

# 문서를 분할한다.
recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size = 1000, chunk_overlap = 200)

splitDocumentList = recursiveCharacterTextSplitter.split_documents(documentList)

# 벡터 저장소를 설정한다.
chroma = Chroma.from_documents(documents = splitDocumentList, embedding = OpenAIEmbeddings())

vectorStoreRetriever = chroma.as_retriever()

# 검색 도구를 생성한다.
tool = create_retriever_tool(
    vectorStoreRetriever,
    "BlogPostRetriever",
    "Searches and returns excerpts from the Autonomous Agents blog post.",
)

toolList = [tool]

# 대화형 에이전트를 생성한다.
compiledStateGraph = create_react_agent(chatOpenAI, toolList, checkpointer = sqliteSaver)

# 응답 질의를 실행한다.
configurationDictionary = {"configurable" : {"thread_id" : "thread1"}}

query1 = "Hi! I'm bob"

for text in compiledStateGraph.stream({"messages" : [HumanMessage(content = query1)]}, config = configurationDictionary):
    print(text)
print("----")

query2 = "What is Task Decomposition?"

for text in compiledStateGraph.stream({"messages" : [HumanMessage(content = query2)]}, config = configurationDictionary):
    print(text)
print("----")

query3 = "What is Task Decomposition?"

for text in compiledStateGraph.stream({"messages" : [HumanMessage(content = query3)]}, config = configurationDictionary):
    print(text)
print("----")

import os

import bs4

from langgraph.checkpoint.sqlite import SqliteSaver

from langchain_openai import ChatOpenAI

from langchain_community.document_loaders import WebBaseLoader

from langchain_text_splitters import RecursiveCharacterTextSplitter

from langchain_chroma import Chroma

from langchain_openai import OpenAIEmbeddings

from langchain.tools.retriever import create_retriever_tool

from langgraph.prebuilt import create_react_agent

from langchain_core.messages import HumanMessage

os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>"

# SQLITE를 사용해 상태를 저장한다.

sqliteSaver = SqliteSaver.from_conn_string(":memory:")

# OpenAI 채팅 모델을 설정한다.

chatOpenAI = ChatOpenAI(model = "gpt-3.5-turbo", temperature = 0)

# 웹 문서를 로드한다.

webBaseLoader = WebBaseLoader(

web_paths = ("https://lilianweng.github.io/posts/2023-06-23-agent/",),

bs_kwargs = dict(parse_only = bs4.SoupStrainer(class_ = ("post-content", "post-title", "post-header")))

)

documentList = webBaseLoader.load()

# 문서를 분할한다.

recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size = 1000, chunk_overlap = 200)

splitDocumentList = recursiveCharacterTextSplitter.split_documents(documentList)

# 벡터 저장소를 설정한다.

chroma = Chroma.from_documents(documents = splitDocumentList, embedding = OpenAIEmbeddings())

vectorStoreRetriever = chroma.as_retriever()

# 검색 도구를 생성한다.

tool = create_retriever_tool(

vectorStoreRetriever,

"BlogPostRetriever",

"Searches and returns excerpts from the Autonomous Agents blog post.",

)

toolList = [tool]

# 대화형 에이전트를 생성한다.

compiledStateGraph = create_react_agent(chatOpenAI, toolList, checkpointer = sqliteSaver)

# 응답 질의를 실행한다.

configurationDictionary = {"configurable" : {"thread_id" : "thread1"}}

query1 = "Hi! I'm bob"

for text in compiledStateGraph.stream({"messages" : [HumanMessage(content = query1)]}, config = configurationDictionary):

print(text)

print("----")

query2 = "What is Task Decomposition?"

for text in compiledStateGraph.stream({"messages" : [HumanMessage(content = query2)]}, config = configurationDictionary):

print(text)

print("----")

query3 = "What is Task Decomposition?"

for text in compiledStateGraph.stream({"messages" : [HumanMessage(content = query3)]}, config = configurationDictionary):

print(text)

print("----")

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
anyio==4.4.0
asgiref==3.8.1
async-timeout==4.0.3
attrs==23.2.0
backoff==2.2.1
bcrypt==4.1.3
beautifulsoup4==4.12.3
bs4==0.0.2
build==1.2.1
cachetools==5.3.3
certifi==2024.6.2
charset-normalizer==3.3.2
chroma-hnswlib==0.7.3
chromadb==0.5.0
click==8.1.7
coloredlogs==15.0.1
dataclasses-json==0.6.7
Deprecated==1.2.14
distro==1.9.0
dnspython==2.6.1
email_validator==2.1.1
exceptiongroup==1.2.1
fastapi==0.111.0
fastapi-cli==0.0.4
filelock==3.14.0
flatbuffers==24.3.25
frozenlist==1.4.1
fsspec==2024.6.0
google-auth==2.30.0
googleapis-common-protos==1.63.1
greenlet==3.0.3
grpcio==1.64.1
h11==0.14.0
httpcore==1.0.5
httptools==0.6.1
httpx==0.27.0
huggingface-hub==0.23.3
humanfriendly==10.0
idna==3.7
importlib_metadata==7.1.0
importlib_resources==6.4.0
Jinja2==3.1.4
jsonpatch==1.33
jsonpointer==3.0.0
kubernetes==30.1.0
langchain==0.2.3
langchain-chroma==0.1.1
langchain-community==0.2.4
langchain-core==0.2.5
langchain-openai==0.1.8
langchain-text-splitters==0.2.1
langgraph==0.0.66
langsmith==0.1.77
markdown-it-py==3.0.0
MarkupSafe==2.1.5
marshmallow==3.21.3
mdurl==0.1.2
mmh3==4.1.0
monotonic==1.6
mpmath==1.3.0
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
oauthlib==3.2.2
onnxruntime==1.18.0
openai==1.33.0
opentelemetry-api==1.25.0
opentelemetry-exporter-otlp-proto-common==1.25.0
opentelemetry-exporter-otlp-proto-grpc==1.25.0
opentelemetry-instrumentation==0.46b0
opentelemetry-instrumentation-asgi==0.46b0
opentelemetry-instrumentation-fastapi==0.46b0
opentelemetry-proto==1.25.0
opentelemetry-sdk==1.25.0
opentelemetry-semantic-conventions==0.46b0
opentelemetry-util-http==0.46b0
orjson==3.10.4
overrides==7.7.0
packaging==23.2
posthog==3.5.0
protobuf==4.25.3
pyasn1==0.6.0
pyasn1_modules==0.4.0
pydantic==2.7.3
pydantic_core==2.18.4
Pygments==2.18.0
PyPika==0.48.9
pyproject_hooks==1.1.0
python-dateutil==2.9.0.post0
python-dotenv==1.0.1
python-multipart==0.0.9
PyYAML==6.0.1
regex==2024.5.15
requests==2.32.3
requests-oauthlib==2.0.0
rich==13.7.1
rsa==4.9
shellingham==1.5.4
six==1.16.0
sniffio==1.3.1
soupsieve==2.5
SQLAlchemy==2.0.30
starlette==0.37.2
sympy==1.12.1
tenacity==8.3.0
tiktoken==0.7.0
tokenizers==0.19.1
tomli==2.0.1
tqdm==4.66.4
typer==0.12.3
typing-inspect==0.9.0
typing_extensions==4.12.2
ujson==5.10.0
urllib3==2.2.1
uvicorn==0.30.1
uvloop==0.19.0
watchfiles==0.22.0
websocket-client==1.8.0
websockets==12.0
wrapt==1.16.0
yarl==1.9.4
zipp==3.19.2

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

127

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

anyio==4.4.0

asgiref==3.8.1

async-timeout==4.0.3

attrs==23.2.0

backoff==2.2.1

bcrypt==4.1.3

beautifulsoup4==4.12.3

bs4==0.0.2

build==1.2.1

cachetools==5.3.3

certifi==2024.6.2

charset-normalizer==3.3.2

chroma-hnswlib==0.7.3

chromadb==0.5.0

click==8.1.7

coloredlogs==15.0.1

dataclasses-json==0.6.7

Deprecated==1.2.14

distro==1.9.0

dnspython==2.6.1

email_validator==2.1.1

exceptiongroup==1.2.1

fastapi==0.111.0

fastapi-cli==0.0.4

filelock==3.14.0

flatbuffers==24.3.25

frozenlist==1.4.1

fsspec==2024.6.0

google-auth==2.30.0

googleapis-common-protos==1.63.1

greenlet==3.0.3

grpcio==1.64.1

h11==0.14.0

httpcore==1.0.5

httptools==0.6.1

httpx==0.27.0

huggingface-hub==0.23.3

humanfriendly==10.0

idna==3.7

importlib_metadata==7.1.0

importlib_resources==6.4.0

Jinja2==3.1.4

jsonpatch==1.33

jsonpointer==3.0.0

kubernetes==30.1.0

langchain==0.2.3

langchain-chroma==0.1.1

langchain-community==0.2.4

langchain-core==0.2.5

langchain-openai==0.1.8

langchain-text-splitters==0.2.1

langgraph==0.0.66

langsmith==0.1.77

markdown-it-py==3.0.0

MarkupSafe==2.1.5

marshmallow==3.21.3

mdurl==0.1.2

mmh3==4.1.0

monotonic==1.6

mpmath==1.3.0

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

oauthlib==3.2.2

onnxruntime==1.18.0

openai==1.33.0

opentelemetry-api==1.25.0

opentelemetry-exporter-otlp-proto-common==1.25.0

opentelemetry-exporter-otlp-proto-grpc==1.25.0

opentelemetry-instrumentation==0.46b0

opentelemetry-instrumentation-asgi==0.46b0

opentelemetry-instrumentation-fastapi==0.46b0

opentelemetry-proto==1.25.0

opentelemetry-sdk==1.25.0

opentelemetry-semantic-conventions==0.46b0

opentelemetry-util-http==0.46b0

orjson==3.10.4

overrides==7.7.0

packaging==23.2

posthog==3.5.0

protobuf==4.25.3

pyasn1==0.6.0

pyasn1_modules==0.4.0

pydantic==2.7.3

pydantic_core==2.18.4

Pygments==2.18.0

PyPika==0.48.9

pyproject_hooks==1.1.0

python-dateutil==2.9.0.post0

python-dotenv==1.0.1

python-multipart==0.0.9

PyYAML==6.0.1

regex==2024.5.15

requests==2.32.3

requests-oauthlib==2.0.0

rich==13.7.1

rsa==4.9

shellingham==1.5.4

six==1.16.0

sniffio==1.3.1

soupsieve==2.5

SQLAlchemy==2.0.30

starlette==0.37.2

sympy==1.12.1

tenacity==8.3.0

tiktoken==0.7.0

tokenizers==0.19.1

tomli==2.0.1

tqdm==4.66.4

typer==0.12.3

typing-inspect==0.9.0

typing_extensions==4.12.2

ujson==5.10.0

urllib3==2.2.1

uvicorn==0.30.1

uvloop==0.19.0

watchfiles==0.22.0

websocket-client==1.8.0

websockets==12.0

wrapt==1.16.0

yarl==1.9.4

zipp==3.19.2

※ pip install langchain langchain-chroma

[PYTHON/LANGCHAIN] create_retrieval_chain 함수 : 문서 검색 모듈과 질문/답변 생성 모듈 연결하기

■ create_retrieval_chain 함수를 사용해 문서 검색 모듈과 질문/답변 생성 모듈을 연결하는 방법을 보여준다. ▶ main.py


import os
import bs4

from langchain_community.document_loaders import WebBaseLoader
from langchain_text_splitters             import RecursiveCharacterTextSplitter
from langchain_chroma                     import Chroma
from langchain_openai                     import OpenAIEmbeddings
from langchain_openai                     import ChatOpenAI
from langchain_core.prompts               import ChatPromptTemplate
from langchain.chains.combine_documents   import create_stuff_documents_chain
from langchain.chains                     import create_retrieval_chain

os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>"

webBaseLoader = WebBaseLoader(
    web_paths = ("https://lilianweng.github.io/posts/2023-06-23-agent/",),
    bs_kwargs = dict(parse_only = bs4.SoupStrainer(class_ = ("media_end_head_headline", "newsct_body")))
)

documentList = webBaseLoader.load()

recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size = 1000, chunk_overlap = 200)

splitDocumentList = recursiveCharacterTextSplitter.split_documents(documentList)

chroma = Chroma.from_documents(documents = splitDocumentList, embedding = OpenAIEmbeddings())

vectorStoreRetriever = chroma.as_retriever()

systemString = (
    "You are an assistant for question-answering tasks. "
    "Use the following pieces of retrieved context to answer "
    "the question. If you don't know the answer, say that you "
    "don't know. Use three sentences maximum and keep the "
    "answer concise."
    "\n\n"
    "{context}"
)

chatPromptTemplate = ChatPromptTemplate.from_messages(
    [
        ("system", systemString),
        ("human", "{input}"),
    ]
)

chatOpenAI = ChatOpenAI(model = "gpt-3.5-turbo-0125")

questionAnswerRunnableBinding = create_stuff_documents_chain(chatOpenAI, chatPromptTemplate)

ragRunnableBinding = create_retrieval_chain(vectorStoreRetriever, questionAnswerRunnableBinding)

responseDictionary = ragRunnableBinding.invoke({"input" : "What is Task Decomposition?"})

print(responseDictionary["answer"])

"""
Task decomposition involves breaking down a complex task into smaller and more manageable subtasks. This process helps agents or models tackle difficult tasks step by step, making it easier to plan and execute the overall task efficiently. Task decomposition can be achieved through techniques like Chain of Thought or Tree of Thoughts, which guide the model in breaking down tasks into simpler components.
"""

import os

import bs4

from langchain_community.document_loaders import WebBaseLoader

from langchain_text_splitters import RecursiveCharacterTextSplitter

from langchain_chroma import Chroma

from langchain_openai import OpenAIEmbeddings

from langchain_openai import ChatOpenAI

from langchain_core.prompts import ChatPromptTemplate

from langchain.chains.combine_documents import create_stuff_documents_chain

from langchain.chains import create_retrieval_chain

os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>"

webBaseLoader = WebBaseLoader(

web_paths = ("https://lilianweng.github.io/posts/2023-06-23-agent/",),

bs_kwargs = dict(parse_only = bs4.SoupStrainer(class_ = ("media_end_head_headline", "newsct_body")))

)

documentList = webBaseLoader.load()

recursiveCharacterTextSplitter = RecursiveCharacterTextSplitter(chunk_size = 1000, chunk_overlap = 200)

splitDocumentList = recursiveCharacterTextSplitter.split_documents(documentList)

chroma = Chroma.from_documents(documents = splitDocumentList, embedding = OpenAIEmbeddings())

vectorStoreRetriever = chroma.as_retriever()

systemString = (

"You are an assistant for question-answering tasks. "

"Use the following pieces of retrieved context to answer "

"the question. If you don't know the answer, say that you "

"don't know. Use three sentences maximum and keep the "

"answer concise."

"\n\n"

"{context}"

)

chatPromptTemplate = ChatPromptTemplate.from_messages(

[

("system", systemString),

("human", "{input}"),

]

)

chatOpenAI = ChatOpenAI(model = "gpt-3.5-turbo-0125")

questionAnswerRunnableBinding = create_stuff_documents_chain(chatOpenAI, chatPromptTemplate)

ragRunnableBinding = create_retrieval_chain(vectorStoreRetriever, questionAnswerRunnableBinding)

responseDictionary = ragRunnableBinding.invoke({"input" : "What is Task Decomposition?"})

print(responseDictionary["answer"])

"""

Task decomposition involves breaking down a complex task into smaller and more manageable subtasks. This process helps agents or models tackle difficult tasks step by step, making it easier to plan and execute the overall task efficiently. Task decomposition can be achieved through techniques like Chain of Thought or Tree of Thoughts, which guide the model in breaking down tasks into simpler components.

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
anyio==4.4.0
asgiref==3.8.1
async-timeout==4.0.3
attrs==23.2.0
backoff==2.2.1
bcrypt==4.1.3
beautifulsoup4==4.12.3
bs4==0.0.2
build==1.2.1
cachetools==5.3.3
certifi==2024.6.2
charset-normalizer==3.3.2
chroma-hnswlib==0.7.3
chromadb==0.5.0
click==8.1.7
coloredlogs==15.0.1
dataclasses-json==0.6.7
Deprecated==1.2.14
distro==1.9.0
dnspython==2.6.1
email_validator==2.1.1
exceptiongroup==1.2.1
fastapi==0.111.0
fastapi-cli==0.0.4
filelock==3.14.0
flatbuffers==24.3.25
frozenlist==1.4.1
fsspec==2024.6.0
google-auth==2.30.0
googleapis-common-protos==1.63.1
greenlet==3.0.3
grpcio==1.64.1
h11==0.14.0
httpcore==1.0.5
httptools==0.6.1
httpx==0.27.0
huggingface-hub==0.23.3
humanfriendly==10.0
idna==3.7
importlib_metadata==7.1.0
importlib_resources==6.4.0
Jinja2==3.1.4
jsonpatch==1.33
jsonpointer==3.0.0
kubernetes==30.1.0
langchain==0.2.3
langchain-chroma==0.1.1
langchain-community==0.2.4
langchain-core==0.2.5
langchain-openai==0.1.8
langchain-text-splitters==0.2.1
langsmith==0.1.77
markdown-it-py==3.0.0
MarkupSafe==2.1.5
marshmallow==3.21.3
mdurl==0.1.2
mmh3==4.1.0
monotonic==1.6
mpmath==1.3.0
multidict==6.0.5
mypy-extensions==1.0.0
numpy==1.26.4
oauthlib==3.2.2
onnxruntime==1.18.0
openai==1.33.0
opentelemetry-api==1.25.0
opentelemetry-exporter-otlp-proto-common==1.25.0
opentelemetry-exporter-otlp-proto-grpc==1.25.0
opentelemetry-instrumentation==0.46b0
opentelemetry-instrumentation-asgi==0.46b0
opentelemetry-instrumentation-fastapi==0.46b0
opentelemetry-proto==1.25.0
opentelemetry-sdk==1.25.0
opentelemetry-semantic-conventions==0.46b0
opentelemetry-util-http==0.46b0
orjson==3.10.4
overrides==7.7.0
packaging==23.2
posthog==3.5.0
protobuf==4.25.3
pyasn1==0.6.0
pyasn1_modules==0.4.0
pydantic==2.7.3
pydantic_core==2.18.4
Pygments==2.18.0
PyPika==0.48.9
pyproject_hooks==1.1.0
python-dateutil==2.9.0.post0
python-dotenv==1.0.1
python-multipart==0.0.9
PyYAML==6.0.1
regex==2024.5.15
requests==2.32.3
requests-oauthlib==2.0.0
rich==13.7.1
rsa==4.9
shellingham==1.5.4
six==1.16.0
sniffio==1.3.1
soupsieve==2.5
SQLAlchemy==2.0.30
starlette==0.37.2
sympy==1.12.1
tenacity==8.3.0
tiktoken==0.7.0
tokenizers==0.19.1
tomli==2.0.1
tqdm==4.66.4
typer==0.12.3
typing-inspect==0.9.0
typing_extensions==4.12.2
ujson==5.10.0
urllib3==2.2.1
uvicorn==0.30.1
uvloop==0.19.0
watchfiles==0.22.0
websocket-client==1.8.0
websockets==12.0
wrapt==1.16.0
yarl==1.9.4
zipp==3.19.2

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

119

120

121

122

123

124

125

126

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

anyio==4.4.0

asgiref==3.8.1

async-timeout==4.0.3

attrs==23.2.0

backoff==2.2.1

bcrypt==4.1.3

beautifulsoup4==4.12.3

bs4==0.0.2

build==1.2.1

cachetools==5.3.3

certifi==2024.6.2

charset-normalizer==3.3.2

chroma-hnswlib==0.7.3

chromadb==0.5.0

click==8.1.7

coloredlogs==15.0.1

dataclasses-json==0.6.7

Deprecated==1.2.14

distro==1.9.0

dnspython==2.6.1

email_validator==2.1.1

exceptiongroup==1.2.1

fastapi==0.111.0

fastapi-cli==0.0.4

filelock==3.14.0

flatbuffers==24.3.25

frozenlist==1.4.1

fsspec==2024.6.0

google-auth==2.30.0

googleapis-common-protos==1.63.1

greenlet==3.0.3

grpcio==1.64.1

h11==0.14.0

httpcore==1.0.5

httptools==0.6.1

httpx==0.27.0

huggingface-hub==0.23.3

humanfriendly==10.0

idna==3.7

importlib_metadata==7.1.0

importlib_resources==6.4.0

Jinja2==3.1.4

jsonpatch==1.33

jsonpointer==3.0.0

kubernetes==30.1.0

langchain==0.2.3

langchain-chroma==0.1.1

langchain-community==0.2.4

langchain-core==0.2.5

langchain-openai==0.1.8

langchain-text-splitters==0.2.1

langsmith==0.1.77

markdown-it-py==3.0.0

MarkupSafe==2.1.5

marshmallow==3.21.3

mdurl==0.1.2

mmh3==4.1.0

monotonic==1.6

mpmath==1.3.0

multidict==6.0.5

mypy-extensions==1.0.0

numpy==1.26.4

oauthlib==3.2.2

onnxruntime==1.18.0

openai==1.33.0

opentelemetry-api==1.25.0

opentelemetry-exporter-otlp-proto-common==1.25.0

opentelemetry-exporter-otlp-proto-grpc==1.25.0

opentelemetry-instrumentation==0.46b0

opentelemetry-instrumentation-asgi==0.46b0

opentelemetry-instrumentation-fastapi==0.46b0

opentelemetry-proto==1.25.0

opentelemetry-sdk==1.25.0

opentelemetry-semantic-conventions==0.46b0

opentelemetry-util-http==0.46b0

orjson==3.10.4

overrides==7.7.0

packaging==23.2

posthog==3.5.0

protobuf==4.25.3

pyasn1==0.6.0

pyasn1_modules==0.4.0

pydantic==2.7.3

pydantic_core==2.18.4

Pygments==2.18.0

PyPika==0.48.9

pyproject_hooks==1.1.0

python-dateutil==2.9.0.post0

python-dotenv==1.0.1

python-multipart==0.0.9

PyYAML==6.0.1

regex==2024.5.15

requests==2.32.3

requests-oauthlib==2.0.0

rich==13.7.1

rsa==4.9

shellingham==1.5.4

six==1.16.0

sniffio==1.3.1

soupsieve==2.5

SQLAlchemy==2.0.30

starlette==0.37.2

sympy==1.12.1

tenacity==8.3.0

tiktoken==0.7.0

tokenizers==0.19.1

tomli==2.0.1

tqdm==4.66.4

typer==0.12.3

typing-inspect==0.9.0

typing_extensions==4.12.2

ujson==5.10.0

urllib3==2.2.1

uvicorn==0.30.1

uvloop==0.19.0

watchfiles==0.22.0

websocket-client==1.8.0

websockets==12.0

wrapt==1.16.0

yarl==1.9.4

zipp==3.19.2

※ pip install

[PYTHON/LANGCHAIN] VectorStoreRetriever 클래스 : batch 메소드를 사용해 복수 문자열 쿼리 유사성 기반으로 문서 리스트 구하기

■ VectorStoreRetriever 클래스의 batch 메소드를 사용해 복수 문자열 쿼리와의 유사성 기반으로 문서 리스트를 구하는 방법을 보여준다. ▶ main.py


import os

from langchain_core.documents import Document
from langchain_chroma         import Chroma
from langchain_openai         import OpenAIEmbeddings

os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>"

documentList = [
    Document(
        page_content = "Dogs are great companions, known for their loyalty and friendliness.",
        metadata     = {"source" : "mammal-pets-doc"}
    ),
    Document(
        page_content = "Cats are independent pets that often enjoy their own space.",
        metadata     = {"source" : "mammal-pets-doc"},
    ),
    Document(
        page_content = "Goldfish are popular pets for beginners, requiring relatively simple care.",
        metadata     = {"source" : "fish-pets-doc"},
    ),
    Document(
        page_content = "Parrots are intelligent birds capable of mimicking human speech.",
        metadata     = {"source" : "bird-pets-doc"},
    ),
    Document(
        page_content = "Rabbits are social animals that need plenty of space to hop around.",
        metadata     = {"source" : "mammal-pets-doc"},
    ),
]

chroma = Chroma.from_documents(
    documentList,
    embedding = OpenAIEmbeddings(),
)

vectorStoreRetriever = chroma.as_retriever(
    search_type   = "similarity", # "similarity"(디폴트), "mmr" (maximum marginal relevance, described above), "similarity_score_threshold"
    search_kwargs = {"k" : 1},
)

searchResultList = vectorStoreRetriever.batch(["cat", "shark"])

print(searchResultList)

"""
[
    [
        Document(
            page_content = 'Cats are independent pets that often enjoy their own space.',
            metadata     = {'source' : 'mammal-pets-doc'}
        )
    ],
    [
        Document(
            page_content = 'Goldfish are popular pets for beginners, requiring relatively simple care.',
            metadata     = {'source' : 'fish-pets-doc'}
        )
    ]
]
"""

import os

from langchain_core.documents import Document

from langchain_chroma import Chroma

from langchain_openai import OpenAIEmbeddings

os.environ["OPENAI_API_KEY"] = "<OPENAI_API_KEY>"

documentList = [

Document(

page_content = "Dogs are great companions, known for their loyalty and friendliness.",

metadata = {"source" : "mammal-pets-doc"}

Document(

page_content = "Cats are independent pets that often enjoy their own space.",

metadata = {"source" : "mammal-pets-doc"},

Document(

page_content = "Goldfish are popular pets for beginners, requiring relatively simple care.",

metadata = {"source" : "fish-pets-doc"},

Document(

page_content = "Parrots are intelligent birds capable of mimicking human speech.",

metadata = {"source" : "bird-pets-doc"},

Document(

page_content = "Rabbits are social animals that need plenty of space to hop around.",

metadata = {"source" : "mammal-pets-doc"},

]

chroma = Chroma.from_documents(

documentList,

embedding = OpenAIEmbeddings(),

)

vectorStoreRetriever = chroma.as_retriever(

search_type = "similarity", # "similarity"(디폴트), "mmr" (maximum marginal relevance, described above), "similarity_score_threshold"

search_kwargs = {"k" : 1},

)

searchResultList = vectorStoreRetriever.batch(["cat", "shark"])

print(searchResultList)

"""

[

Document(

page_content = 'Cats are independent pets that often enjoy their own space.',

metadata = {'source' : 'mammal-pets-doc'}

)

[

Document(

page_content = 'Goldfish are popular pets for beginners, requiring relatively simple care.',

metadata = {'source' : 'fish-pets-doc'}

)

]

"""

▶ requirements.txt


aiohttp==3.9.5
aiosignal==1.3.1
annotated-types==0.7.0
anyio==4.4.0
asgiref==3.8.1
async-timeout==4.0.3
attrs==23.2.0
backoff==2.2.1
bcrypt==4.1.3
build==1.2.1
cachetools==5.3.3
certifi==2024.6.2
charset-normalizer==3.3.2
chroma-hnswlib==0.7.3
chromadb==0.5.0
click==8.1.7
coloredlogs==15.0.1
Deprecated==1.2.14
distro==1.9.0
dnspython==2.6.1
email_validator==2.1.1
exceptiongroup==1.2.1
fastapi==0.111.0
fastapi-cli==0.0.4
filelock==3.14.0
flatbuffers==24.3.25
frozenlist==1.4.1
fsspec==2024.6.0
google-auth==2.30.0
googleapis-common-protos==1.63.1
greenlet==3.0.3
grpcio==1.64.1
h11==0.14.0
httpcore==1.0.5
httptools==0.6.1
httpx==0.27.0
huggingface-hub==0.23.3
humanfriendly==10.0
idna==3.7
importlib_metadata==7.1.0
importlib_resources==6.4.0
Jinja2==3.1.4
jsonpatch==1.33
jsonpointer==2.4
kubernetes==30.1.0
langchain==0.2.3
langchain-chroma==0.1.1
langchain-core==0.2.5
langchain-openai==0.1.8
langchain-text-splitters==0.2.1
langsmith==0.1.75
markdown-it-py==3.0.0
MarkupSafe==2.1.5
mdurl==0.1.2
mmh3==4.1.0
monotonic==1.6
mpmath==1.3.0
multidict==6.0.5
numpy==1.26.4
oauthlib==3.2.2
onnxruntime==1.18.0
openai==1.33.0
opentelemetry-api==1.25.0
opentelemetry-exporter-otlp-proto-common==1.25.0
opentelemetry-exporter-otlp-proto-grpc==1.25.0
opentelemetry-instrumentation==0.46b0
opentelemetry-instrumentation-asgi==0.46b0
opentelemetry-instrumentation-fastapi==0.46b0
opentelemetry-proto==1.25.0
opentelemetry-sdk==1.25.0
opentelemetry-semantic-conventions==0.46b0
opentelemetry-util-http==0.46b0
orjson==3.10.3
overrides==7.7.0
packaging==23.2
posthog==3.5.0
protobuf==4.25.3
pyasn1==0.6.0
pyasn1_modules==0.4.0
pydantic==2.7.3
pydantic_core==2.18.4
Pygments==2.18.0
PyPika==0.48.9
pyproject_hooks==1.1.0
python-dateutil==2.9.0.post0
python-dotenv==1.0.1
python-multipart==0.0.9
PyYAML==6.0.1
regex==2024.5.15
requests==2.32.3
requests-oauthlib==2.0.0
rich==13.7.1
rsa==4.9
shellingham==1.5.4
six==1.16.0
sniffio==1.3.1
SQLAlchemy==2.0.30
starlette==0.37.2
sympy==1.12.1
tenacity==8.3.0
tiktoken==0.7.0
tokenizers==0.19.1
tomli==2.0.1
tqdm==4.66.4
typer==0.12.3
typing_extensions==4.12.2
ujson==5.10.0
urllib3==2.2.1
uvicorn==0.30.1
uvloop==0.19.0
watchfiles==0.22.0
websocket-client==1.8.0
websockets==12.0
wrapt==1.16.0
yarl==1.9.4
zipp==3.19.2

100

101

102

103

104

105

106

107

108

109

110

111

112

113

114

115

116

117

118

aiohttp==3.9.5

aiosignal==1.3.1

annotated-types==0.7.0

anyio==4.4.0

asgiref==3.8.1

async-timeout==4.0.3

attrs==23.2.0

backoff==2.2.1

bcrypt==4.1.3

build==1.2.1

cachetools==5.3.3

certifi==2024.6.2

charset-normalizer==3.3.2

chroma-hnswlib==0.7.3

chromadb==0.5.0

click==8.1.7

coloredlogs==15.0.1

Deprecated==1.2.14

distro==1.9.0

dnspython==2.6.1

email_validator==2.1.1

exceptiongroup==1.2.1

fastapi==0.111.0

fastapi-cli==0.0.4

filelock==3.14.0

flatbuffers==24.3.25

frozenlist==1.4.1

fsspec==2024.6.0

google-auth==2.30.0

googleapis-common-protos==1.63.1

greenlet==3.0.3

grpcio==1.64.1

h11==0.14.0

httpcore==1.0.5

httptools==0.6.1

httpx==0.27.0

huggingface-hub==0.23.3

humanfriendly==10.0

idna==3.7

importlib_metadata==7.1.0

importlib_resources==6.4.0

Jinja2==3.1.4

jsonpatch==1.33

jsonpointer==2.4

kubernetes==30.1.0

langchain==0.2.3

langchain-chroma==0.1.1

langchain-core==0.2.5

langchain-openai==0.1.8

langchain-text-splitters==0.2.1

langsmith==0.1.75

markdown-it-py==3.0.0

MarkupSafe==2.1.5

mdurl==0.1.2

mmh3==4.1.0

monotonic==1.6

mpmath==1.3.0

multidict==6.0.5

numpy==1.26.4

oauthlib==3.2.2

onnxruntime==1.18.0

openai==1.33.0

opentelemetry-api==1.25.0

opentelemetry-exporter-otlp-proto-common==1.25.0

opentelemetry-exporter-otlp-proto-grpc==1.25.0

opentelemetry-instrumentation==0.46b0

opentelemetry-instrumentation-asgi==0.46b0

opentelemetry-instrumentation-fastapi==0.46b0

opentelemetry-proto==1.25.0

opentelemetry-sdk==1.25.0

opentelemetry-semantic-conventions==0.46b0

opentelemetry-util-http==0.46b0

orjson==3.10.3

overrides==7.7.0

packaging==23.2

posthog==3.5.0

protobuf==4.25.3

pyasn1==0.6.0

pyasn1_modules==0.4.0

pydantic==2.7.3

pydantic_core==2.18.4

Pygments==2.18.0

PyPika==0.48.9

pyproject_hooks==1.1.0

python-dateutil==2.9.0.post0

python-dotenv==1.0.1

python-multipart==0.0.9

PyYAML==6.0.1

regex==2024.5.15

requests==2.32.3

requests-oauthlib==2.0.0

rich==13.7.1

rsa==4.9

shellingham==1.5.4

six==1.16.0

sniffio==1.3.1

SQLAlchemy==2.0.30

starlette==0.37.2

sympy==1.12.1

tenacity==8.3.0

tiktoken==0.7.0

tokenizers==0.19.1

tomli==2.0.1

tqdm==4.66.4

typer==0.12.3

typing_extensions==4.12.2

ujson==5.10.0

urllib3==2.2.1

uvicorn==0.30.1

uvloop==0.19.0

watchfiles==0.22.0

websocket-client==1.8.0

websockets==12.0

wrapt==1.16.0

yarl==1.9.4

zipp==3.19.2