langchain/templates/rag-multi-modal-local/ingest.py
Bagatur fa5d49f2c1
docs, experimental[patch], langchain[patch], community[patch]: update storage imports (#15429)
ran 
```bash
g grep -l "langchain.vectorstores" | xargs -L 1 sed -i '' "s/langchain\.vectorstores/langchain_community.vectorstores/g"
g grep -l "langchain.document_loaders" | xargs -L 1 sed -i '' "s/langchain\.document_loaders/langchain_community.document_loaders/g"
g grep -l "langchain.chat_loaders" | xargs -L 1 sed -i '' "s/langchain\.chat_loaders/langchain_community.chat_loaders/g"
g grep -l "langchain.document_transformers" | xargs -L 1 sed -i '' "s/langchain\.document_transformers/langchain_community.document_transformers/g"
g grep -l "langchain\.graphs" | xargs -L 1 sed -i '' "s/langchain\.graphs/langchain_community.graphs/g"
g grep -l "langchain\.memory\.chat_message_histories" | xargs -L 1 sed -i '' "s/langchain\.memory\.chat_message_histories/langchain_community.chat_message_histories/g"
gco master libs/langchain/tests/unit_tests/*/test_imports.py
gco master libs/langchain/tests/unit_tests/**/test_public_api.py
```
2024-01-02 16:47:11 -05:00

36 lines
1017 B
Python

import os
from pathlib import Path
from langchain_community.vectorstores import Chroma
from langchain_experimental.open_clip import OpenCLIPEmbeddings
# Load images
img_dump_path = Path(__file__).parent / "docs/"
rel_img_dump_path = img_dump_path.relative_to(Path.cwd())
image_uris = sorted(
[
os.path.join(rel_img_dump_path, image_name)
for image_name in os.listdir(rel_img_dump_path)
if image_name.endswith(".jpg")
]
)
# Index
vectorstore = Path(__file__).parent / "chroma_db_multi_modal"
re_vectorstore_path = vectorstore.relative_to(Path.cwd())
# Load embedding function
print("Loading embedding function")
embedding = OpenCLIPEmbeddings(model_name="ViT-H-14", checkpoint="laion2b_s32b_b79k")
# Create chroma
vectorstore_mmembd = Chroma(
collection_name="multi-modal-rag",
persist_directory=str(Path(__file__).parent / "chroma_db_multi_modal"),
embedding_function=embedding,
)
# Add images
print("Embedding images")
vectorstore_mmembd.add_images(uris=image_uris)