unable to use embed_documents function for ChromaDB

[nithinreddyyyyyy]

Issue with current documentation:

below's the code i'm using to try for handling longer context lengths

# Instantiate the OpenAIEmbeddings class
openai = OpenAIEmbeddings(openai_api_key="sk-")

# Generate embeddings for your documents
documents = [doc for doc in documents]

# Create a Chroma vector store from the documents
vectorstore = Chroma.from_documents(documents, openai.embed_documents)

it is returning below error

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
[<ipython-input-81-029281717453>](https://localhost:8080/#) in <cell line: 8>()
      6 
      7 # Create a Chroma vector store from the documents
----> 8 vectorstore = Chroma.from_documents(documents, openai.embed_documents)

2 frames
[/usr/local/lib/python3.10/dist-packages/langchain_community/vectorstores/chroma.py](https://localhost:8080/#) in from_documents(cls, documents, embedding, ids, collection_name, persist_directory, client_settings, client, collection_metadata, **kwargs)
    776         texts = [doc.page_content for doc in documents]
    777         metadatas = [doc.metadata for doc in documents]
--> 778         return cls.from_texts(
    779             texts=texts,
    780             embedding=embedding,

[/usr/local/lib/python3.10/dist-packages/langchain_community/vectorstores/chroma.py](https://localhost:8080/#) in from_texts(cls, texts, embedding, metadatas, ids, collection_name, persist_directory, client_settings, client, collection_metadata, **kwargs)
    734                 documents=texts,
    735             ):
--> 736                 chroma_collection.add_texts(
    737                     texts=batch[3] if batch[3] else [],
    738                     metadatas=batch[2] if batch[2] else None,

[/usr/local/lib/python3.10/dist-packages/langchain_community/vectorstores/chroma.py](https://localhost:8080/#) in add_texts(self, texts, metadatas, ids, **kwargs)
    273         texts = list(texts)
    274         if self._embedding_function is not None:
--> 275             embeddings = self._embedding_function.embed_documents(texts)
    276         if metadatas:
    277             # fill metadatas with empty dicts if somebody

AttributeError: 'function' object has no attribute 'embed_documents'

Can you assist me in dealing with handling context length issue beacuse i don't wanna use RecursiveCharacterTextSplitter as i've already chunked the data manually, I just want to send the data to ChromaDB at the same time by handling its context length

Idea or request for content:

No response

[dosubot]

🤖

Hey there, @nithinreddyyyyyy! Great to see you back. Let's dive into this new challenge you've brought to our doorstep.

Based on the error message you're seeing, it appears that the embed_documents method is not found in the OpenAIEmbeddings instance you're trying to use. This is likely because the embed_documents method is not a part of the OpenAIEmbeddings class.

The OpenAIEmbeddings class in LangChain is designed to generate embeddings for individual documents, not for a list of documents. Therefore, it doesn't have an embed_documents method. Instead, it has an embed_document method that takes a single document as input and returns its embedding.

Here's how you can modify your code to use the embed_document method:

# Instantiate the OpenAIEmbeddings class
openai = OpenAIEmbeddings(openai_api_key="sk-")

# Generate embeddings for your documents
documents = [doc for doc in documents]

# Create a Chroma vector store from the documents
vectorstore = Chroma.from_documents(documents, openai.embed_document)

Please note that this will generate embeddings for each document individually. If you want to generate embeddings for all documents at once, you might need to implement a custom embedding function that has an embed_documents method.

Alternatively, you can use a loop to generate embeddings for each document and add them to the Chroma vector store one by one:

# Instantiate the OpenAIEmbeddings class
openai = OpenAIEmbeddings(openai_api_key="sk-")

# Generate embeddings for your documents
documents = [doc for doc in documents]

# Create a Chroma vector store
vectorstore = Chroma()

# Add each document to the vector store individually
for doc in documents:
    vectorstore.add_text(doc, openai.embed_document(doc))

I hope this helps! If you have any other questions or run into any issues, please let me know.

Sources

• Bug after the openai updated in Embedding
• libs/langchain/langchain/vectorstores/chroma.py
• libs/core/langchain_core/embeddings.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.