github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-12 21:11:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

community[major], core[patch], langchain[patch], experimental[patch]: Create langchain-community (#14463)

Browse Source 
Moved the following modules to new package langchain-community in a backwards compatible fashion:

```
mv langchain/langchain/adapters community/langchain_community
mv langchain/langchain/callbacks community/langchain_community/callbacks
mv langchain/langchain/chat_loaders community/langchain_community
mv langchain/langchain/chat_models community/langchain_community
mv langchain/langchain/document_loaders community/langchain_community
mv langchain/langchain/docstore community/langchain_community
mv langchain/langchain/document_transformers community/langchain_community
mv langchain/langchain/embeddings community/langchain_community
mv langchain/langchain/graphs community/langchain_community
mv langchain/langchain/llms community/langchain_community
mv langchain/langchain/memory/chat_message_histories community/langchain_community
mv langchain/langchain/retrievers community/langchain_community
mv langchain/langchain/storage community/langchain_community
mv langchain/langchain/tools community/langchain_community
mv langchain/langchain/utilities community/langchain_community
mv langchain/langchain/vectorstores community/langchain_community
mv langchain/langchain/agents/agent_toolkits community/langchain_community
mv langchain/langchain/cache.py community/langchain_community
mv langchain/langchain/adapters community/langchain_community
mv langchain/langchain/callbacks community/langchain_community/callbacks
mv langchain/langchain/chat_loaders community/langchain_community
mv langchain/langchain/chat_models community/langchain_community
mv langchain/langchain/document_loaders community/langchain_community
mv langchain/langchain/docstore community/langchain_community
mv langchain/langchain/document_transformers community/langchain_community
mv langchain/langchain/embeddings community/langchain_community
mv langchain/langchain/graphs community/langchain_community
mv langchain/langchain/llms community/langchain_community
mv langchain/langchain/memory/chat_message_histories community/langchain_community
mv langchain/langchain/retrievers community/langchain_community
mv langchain/langchain/storage community/langchain_community
mv langchain/langchain/tools community/langchain_community
mv langchain/langchain/utilities community/langchain_community
mv langchain/langchain/vectorstores community/langchain_community
mv langchain/langchain/agents/agent_toolkits community/langchain_community
mv langchain/langchain/cache.py community/langchain_community
```

Moved the following to core
```
mv langchain/langchain/utils/json_schema.py core/langchain_core/utils
mv langchain/langchain/utils/html.py core/langchain_core/utils
mv langchain/langchain/utils/strings.py core/langchain_core/utils
cat langchain/langchain/utils/env.py >> core/langchain_core/utils/env.py
rm langchain/langchain/utils/env.py
```

See .scripts/community_split/script_integrations.sh for all changes
This commit is contained in:
Bagatur
2023-12-11 13:53:30 -08:00
committed by GitHub
parent c0f4b95aa9
commit ed58eeb9c5
2446 changed files with 171805 additions and 137118 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
libs/community/tests/integration_tests/embeddings/test_llamacpp.py Normal file
View File

@@ -0,0 +1,46 @@
# flake8: noqa
"""Test llamacpp embeddings."""
import os
from urllib.request import urlretrieve
from langchain_community.embeddings.llamacpp import LlamaCppEmbeddings
def get_model() -> str:
"""Download model.
From https://huggingface.co/Sosaka/Alpaca-native-4bit-ggml/,
convert to new ggml format and return model path.
"""
model_url = "https://huggingface.co/Sosaka/Alpaca-native-4bit-ggml/resolve/main/ggml-alpaca-7b-q4.bin"
tokenizer_url = "https://huggingface.co/decapoda-research/llama-7b-hf/resolve/main/tokenizer.model"
conversion_script = "https://github.com/ggerganov/llama.cpp/raw/master/convert-unversioned-ggml-to-ggml.py"
local_filename = model_url.split("/")[-1]
if not os.path.exists("convert-unversioned-ggml-to-ggml.py"):
urlretrieve(conversion_script, "convert-unversioned-ggml-to-ggml.py")
if not os.path.exists("tokenizer.model"):
urlretrieve(tokenizer_url, "tokenizer.model")
if not os.path.exists(local_filename):
urlretrieve(model_url, local_filename)
os.system("python convert-unversioned-ggml-to-ggml.py . tokenizer.model")
return local_filename
def test_llamacpp_embedding_documents() -> None:
"""Test llamacpp embeddings."""
documents = ["foo bar"]
model_path = get_model()
embedding = LlamaCppEmbeddings(model_path=model_path)
output = embedding.embed_documents(documents)
assert len(output) == 1
assert len(output[0]) == 512
def test_llamacpp_embedding_query() -> None:
"""Test llamacpp embeddings."""
document = "foo bar"
model_path = get_model()
embedding = LlamaCppEmbeddings(model_path=model_path)
output = embedding.embed_query(document)
assert len(output) == 512