mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
1a55e950aa
**Description:** #18040 forces `fastembed>2.0`, and this causes dependency conflicts with the new `unstructured` package (different `onnxruntime`). There may be other dependency conflicts.. The only way to use `langchain-community>=0.0.28` is rollback to `unstructured 0.10.X`. But new `unstructured` contains many fixes. This PR allows to use both `fastembed` `v1` and `v2`. How to reproduce: `pyproject.toml`: ```toml [tool.poetry] name = "depstest" version = "0.0.0" description = "test" authors = ["<dev@example.org>"] [tool.poetry.dependencies] python = ">=3.10,<3.12" langchain-community = "^0.0.28" fastembed = "^0.2.0" unstructured = {extras = ["pdf"], version = "^0.12"} ``` ```bash $ poetry lock ``` Co-authored-by: Sergey Kozlov <sergey.kozlov@ludditelabs.io> |
||
---|---|---|
.. | ||
__init__.py | ||
aleph_alpha.py | ||
awa.py | ||
azure_openai.py | ||
baichuan.py | ||
baidu_qianfan_endpoint.py | ||
bedrock.py | ||
bookend.py | ||
clarifai.py | ||
cloudflare_workersai.py | ||
cohere.py | ||
dashscope.py | ||
databricks.py | ||
deepinfra.py | ||
edenai.py | ||
elasticsearch.py | ||
embaas.py | ||
ernie.py | ||
fake.py | ||
fastembed.py | ||
google_palm.py | ||
gpt4all.py | ||
gradient_ai.py | ||
huggingface_hub.py | ||
huggingface.py | ||
infinity_local.py | ||
infinity.py | ||
javelin_ai_gateway.py | ||
jina.py | ||
johnsnowlabs.py | ||
laser.py | ||
llamacpp.py | ||
llamafile.py | ||
llm_rails.py | ||
localai.py | ||
minimax.py | ||
mlflow_gateway.py | ||
mlflow.py | ||
modelscope_hub.py | ||
mosaicml.py | ||
nemo.py | ||
nlpcloud.py | ||
oci_generative_ai.py | ||
octoai_embeddings.py | ||
ollama.py | ||
openai.py | ||
optimum_intel.py | ||
sagemaker_endpoint.py | ||
self_hosted_hugging_face.py | ||
self_hosted.py | ||
sentence_transformer.py | ||
spacy_embeddings.py | ||
sparkllm.py | ||
tensorflow_hub.py | ||
vertexai.py | ||
volcengine.py | ||
voyageai.py | ||
xinference.py | ||
yandex.py |