llmflows

llmflows copied to clipboard

[FEATURE REQUEST]: Stream Results options

8

### The problem you are trying to solve: Streaming flow results eliminates dead time of users waiting around. I know it's not possible for intermediate flow steps, but the final...

jonnyjohnson1

[FEATURE REQUEST]: How to create a wikipedia Vector Store in your demo LLM-99

1

### The problem you are trying to solve: Thank you so much for your amazing work! I have experienced your LLM-99 physics demo and it‘s fantastic! I'm a little curious...

Connor-Shen

feat: added api_base optional parameter to OpenAI and OpenAIChat

1

feat: added api_base optional parameter to OpenAI and OpenAIChat to set custom base url for API calls. This is useful to reuse the OpenAI and OpenAIChat llms adapters with openai-compatible...

teomurgi

OpenAI() key default to "OPENAI_API_KEY"

1

### Describe the issue: OpenAI() has arg `api_key`. Why this does not default to os.environ['OPENAI_API_KEY']? ### Expected behavior `OpenAI()` is callable without args ### Reproduce the code example: ```python `OpenAI()`...

iuiu34

Bump jinja2 from 3.1.2 to 3.1.3 in /docs

1

Bumps [jinja2](https://github.com/pallets/jinja) from 3.1.2 to 3.1.3. Release notes Sourced from jinja2's releases. 3.1.3 This is a fix release for the 3.1.x feature branch. Fix for GHSA-h5c8-rqwp-cp95. You are affected if...

dependabot[bot]

Bump urllib3 from 1.26.17 to 1.26.18

1

Bumps [urllib3](https://github.com/urllib3/urllib3) from 1.26.17 to 1.26.18. Release notes Sourced from urllib3's releases. 1.26.18 Made body stripped from HTTP requests changing the request method to GET after HTTP 303 "See Other"...

dependabot[bot]

Bump urllib3 from 2.0.6 to 2.0.7 in /docs

1

Bumps [urllib3](https://github.com/urllib3/urllib3) from 2.0.6 to 2.0.7. Release notes Sourced from urllib3's releases. 2.0.7 Made body stripped from HTTP requests changing the request method to GET after HTTP 303 "See Other"...

dependabot[bot]

[FEATURE REQUEST]: llama.cpp wrapper

5

### The problem you are trying to solve: Currently the library only provides a wrapper for OpenAi models. ### Suggested new feature or change: Add an `LLM` wrapper for llama.cpp...

collin-klippel

refactor: consider data types for logically-grouped variables

3

https://github.com/stoyan-stoyanov/llmflows/blob/6ce79a8cc3b06e799d2b6eb6f6e8e78354f68dcd/llmflows/llms/openai.py#L80 I would always consider whether to make my code _more informative_ and cleaner by e.g. making a specific data type out of a tuple. Consider e.g. ```python from dataclasses...

inspiralpatterns

### The problem you are trying to solve: I would like to use Qdrant just like I am able to easily use Pinecone in flows. ### Suggested new feature or...

stoyan-stoyanov