aws-ai-ml-workshop-kr icon indicating copy to clipboard operation
aws-ai-ml-workshop-kr copied to clipboard

Bump the pip group across 14 directories with 2 updates

Open dependabot[bot] opened this issue 1 year ago • 0 comments

Bumps the pip group with 1 update in the /genai/aws-gen-ai-kr/10_advanced_question_answering directory: langchain. Bumps the pip group with 1 update in the /genai/aws-gen-ai-kr/11_bedrock-with-opensearch directory: langchain. Bumps the pip group with 1 update in the /genai/aws-gen-ai-kr/30_fine_tune/04-deepspeed-on-sagemaker/notebook/scripts directory: transformers. Bumps the pip group with 1 update in the /genai/aws-gen-ai-kr/30_fine_tune/04-deepspeed-on-sagemaker/setup directory: transformers. Bumps the pip group with 1 update in the /genai/genai-app-demo/01-prompt-engineering-demo directory: langchain. Bumps the pip group with 1 update in the /genai/genai-app-demo/01-prompt-engineering-demo/sample_source/containers/comment directory: langchain. Bumps the pip group with 1 update in the /genai/genai-app-demo/01-prompt-engineering-demo/sample_source/containers/identification directory: langchain. Bumps the pip group with 1 update in the /genai/genai-app-demo/01-prompt-engineering-demo/sample_source/containers/image_gen directory: langchain. Bumps the pip group with 1 update in the /genai/genai-app-demo/01-prompt-engineering-demo/sample_source/containers/image_replace directory: langchain. Bumps the pip group with 1 update in the /genai/genai-app-demo/01-prompt-engineering-demo/sample_source/containers/image_variation directory: langchain. Bumps the pip group with 1 update in the /genai/genai-app-demo/01-prompt-engineering-demo/sample_source/containers/product_block directory: langchain. Bumps the pip group with 1 update in the /genai/genai-app-demo/01-prompt-engineering-demo/sample_source/containers/prompt directory: langchain. Bumps the pip group with 1 update in the /genai/genai-app-demo/01-prompt-engineering-demo/sample_source/containers/shortform directory: langchain. Bumps the pip group with 1 update in the /genai/genai-app-demo/01-prompt-engineering-demo/sample_source/containers/summarization directory: langchain.

Updates langchain from 0.0.348 to 0.2.3

Release notes

Sourced from langchain's releases.

langchain==0.2.3

Release langchain==0.2.3

Changes since langchain==0.2.2

langchain[patch]: Release 0.2.3 (#22644) multiple: get rid of pyproject extras (#22581) langchain[minor]: add universal init_model (#22039)

langchain-together==0.1.3

Release langchain-together==0.1.3

Changes since langchain-together==0.1.2

together: bump langchain-core (#22616) together[patch]: Release 0.1.3 (#22615) together, upstage: bump minimum langchain-openai version (#22505) infra: rm unused # noqa violations (#22049) partners: bump core in packages implementing ls_params (#21868) core, standard tests, partner packages: add test for model params (#21677)

langchain-community==0.2.3

Release langchain-community==0.2.3

Changes since langchain-community==0.2.2

community[patch]: Release 0.2.3 (#22562) community[patch]: improve test setup to accurately test filtering of labels in neo4j (#22531) community[minor]: Add support for metadata indexing policy in Cassandra vector store (#22548) community[minor]: add user agent for web scraping loaders (#22480) community[minor]: Add native async support to SQLChatMessageHistory (#22065) community[minor]: Improve InMemoryVectorStore with ability to persist to disk and filter on metadata. (#22186) community[patch]: add detailed paragraph and example for BaichuanTextEmbeddings (#22031) community[minor]: Added filter search for LanceDB (#22461) community: fix huggingface deprecations (#22522) community[minor]: Vectara Integration Update - Streaming, FCS, Chat, updates to documentation and example notebooks (#21334)

langchain-nomic==0.1.2

Release langchain-nomic==0.1.2

Changes since langchain-nomic==0.1.1

nomic[patch]: Release 0.1.2 (#22561) embeddings: nomic embed vision (#22482)

langchain-mongodb==0.1.6

Release langchain-mongodb==0.1.6

Changes since langchain-mongodb==0.1.5

mongodb[patch]: Release 0.1.6 (#22501) community, milvus, pinecone, qdrant, mongo: Broadcast operation failure while using simsimd beyond v3.7.7 (#22271) infra: rm unused # noqa violations (#22049)

langchain-milvus==0.1.1

... (truncated)

Commits

Updates langchain from 0.1.11 to 0.2.3

Release notes

Sourced from langchain's releases.

langchain==0.2.3

Release langchain==0.2.3

Changes since langchain==0.2.2

langchain[patch]: Release 0.2.3 (#22644) multiple: get rid of pyproject extras (#22581) langchain[minor]: add universal init_model (#22039)

langchain-together==0.1.3

Release langchain-together==0.1.3

Changes since langchain-together==0.1.2

together: bump langchain-core (#22616) together[patch]: Release 0.1.3 (#22615) together, upstage: bump minimum langchain-openai version (#22505) infra: rm unused # noqa violations (#22049) partners: bump core in packages implementing ls_params (#21868) core, standard tests, partner packages: add test for model params (#21677)

langchain-community==0.2.3

Release langchain-community==0.2.3

Changes since langchain-community==0.2.2

community[patch]: Release 0.2.3 (#22562) community[patch]: improve test setup to accurately test filtering of labels in neo4j (#22531) community[minor]: Add support for metadata indexing policy in Cassandra vector store (#22548) community[minor]: add user agent for web scraping loaders (#22480) community[minor]: Add native async support to SQLChatMessageHistory (#22065) community[minor]: Improve InMemoryVectorStore with ability to persist to disk and filter on metadata. (#22186) community[patch]: add detailed paragraph and example for BaichuanTextEmbeddings (#22031) community[minor]: Added filter search for LanceDB (#22461) community: fix huggingface deprecations (#22522) community[minor]: Vectara Integration Update - Streaming, FCS, Chat, updates to documentation and example notebooks (#21334)

langchain-nomic==0.1.2

Release langchain-nomic==0.1.2

Changes since langchain-nomic==0.1.1

nomic[patch]: Release 0.1.2 (#22561) embeddings: nomic embed vision (#22482)

langchain-mongodb==0.1.6

Release langchain-mongodb==0.1.6

Changes since langchain-mongodb==0.1.5

mongodb[patch]: Release 0.1.6 (#22501) community, milvus, pinecone, qdrant, mongo: Broadcast operation failure while using simsimd beyond v3.7.7 (#22271) infra: rm unused # noqa violations (#22049)

langchain-milvus==0.1.1

... (truncated)

Commits

Updates transformers from 4.30.2 to 4.38.0

Release notes

Sourced from transformers's releases.

v4.38: Gemma, Depth Anything, Stable LM; Static Cache, HF Quantizer, AQLM

New model additions

💎 Gemma 💎

Gemma is a new opensource Language Model series from Google AI that comes with a 2B and 7B variant. The release comes with the pre-trained and instruction fine-tuned versions and you can use them via AutoModelForCausalLM, GemmaForCausalLM or pipeline interface!

Read more about it in the Gemma release blogpost: https://hf.co/blog/gemma

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b") model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.float16)

input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)

You can use the model with Flash Attention, SDPA, Static cache and quantization API for further optimizations !

  • Flash Attention 2
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")

model = AutoModelForCausalLM.from_pretrained( "google/gemma-2b", device_map="auto", torch_dtype=torch.float16, attn_implementation="flash_attention_2" )

input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)

  • bitsandbytes-4bit
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")

model = AutoModelForCausalLM.from_pretrained( "google/gemma-2b", device_map="auto", load_in_4bit=True ) </tr></table>

... (truncated)

Commits
  • 08ab54a [ gemma] Adds support for Gemma 💎 (#29167)
  • 2de9314 [Maskformer] safely get backbone config (#29166)
  • 476957b 🚨 Llama: update rope scaling to match static cache changes (#29143)
  • 7a4bec6 Release: 4.38.0
  • ee3af60 Add support for fine-tuning CLIP-like models using contrastive-image-text exa...
  • 0996a10 Revert low cpu mem tie weights (#29135)
  • 15cfe38 [Core tokenization] add_dummy_prefix_space option to help with latest is...
  • efdd436 FIX [PEFT / Trainer ] Handle better peft + quantized compiled models (#29...
  • 5e95dca [cuda kernels] only compile them when initializing (#29133)
  • a7755d2 Generate: unset GenerationConfig parameters do not raise warning (#29119)
  • Additional commits viewable in compare view

Updates transformers from 4.30.2 to 4.38.0

Release notes

Sourced from transformers's releases.

v4.38: Gemma, Depth Anything, Stable LM; Static Cache, HF Quantizer, AQLM

New model additions

💎 Gemma 💎

Gemma is a new opensource Language Model series from Google AI that comes with a 2B and 7B variant. The release comes with the pre-trained and instruction fine-tuned versions and you can use them via AutoModelForCausalLM, GemmaForCausalLM or pipeline interface!

Read more about it in the Gemma release blogpost: https://hf.co/blog/gemma

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b") model = AutoModelForCausalLM.from_pretrained("google/gemma-2b", device_map="auto", torch_dtype=torch.float16)

input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)

You can use the model with Flash Attention, SDPA, Static cache and quantization API for further optimizations !

  • Flash Attention 2
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")

model = AutoModelForCausalLM.from_pretrained( "google/gemma-2b", device_map="auto", torch_dtype=torch.float16, attn_implementation="flash_attention_2" )

input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

outputs = model.generate(**input_ids)

  • bitsandbytes-4bit
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2b")

model = AutoModelForCausalLM.from_pretrained( "google/gemma-2b", device_map="auto", load_in_4bit=True ) </tr></table>

... (truncated)

Commits
  • 08ab54a [ gemma] Adds support for Gemma 💎 (#29167)
  • 2de9314 [Maskformer] safely get backbone config (#29166)
  • 476957b 🚨 Llama: update rope scaling to match static cache changes (#29143)
  • 7a4bec6 Release: 4.38.0
  • ee3af60 Add support for fine-tuning CLIP-like models using contrastive-image-text exa...
  • 0996a10 Revert low cpu mem tie weights (#29135)
  • 15cfe38 [Core tokenization] add_dummy_prefix_space option to help with latest is...
  • efdd436 FIX [PEFT / Trainer ] Handle better peft + quantized compiled models (#29...
  • 5e95dca [cuda kernels] only compile them when initializing (#29133)
  • a7755d2 Generate: unset GenerationConfig parameters do not raise warning (#29119)
  • Additional commits viewable in compare view

Updates langchain from 0.1.12 to 0.2.3

Release notes

Sourced from langchain's releases.

langchain==0.2.3

Release langchain==0.2.3

Changes since langchain==0.2.2

langchain[patch]: Release 0.2.3 (#22644) multiple: get rid of pyproject extras (#22581) langchain[minor]: add universal init_model (#22039)

langchain-together==0.1.3

Release langchain-together==0.1.3

Changes since langchain-together==0.1.2

together: bump langchain-core (#22616) together[patch]: Release 0.1.3 (#22615) together, upstage: bump minimum langchain-openai version (#22505) infra: rm unused # noqa violations (#22049) partners: bump core in packages implementing ls_params (#21868) core, standard tests, partner packages: add test for model params (#21677)

langchain-community==0.2.3

Release langchain-community==0.2.3

Changes since langchain-community==0.2.2

community[patch]: Release 0.2.3 (#22562) community[patch]: improve test setup to accurately test filtering of labels in neo4j (#22531) community[minor]: Add support for metadata indexing policy in Cassandra vector store (#22548) community[minor]: add user agent for web scraping loaders (#22480) community[minor]: Add native async support to SQLChatMessageHistory (#22065) community[minor]: Improve InMemoryVectorStore with ability to persist to disk and filter on metadata. (#22186) community[patch]: add detailed paragraph and example for BaichuanTextEmbeddings (#22031) community[minor]: Added filter search for LanceDB (#22461) community: fix huggingface deprecations (#22522) community[minor]: Vectara Integration Update - Streaming, FCS, Chat, updates to documentation and example notebooks (#21334)

langchain-nomic==0.1.2

Release langchain-nomic==0.1.2

Changes since langchain-nomic==0.1.1

nomic[patch]: Release 0.1.2 (#22561) embeddings: nomic embed vision (#22482)

langchain-mongodb==0.1.6

Release langchain-mongodb==0.1.6

Changes since langchain-mongodb==0.1.5

mongodb[patch]: Release 0.1.6 (#22501) community, milvus, pinecone, qdrant, mongo: Broadcast operation failure while using simsimd beyond v3.7.7 (#22271) infra: rm unused # noqa violations (#22049)

langchain-milvus==0.1.1

... (truncated)

Commits

Updates langchain from 0.1.12 to 0.2.3

Release notes

Sourced from langchain's releases.

langchain==0.2.3

Release langchain==0.2.3

Changes since langchain==0.2.2

langchain[patch]: Release 0.2.3 (#22644) multiple: get rid of pyproject extras (#22581) langchain[minor]: add universal init_model (#22039)

langchain-together==0.1.3

Release langchain-together==0.1.3

Changes since langchain-together==0.1.2

together: bump langchain-core (#22616) together[patch]: Release 0.1.3 (#22615) together, upstage: bump minimum langchain-openai version (#22505) infra: rm unused # noqa violations (#22049) partners: bump core in packages implementing ls_params (#21868) core, standard tests, partner packages: add test for model params (#21677)

langchain-community==0.2.3

Release langchain-community==0.2.3

Changes since langchain-community==0.2.2

community[patch]: Release 0.2.3 (#22562) community[patch]: improve test setup to accurately test filtering of labels in neo4j (#22531) community[minor]: Add support for metadata indexing policy in Cassandra vector store (#22548) community[minor]: add user agent for web scraping loaders (#22480) community[minor]: Add native async support to SQLChatMessageHistory (#22065) community[minor]: Improve InMemoryVectorStore with ability to persist to disk and filter on metadata. (#22186) community[patch]: add detailed paragraph and example for BaichuanTextEmbeddings (#22031) community[minor]: Added filter search for LanceDB (#22461) community: fix huggingface deprecations (#22522) community[minor]: Vectara Integration Update - Streaming, FCS, Chat, updates to documentation and example notebooks (#21334)

langchain-nomic==0.1.2

Release langchain-nomic==0.1.2

Changes since langchain-nomic==0.1.1

nomic[patch]: Release 0.1.2 (#22561) embeddings: nomic embed vision (#22482)

langchain-mongodb==0.1.6

Release langchain-mongodb==0.1.6

Changes since langchain-mongodb==0.1.5

mongodb[patch]: Release 0.1.6 (#22501) community, milvus, pinecone, qdrant, mongo: Broadcast operation failure while using simsimd beyond v3.7.7 (#22271) infra: rm unused # noqa violations (#22049)

langchain-milvus==0.1.1

... (truncated)

Commits

Updates langchain from 0.1.12 to 0.2.3

Release notes

Sourced from langchain's releases.

langchain==0.2.3

Release langchain==0.2.3

Changes since langchain==0.2.2

langchain[patch]: Release 0.2.3 (#22644) multiple: get rid of pyproject extras (#22581) langchain[minor]: add universal init_model (#22039)

langchain-together==0.1.3

Release langchain-together==0.1.3

Changes since langchain-together==0.1.2

together: bump langchain-core (#22616) together[patch]: Release 0.1.3 (#22615) together, upstage: bump minimum langchain-openai version (#22505) infra: rm unused # noqa violations (#22049) partners: bump core in packages implementing ls_params (#21868) core, standard tests, partner packages: add test for model params (#21677)

langchain-community==0.2.3

Release langchain-community==0.2.3

Changes since langchain-community==0.2.2

community[patch]: Release 0.2.3 (#22562) community[patch]: improve test setup to accurately test filtering of labels in neo4j (#22531) community[minor]: Add support for metadata indexing policy in Cassandra vector store (#22548) community[minor]: add user agent for web scraping loaders (#22480) community[minor]: Add native async support to SQLChatMessageHistory (#22065) community[minor]: Improve InMemoryVectorStore with ability to persist to disk and filter on metadata. (#22186) community[patch]: add detailed paragraph and example for BaichuanTextEmbeddings (#22031) community[minor]: Added filter search for LanceDB (#22461) community: fix huggingface deprecations (#22522) community[minor]: Vectara Integration Update - Streaming, FCS, Chat, updates to documentation and example notebooks (#21334)

langchain-nomic==0.1.2

Release langchain-nomic==0.1.2

Changes since langchain-nomic==0.1.1

nomic[patch]: Release 0.1.2 (#22561) embeddings: nomic embed vision (#22482)

langchain-mongodb==0.1.6

Release langchain-mongodb==0.1.6

Changes since langchain-mongodb==0.1.5

mongodb[patch]: Release 0.1.6 (#22501) community, milvus, pinecone, qdrant, mongo: Broadcast operation failure while using simsimd beyond v3.7.7 (#22271) infra: rm unused # noqa violations (#22049)

langchain-milvus==0.1.1

... (truncated)

Commits

Updates langchain from 0.1.12 to 0.2.3

Release notes

Sourced from langchain's releases.

langchain==0.2.3

Release langchain==0.2.3

Changes since langchain==0.2.2

langchain[patch]: Release 0.2.3 (#22644) multiple: get rid of pyproject extras (#22581) langchain[minor]: add universal init_model (#22039)

langchain-together==0.1.3

Release langchain-together==0.1.3

Changes since langchain-together==0.1.2

together: bump langchain-core (#22616) together[patch]: Release 0.1.3 (#22615) together, upstage: bump minimum langchain-openai version (#22505) infra: rm unused # noqa violations (#22049) partners: bump core in packages implementing ls_params (#21868) core, standard tests, partner packages: add test for model params (#21677)

langchain-community==0.2.3

Release langchain-community==0.2.3

Changes since langchain-community==0.2.2

community[patch]: Release 0.2.3 (#22562) community[patch]: improve test setup to accurately test filtering of labels in neo4j (#22531) community[minor]: Add support for metadata indexing policy in Cassandra vector store (#22548) community[minor]: add user agent for web scraping loaders (#22480) community[minor]: Add native async support to SQLChatMessageHistory (#22065) community[minor]: Improve InMemoryVectorStore with ability to persist to disk and filter on metadata. (#22186) community[patch]: add detailed paragraph and example for BaichuanTextEmbeddings (#22031) community[minor]: Added filter search for LanceDB (#22461) community: fix huggingface deprecations (#22522) community[minor]: Vectara Integration Update - Streaming, FCS, Chat, updates to documentation and example notebooks (#21334)

langchain-nomic==0.1.2

Release langchain-nomic==0.1.2

Changes since langchain-nomic==0.1.1

nomic[patch]: Release 0.1.2 (#22561) embeddings: nomic embed vision (#22482)

langchain-mongodb==0.1.6

Release langchain-mongodb==0.1.6

Changes since langchain-mongodb==0.1.5

mongodb[patch]: Release 0.1.6 (#22501) community, milvus, pinecone, qdrant, mongo: Broadcast operation failure while using simsimd beyond v3.7.7 (#22271) infra: rm unused # noqa violations (#22049)

langchain-milvus==0.1.1

... (truncated)

Commits

Updates langchain from 0.1.12 to 0.2.3

Release notes

Sourced from langchain's releases.

langchain==0.2.3

Release langchain==0.2.3

Changes since langchain==0.2.2

langchain[patch]: Release 0.2.3 (#22644) multiple: get rid of pyproject extras (#22581) langchain[minor]: add universal init_model (#22039)

langchain-together==0.1.3

Release langchain-together==0.1.3

Changes since langchain-together==0.1.2

together: bump langchain-core (#22616) together[patch]: Release 0.1.3 (#22615) together, upstage: bump minimum langchain-openai version (#22505) infra: rm unused # noqa violations (#22049) partners: bump core in packages implementing ls_params (#21868) core, standard tests, partner packages: add test for model params (#21677)

langchain-community==0.2.3

Release langchain-community==0.2.3

Changes since langchain-community==0.2.2

community[patch]: Release 0.2.3 (#22562) community[patch]: improve test setup to accurately test filtering of labels in neo4j (#22531) community[minor]: Add support for metadata indexing policy in Cassandra vector store (#22548) community[minor]: add user agent for web scraping loaders (#22480) community[minor]: Add native async support to SQLChatMessageHistory (#22065) community[minor]: Improve InMemoryVectorStore with ability to persist to disk and filter on metadata. (#22186) community[patch]: add detailed paragraph and example for BaichuanTextEmbeddings (#22031) community[minor]: Added filter search for LanceDB (#22461) community: fix huggingface deprecations (#22522) community[minor]: Vectara Integration Update - Streaming, FCS, Chat, updates to documentation and example notebooks (#21334)

langchain-nomic==0.1.2

Release langchain-nomic==0.1.2

Changes since langchain-nomic==0.1.1

nomic[patch]: Release 0.1.2 (#22561) embeddings: nomic embed vision (#22482)

langchain-mongodb==0.1.6

Release langchain-mongodb==0.1.6

Changes since langchain-mongodb==0.1.5

mongodb[patch]: Release 0.1.6 (#22501) community, milvus, pinecone, qdrant, mongo: Broadcast operation failure while using simsimd beyond v3.7.7 (#22271) infra: rm unused # noqa violations (#22049)

langchain-milvus==0.1.1

... (truncated)

Commits

Updates langchain from 0.1.12 to 0.2.3

Release notes

Sourced from langchain's releases.

langchain==0.2.3

Release langchain==0.2.3

Changes since langchain==0.2.2

langchain[patch]: Release 0.2.3 (#22644) multiple: get rid of pyproject extras (#22581) langchain[minor]: add universal init_model (#22039)

langchain-together==0.1.3

Release langchain-together==0.1.3

Changes since langchain-together==0.1.2

together: bump langchain-core (#22616) together[patch]: Release 0.1.3 (#22615) together, upstage: bump minimum langchain-openai version (#22505) infra: rm unused # noqa violations (#22049) partners: bump core in packages implementing ls_params (#21868) core, standard tests, partner packages: add test for model params (#21677)

langchain-community==0.2.3

Release langchain-community==0.2.3

Changes since langchain-community==0.2.2

community[patch]: Release 0.2.3 (#22562) community[patch]: improve test setup to accurately test filtering of labels in neo4j (#22531) community[minor]: Add support for metadata indexing policy in Cassandra vector store (#22548) community[minor]: add user agent for web scraping loaders (#22480) community[minor]: Add native async support to SQLChatMessageHistory (Description%20has%20been%20truncated

%0A" rel="nofollow" target="_blank" >

dependabot[bot] avatar Jun 09 '24 12:06 dependabot[bot]