forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
bc7e56e8df
Supporting asyncio in langchain primitives allows for users to run them concurrently and creates more seamless integration with asyncio-supported frameworks (FastAPI, etc.) Summary of changes: **LLM** * Add `agenerate` and `_agenerate` * Implement in OpenAI by leveraging `client.Completions.acreate` **Chain** * Add `arun`, `acall`, `_acall` * Implement them in `LLMChain` and `LLMMathChain` for now **Agent** * Refactor and leverage async chain and llm methods * Add ability for `Tools` to contain async coroutine * Implement async SerpaPI `arun` Create demo notebook. Open questions: * Should all the async stuff go in separate classes? I've seen both patterns (keeping the same class and having async and sync methods vs. having class separation) |
1 year ago | |
|---|---|---|
| .. | ||
| agents | 1 year ago | |
| callbacks | 1 year ago | |
| chains | 1 year ago | |
| docstore | 1 year ago | |
| document_loaders | 1 year ago | |
| embeddings | 1 year ago | |
| evaluation | 1 year ago | |
| llms | 1 year ago | |
| prompts | 1 year ago | |
| utilities | 1 year ago | |
| vectorstores | 1 year ago | |
| __init__.py | 1 year ago | |
| cache.py | 1 year ago | |
| docker-compose.yaml | 1 year ago | |
| example_generator.py | 1 year ago | |
| formatting.py | 2 years ago | |
| input.py | 1 year ago | |
| model_laboratory.py | 1 year ago | |
| py.typed | 2 years ago | |
| python.py | 1 year ago | |
| requests.py | 2 years ago | |
| schema.py | 1 year ago | |
| serpapi.py | 1 year ago | |
| server.py | 1 year ago | |
| sql_database.py | 1 year ago | |
| text_splitter.py | 1 year ago | |
| utils.py | 1 year ago | |