Zack Song

60th example error with litellm LLM

1

If the llama3 from ollama is running on http://8.140.18.**:28275, the following code from 60th example runs fine. ``` from txtai.pipeline import LLM llm = LLM("ollama/llama3", method="litellm", api_base="http://8.140.18.**:28275") def rag(question, text):...

New to txtai, some general questions

2

I'm familiar with Langchain's RAG process. When I first encountered Txtai, however, I was a bit uneasy. As the author mentioned, not all steps require LLM participation, and many models...

希望能接入自己开发的bot

5

### ⚠️ 搜索是否存在类似issue - [X] 我已经搜索过issues和disscussions，没有发现相似issue ### 总结 除开各种LLM，不知是否能支持通过web api对接自己开发的 bot，比如：特定目的RAG bot ### 举例 _No response_ ### 动机 希望能利用此项目对接自己开发的 rag bot，不知是否支持

**Describe the bug** When run the library with langserve, it shows error as below: ``` ERROR: Exception in ASGI application RuntimeError: super(): __class__ cell not found The above exception was...

client.model_name doesn't work for langchain ChatAnthropic

1

When running the below: ``` docs = Docs(llm="langchain", client=ChatAnthropic(temperature=0, model_name="claude-3-haiku-20240307"), prompts=prompts) ``` Error: ``` | File "D:\_Ai\my\free\free\langserve\paper\packages\ask-paper\ask_paper\util.py", line 85, in ask_paper | _docs = Docs(llm="langchain", client=ChatAnthropic(temperature=0, model_name="claude-3-haiku-20240307"), prompts=prompts) | File...

Any suggestion when to use autogen, when to use council? Thanks.

Within 'Connect your own data' section, a workflow of hacker_news has been generated and needed to be running. My questions are: 1) where to put the workflow file? save the...

Error when running 'python -m txtchat.agent wikitalk.yml' with Rocket.Chat=6.7.1 and txtai=7.2.0 and txtchat=0.2.0 ``` (txtai) songz:~/txtchat$ python -m txtchat.agent wikitalk.yml Loading checkpoint shards: 100%|██████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:01

I'm using automatic1111 API to call txt2img/img2img process and would like to take the advantage of multi-subject-render extension. But have no idea how to pass the settings to the extension...

How to add ChatGPT like bot to the Raven Channel?

5

Is it possible to add ChatGPT like chatbot in the channel? If so, how to do it?