str' object has no attribute 'page_content'

[shobhitagnihotri69]

Checked other resources

• I added a very descriptive title to this issue.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.

Example Code

vectordb = Chroma.from_documents(documents=chunks
, embedding=embeddings) I am using this code to solve problem but I am not able to solve its showing ttributeError Traceback (most recent call last)
in <cell line: 1>()
----> 1 vectordb = Chroma.from_documents(documents=chunks
2 , embedding=embeddings)

1 frames
/usr/local/lib/python3.10/dist-packages/langchain_community/vectorstores/chroma.py in (.0)
774 Chroma: Chroma vectorstore.
775 """
--> 776 texts = [doc.page_content for doc in documents]
777 metadatas = [doc.metadata for doc in documents]
778 return cls.from_texts(

AttributeError: 'str' object has no attribute 'page_content'

Error Message and Stack Trace (if applicable)

No response

Description

I am using langchain to create chunks and perform vector embedding throughcgroma db , How can I change it into

System Info

I am using Mac

[dosubot]

🤖

Hey again, @shobhitagnihotri69! Great to see you back and diving into more challenges with LangChain. Let's get this sorted out for you.

Based on the error message you provided, it seems like you're trying to access the 'page_content' attribute of a string object, which does not exist. This error typically occurs when you are trying to create a Chroma vectorstore from a list of strings instead of a list of Document objects.

In LangChain, the from_documents method of the Chroma class expects a list of Document objects as input. Here's the relevant code snippet from the LangChain source code:

def from_documents(
    cls: Type[Chroma],
    documents: List[Document],
    ...
) -> Chroma:
    texts = [doc.page_content for doc in documents]
    metadatas = [doc.metadata for doc in documents]
    ...

In this code, 'doc.page_content' and 'doc.metadata' are trying to access the 'page_content' and 'metadata' attributes of each Document object in the 'documents' list. If you pass a list of strings instead of a list of Document objects to this method, you will encounter the 'AttributeError: 'str' object has no attribute 'page_content'' error.

To resolve this issue, you need to ensure that you are passing a list of Document objects to the 'from_documents' method. You can create a Document object in LangChain as follows:

from langchain_core.documents import Document

doc = Document(page_content="your text here", metadata={"your": "metadata here"})

Then, you can create a list of these Document objects and pass it to the 'from_documents' method:

documents = [doc1, doc2, ...]  # doc1, doc2, ... are Document objects
chroma = Chroma.from_documents(documents=documents, ...)

Please adjust the code to fit the specifics of your application and data structure. If you continue to encounter issues, please provide more details about your use case and the data you're working with. This will help me provide a more accurate solution.

Sources

• Issue: Pinecone Embeddings - Error
• AttributeError: 'tuple' object has no attribute 'page_content'
• AttributeError: 'str' object has no attribute 'page_content'
• Use Chromadb with Langchain and embedding from SentenceTransformer model
• libs/community/langchain_community/vectorstores/chroma.py
• libs/langchain/langchain/vectorstores/chroma.py

About Dosu

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.