Fix deprecated langchain warning for llama3 #953
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Thanks for the PR! output Could you please help me resolve the error? I may recommend updating markdown with the new Trace after every cell with code. |
|
Would you like to address deprecation warnings in 3rd and 8th cells? 8th ### Router |
|
You may take a look on this PR #905 for more context |
|
Thanks @IgorKasianenko - addressed the deprecation warnings in 3rd/8th cells & included the updated trace. Interestingly I can't reproduce the error in the last cell, it does seem to work for me... |
|
After installing the conda env from scratch and creating new langchain API key I can confirm that I am facing the same error as #894 (comment) Todays error log Debugging it as stand alone function works as expected: |
|
@sviswana I checked it with all small models and they result in the same issue: |
mhossain-lab
approved these changes
May 29, 2025
|
yea it's super strange - b/c I'm using the small llama3.2:1b model myself |
IgorKasianenko
approved these changes
Jun 3, 2025
| "from langchain_community.document_loaders import WebBaseLoader\n", | ||
| "from langchain_community.vectorstores import Chroma\n", | ||
| "from langchain_community.embeddings import HuggingFaceEmbeddings\n", | ||
| "from langchain_huggingface import HuggingFaceEmbeddings\n", |
There was a problem hiding this comment.
I have created brand new conda env to test it end to end and I am getting
---------------------------------------------------------------------------
ModuleNotFoundError Traceback (most recent call last)
Cell In[4], line 14
6 from langchain_huggingface import HuggingFaceEmbeddings
8 urls = [
9 "https://lilianweng.github.io/posts/2023-06-23-agent/",
10 "https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/",
11 "https://lilianweng.github.io/posts/2023-10-25-adv-attack-llm/",
12 ]
---> 14 docs = [WebBaseLoader(url).load() for url in urls]
15 docs_list = [item for sublist in docs for item in sublist]
17 text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
18 chunk_size=250, chunk_overlap=0
19 )
Cell In[4], line 14, in <listcomp>(.0)
6 from langchain_huggingface import HuggingFaceEmbeddings
8 urls = [
9 "https://lilianweng.github.io/posts/2023-06-23-agent/",
10 "https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/",
11 "https://lilianweng.github.io/posts/2023-10-25-adv-attack-llm/",
12 ]
---> 14 docs = [WebBaseLoader(url).load() for url in urls]
15 docs_list = [item for sublist in docs for item in sublist]
17 text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
...
--> 347 from bs4 import BeautifulSoup
349 if parser is None:
350 if url.endswith(".xml"):
ModuleNotFoundError: No module named 'bs4'
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Fixes # 894 (raised in #894)
Updating the imports & some linter issues in 3p-integrations/langchain/langgraph_rag_agent_local.ipynb --> tested E2E and can view the langchain traces for the last 2 cells:
https://smith.langchain.com/public/35e29916-70be-4146-8fc9-9787cb111ef5/r
https://smith.langchain.com/public/8ec9370f-29e2-46b4-842c-8ab949f8a3fa/r