Programmiererforum

import os
from langchain_community.document_loaders import TextLoader
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import Pinecone
from langchain_community.llms import HuggingFaceHub
from langchain_core.prompts import PromptTemplate
from langchain.chains import RetrievalQA  # This is still in langchain core
from dotenv import load_dotenv

import pinecone
print(pinecone.__version__)
from pinecone import *  # Importing the new Pinecone client
print(pinecone.Client)

# Initialize Pinecone client with new SDK
pinecone_api_key = os.getenv("PINECONE_API_KEY")
pinecone_environment = "us-east-1"  # Your Pinecone [url=viewtopic.php?t=25360]environment[/url] (must match your index region)

client = Client(api_key=pinecone_api_key, environment=pinecone_environment)

index_name = "gentlecat"

# Check if index exists, else create
if index_name not in [idx.name for idx in client.list_indexes()]:
client.create_index(name=index_name, dimension=384, metric="cosine")

# Connect to the index
index = client.index(index_name)

# Load & split documents
loader = TextLoader(r"filepath", encoding="utf-8")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=4)
docs = text_splitter.split_documents(documents)

# Setup embeddings (make sure model outputs 384 dims)
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")

# Create Pinecone vectorstore with new client
vectorstore = Pinecone.from_documents(docs, embeddings, index_name=index_name, client=client)

# Setup LLM
llm = HuggingFaceHub(
repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1",
model_kwargs={"temperature": 0.8, "top_p": 0.8, "top_k": 50},
huggingfacehub_api_token=os.getenv("HUGGINGFACE_API_KEY"),
)

# Setup prompt template
template = """You are a helpful assistant. Answer based on the Costco business context.

Context: {context}
Question: {question}
Answer:"""

prompt = PromptTemplate(template=template, input_variables=["context", "question"])

# Create RetrievalQA chain
qa_chain = RetrievalQA.from_chain_type(
llm=llm,
chain_type="stuff",
retriever=vectorstore.as_retriever(),
chain_type_kwargs={"prompt": prompt},
)

# Example query
query = "What is Costco's primary business model?"
answer = qa_chain.run(query)
print("Answer:", answer)

7.3.0
Traceback (most recent call last):
File "c:\filepath\main.py", line 14, in 
print(pinecone.Client)
File "C:\Users\FilePath\Python\Lib\site-packages\pinecone\utils\lazy_imports.py", line 65, in __getattr__
raise AttributeError(f"module '{self._original_module.__name__}' has no attribute '{name}'")
AttributeError: module 'pinecone' has no attribute 'Client'```

Das Problem mit diesem Code ist, dass ich nicht in der Lage bin, [b] Client [/b] aus der [b] Pnecone [/b] -Bibliothek zu importieren. Ich habe versucht, verschiedene Versionen zu deinstallieren und neu zu installieren, keine von ihnen hat gearbeitet. Ich habe es auch mit der Bibliothek [b] pnecone-Client [/b] versucht, aber nichts davon funktioniert. Jeder Rat würde geschätzt.[code]import os
from langchain_community.document_loaders import TextLoader
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import Pinecone
from langchain_community.llms import HuggingFaceHub
from langchain_core.prompts import PromptTemplate
from langchain.chains import RetrievalQA # This is still in langchain core
from dotenv import load_dotenv

import pinecone
print(pinecone.__version__)
from pinecone import * # Importing the new Pinecone client
print(pinecone.Client)

# Initialize Pinecone client with new SDK
pinecone_api_key = os.getenv("PINECONE_API_KEY")
pinecone_environment = "us-east-1" # Your Pinecone [url=viewtopic.php?t=25360]environment[/url] (must match your index region)

client = Client(api_key=pinecone_api_key, environment=pinecone_environment)

index_name = "gentlecat"

# Check if index exists, else create
if index_name not in [idx.name for idx in client.list_indexes()]:
client.create_index(name=index_name, dimension=384, metric="cosine")

# Connect to the index
index = client.index(index_name)

# Load & split documents
loader = TextLoader(r"filepath", encoding="utf-8")
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=4)
docs = text_splitter.split_documents(documents)

# Setup embeddings (make sure model outputs 384 dims)
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")

# Create Pinecone vectorstore with new client
vectorstore = Pinecone.from_documents(docs, embeddings, index_name=index_name, client=client)

# Setup LLM
llm = HuggingFaceHub(
repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1",
model_kwargs={"temperature": 0.8, "top_p": 0.8, "top_k": 50},
huggingfacehub_api_token=os.getenv("HUGGINGFACE_API_KEY"),
)

# Setup prompt template
template = """You are a helpful assistant. Answer based on the Costco business context.

Context: {context}
Question: {question}
Answer:"""

prompt = PromptTemplate(template=template, input_variables=["context", "question"])

# Create RetrievalQA chain
qa_chain = RetrievalQA.from_chain_type(
llm=llm,
chain_type="stuff",
retriever=vectorstore.as_retriever(),
chain_type_kwargs={"prompt": prompt},
)

# Example query
query = "What is Costco's primary business model?"
answer = qa_chain.run(query)
print("Answer:", answer)
[/code]
[b] Ausgabe: [/b]
[code]7.3.0
Traceback (most recent call last):
File "c:\filepath\main.py", line 14, in
print(pinecone.Client)
File "C:\Users\FilePath\Python\Lib\site-packages\pinecone\utils\lazy_imports.py", line 65, in __getattr__
raise AttributeError(f"module '{self._original_module.__name__}' has no attribute '{name}'")
AttributeError: module 'pinecone' has no attribute 'Client'```
[/code]