From what I understand, you reported an issue with the recent code change in Chroma Collection where embedding functions are being sent as None. This issue was confirmed by keviddles and harithzulfaizal. A fix was proposed in pull request#1444by timothyasp and merged. However, it seems that...
Strictly speaking, this is not a bug rather the constraint chroma imposed. However, I find that chroma has a too strict EmbeddingFunction typing which is not suitable for my usecase and it prevents me from doing the proper thing. In short, chroma only allow a single D type variable (eithe...
>= 3.35.0错误，尽管sqlite3 3.43.0可用通过上面的URL和Chroma的信息源代码建议了一个解决方案。第...
>= 3.35.0错误，尽管sqlite3 3.43.0可用通过上面的URL和Chroma的信息源代码建议了一个解决方案。第...
The Chroma constructor in the vectorstore section uses the document function when it should be the query function for embeddings. As a result, if the documents parameter is blank when using Chroma, Langchain will error out with a ValidationError. Please change line 95 to be embed_query instead...
chromadb version 0.5.7, chroma-hnswlib 0.7.6 (this was installed by chroma, not me directly) python 3.10.12 Ubuntu 22.04 Relevant log output ValueError: Expected EmbeddingFunction.__call__ to have the following signature: odict_keys(['self','input']), got odict_keys(['self','args',...
bug location: site-packages\chromadb\utils\embedding_functions.py class ONNXMiniLM_L6_V2(EmbeddingFunction[Documents]): MODEL_NAME = "all-MiniLM-L6-v2" DOWNLOAD_PATH = Path.home() / ".cache" / "chroma" / "onnx_models" / MODEL_NAME EXTRACTED_FOLDER_NAME = "onnx" ARCHIVE_FILENAME = ...
atroynpushed a commit to csbasil/chroma that referenced this pull requestApr 3, 2024 [ENH]: Ollama embedding function (chroma-core#1813) e34d882 tazarovadded a commit to amikos-tech/chroma-docs that referenced this pull requestApr 5, 2024 ...
Closed kamalendugarai What happened? I am using js api and I have copied the code fromhttps://docs.trychroma.com/getting-started. I realised that we need to set embeddings explicitly. I am using Ollama. So, I am trying to load... ...
Hi, i was randomly browsing Chroma documentation, realised that the default embedding funfction (API integration) for JinaAI is stilljina-embeddings-v2, can we update the default model to support jina-embeddings-v3? The advantage: better performance ...