quivr/backend/requirements.txt

pymupdf==1.22.3
langchain==0.0.207
Markdown==3.4.3
openai==0.27.6
pdf2image==1.16.3
pypdf==3.8.1
StrEnum==0.4.10
supabase==1.0.3
tiktoken==0.4.0
unstructured==0.6.5
anthropic==0.2.8
fastapi==0.95.2
python-multipart==0.0.6
uvicorn==0.22.0
pypandoc==1.11
docx2txt==0.8
guidance==0.0.53
python-jose==3.3.0
google_cloud_aiplatform==1.25.0
transformers==4.30.1
asyncpg==0.27.0
flake8==6.0.0
flake8-black==0.3.6
sentence_transformers>=2.0.0
sentry-sdk==1.26.0
feat(pdf): added new pdf miner that works 2023-06-06 12:18:33 +03:00			`pymupdf==1.22.3`
feat(chat): use openai function for answer (#354) * feat(chat): use openai function for answer (backend) * feat(chat): use openai function for answer (frontend) * chore: refacto BrainPicking * feat: update chat creation logic * feat: simplify chat system logic * feat: set default method to gpt-3.5-turbo-0613 * feat: use user own openai key * feat(chat): slightly improve prompts * feat: add global error interceptor * feat: remove unused endpoints * docs: update chat system doc * chore(linter): add unused import remove config * feat: improve dx * feat: improve OpenAiFunctionBasedAnswerGenerator prompt 2023-06-22 18:50:06 +03:00			`langchain==0.0.207`
feat(init): init repository 2023-05-13 00:05:31 +03:00			`Markdown==3.4.3`
			`openai==0.27.6`
fix(requirements): fixed the issue 2023-05-13 17:37:18 +03:00			`pdf2image==1.16.3`
feat(init): init repository 2023-05-13 00:05:31 +03:00			`pypdf==3.8.1`
			`StrEnum==0.4.10`
			`supabase==1.0.3`
			`tiktoken==0.4.0`
			`unstructured==0.6.5`
Support for Anthropics Models This update enhances the "Second Brain" application by adding support for Anthropics AI models. Users can now use not only OpenAI's GPT-3/4, but also Anthropics' Claude models to store and query their knowledge. Key changes include: Added an anthropic_api_key field in the secrets configuration file. Introduced a selection for different AI models including GPT-3, GPT-4, and various versions of Claude. Updated question handling to be model-agnostic, and added support for Anthropics' Claude models in the question processing workflow. Modified the streamlit interface to allow users to input their choice of model, control the "temperature" of the model's responses, and set the max tokens limit. Upgraded requirements.txt file with the latest version of the Anthropics library. This update empowers users to leverage different AI models based on their needs, providing a more flexible and robust tool for knowledge management. 2023-05-14 11:30:03 +03:00			`anthropic==0.2.8`
feat(api): new api init 2023-05-18 02:22:13 +03:00			`fastapi==0.95.2`
			`python-multipart==0.0.6`
Add epub loader to parse epub uploads. 2023-05-21 09:15:31 +03:00			`uvicorn==0.22.0`
Merge branch 'main' into main 2023-05-21 10:34:31 +03:00			`pypandoc==1.11`
			`docx2txt==0.8`
add summarization backend 2023-05-22 09:39:55 +03:00			`guidance==0.0.53`
VertexAI Google Cloud Palm2 Support (#226) * feat(bard): added * docs(readme): update * chore(print): removed 2023-06-01 17:01:27 +03:00			`python-jose==3.3.0`
feat(pdf): added new pdf miner that works 2023-06-06 12:18:33 +03:00			`google_cloud_aiplatform==1.25.0`
fix(google): requirements 2023-06-12 18:37:58 +03:00			`transformers==4.30.1`
feat: user can create api keys (#329) * feat: user can create api keys * fix: linting on build * Update backend/routes/api_key_routes.py * chore: rename and refactor AuthBearer * chore: add types 2023-06-14 22:21:13 +03:00			`asyncpg==0.27.0`
Feat: chat name edit (#343) * feat(chat): add name update * chore(linting): add flake8 * feat: add chat name edit 2023-06-20 10:54:23 +03:00			`flake8==6.0.0`
			`flake8-black==0.3.6`
feat: private llm (#360) * feat: private llm * Update backend/vectorstore/supabase.py * Update backend/vectorstore/supabase.py 2023-06-22 11:45:35 +03:00			`sentence_transformers>=2.0.0`
feat(sentry): added sentry (#443) 2023-07-01 22:12:13 +03:00			`sentry-sdk==1.26.0`