I am trying to take a bunch of java files and create an embedding to be used by a LLM.
I have a method
<code>
from langchain_community.document_loaders.generic import GenericLoader
def load_documents():
loader = GenericLoader.from_filesystem(
"./path/to/java/files",
glob="**/*",
suffixes=[".java"],
parser=LanguageParser()
)
</code>
<code>
from langchain_community.document_loaders.generic import GenericLoader
def load_documents():
loader = GenericLoader.from_filesystem(
"./path/to/java/files",
glob="**/*",
suffixes=[".java"],
parser=LanguageParser()
)
</code>
from langchain_community.document_loaders.generic import GenericLoader
def load_documents():
loader = GenericLoader.from_filesystem(
"./path/to/java/files",
glob="**/*",
suffixes=[".java"],
parser=LanguageParser()
)
I am getting the following error
<code> main()
File "/Volumes/SamsungT5/langchain/populate_database.py", line 33, in main
documents = load_documents()
^^^^^^^^^^^^^^^^
File "/path/populate_database.py", line 50, in load_documents
return loader.load()
^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.11/site-packages/langchain_core/document_loaders/base.py", line 29, in load
return list(self.lazy_load())
^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.11/site-packages/langchain_community/document_loaders/generic.py", line 116, in lazy_load
yield from self.blob_parser.lazy_parse(blob)
File "/opt/anaconda3/lib/python3.11/site-packages/langchain_community/document_loaders/parsers/generic.py", line 70, in lazy_parse
raise ValueError(f"Unsupported mime type: {mimetype}")
ValueError: Unsupported mime type: text/x-java-source
</code>
<code> main()
File "/Volumes/SamsungT5/langchain/populate_database.py", line 33, in main
documents = load_documents()
^^^^^^^^^^^^^^^^
File "/path/populate_database.py", line 50, in load_documents
return loader.load()
^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.11/site-packages/langchain_core/document_loaders/base.py", line 29, in load
return list(self.lazy_load())
^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.11/site-packages/langchain_community/document_loaders/generic.py", line 116, in lazy_load
yield from self.blob_parser.lazy_parse(blob)
File "/opt/anaconda3/lib/python3.11/site-packages/langchain_community/document_loaders/parsers/generic.py", line 70, in lazy_parse
raise ValueError(f"Unsupported mime type: {mimetype}")
ValueError: Unsupported mime type: text/x-java-source
</code>
main()
File "/Volumes/SamsungT5/langchain/populate_database.py", line 33, in main
documents = load_documents()
^^^^^^^^^^^^^^^^
File "/path/populate_database.py", line 50, in load_documents
return loader.load()
^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.11/site-packages/langchain_core/document_loaders/base.py", line 29, in load
return list(self.lazy_load())
^^^^^^^^^^^^^^^^^^^^^^
File "/opt/anaconda3/lib/python3.11/site-packages/langchain_community/document_loaders/generic.py", line 116, in lazy_load
yield from self.blob_parser.lazy_parse(blob)
File "/opt/anaconda3/lib/python3.11/site-packages/langchain_community/document_loaders/parsers/generic.py", line 70, in lazy_parse
raise ValueError(f"Unsupported mime type: {mimetype}")
ValueError: Unsupported mime type: text/x-java-source
I have no clue why its telling me Unsupported mime type: text/x-java-source
. Its my understanding that java file loading is supported.