Trying to create chroma embedding from langchain to later use it with googlepalm, my code is: vectorstore = Chroma.from_texts(to_vectorize, embedding=embeddings, metadatas=few_shots ), few_shots is a list of strings. My error is: ValueError: Expected EmbeddingFunction.__call__ to have the following signature: odict_keys(['self', 'input']), got odict_keys(['self', 'args', 'kwargs']). Frankly speaking i am new to LLM and I didn't understand what's happening with migration e.t.c. I would highly appreciate your help.

[sultanbeishenkulov]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

from langchain.prompts import SemanticSimilarityExampleSelector
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import Chroma
from few_shots import few_shots
from langchain.vectorstores import Chroma


embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')


to_vectorize = [
    " ".join(
        str(value) if not isinstance(value, dict) else " ".join(f"{k}: {v}" for k, v in value.items())
        for value in example.values()
    )
    for example in few_shots
]
vectorstore = Chroma.from_texts(
    to_vectorize, 
    embedding=embeddings, 
    metadatas=few_shots
)

Description

Trying to create chroma embedding from langchain to later use it with googlepalm, my code is: vectorstore = Chroma.from_texts(to_vectorize, embedding=embeddings, metadatas=few_shots ), few_shots is a list of strings. My error is: ValueError: Expected EmbeddingFunction.call to have the following signature: odict_keys(['self', 'input']), got odict_keys(['self', 'args', 'kwargs']). Frankly speaking i am new to LLM and I didn't understand what's happening with migration e.t.c. I would highly appreciate your help.

System Info

Python Version: 3.9.12 (main, Apr 5 2022, 01:53:17)
[Clang 12.0.0 ]

Package Information

langchain_core: 0.2.12
langchain: 0.2.7
langsmith: 0.1.84
langchain_experimental: 0.0.25
langchain_setup: Installed. No version info available.
langchain_text_splitters: 0.2.2

[dosubot[bot]]

Hello, @sultanbeishenkulov! I'm here to help you with your technical issues and questions while you wait for a human maintainer. Let's squash those bugs together! 🤖

To resolve the ValueError: Expected EmbeddingFunction.__call__ to have the following signature: odict_keys(['self', 'input']), got odict_keys(['self', 'args', 'kwargs']) error, you need to ensure that the __call__ method of your embedding function has the correct signature. Specifically, it should accept self and input as parameters, not self, args, and kwargs.

Here's how you can define the __call__ method correctly:

class CorrectEmbeddingFunction:
    def __call__(self, input):
        # Your embedding logic here
        pass

In your case, since you are using HuggingFaceEmbeddings, you should ensure that the HuggingFaceEmbeddings class is correctly implemented. If you are using an older version of LangChain, you might need to update it to the latest version to ensure compatibility.

Additionally, you can update your LangChain and Chroma packages to the latest versions to avoid any compatibility issues:

pip install -U langchain chromadb

This should resolve the issue with the EmbeddingFunction.__call__ method signature ^[1][2].

To continue talking to Dosu, mention @dosu.