github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #2783] Connection Error with OllamaFunctions in Langchain #1679

New Issue
Closed
opened 2026-04-12 11:39:08 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-12 11:39:08 -05:00
Owner
Copy Link

Originally created by @quartermaine on GitHub (Feb 27, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2783

Description

I am attempting to replicate the Langchain tutorial in order to use OllamaFunctions for web extraction, as also demonstrated here in a Google Colab environment.

Code

[1] %%capture
     !pip install langchain_experimental


[2] from langchain_experimental.llms.ollama_functions import OllamaFunctions

     lm = OllamaFunctions(model="llama2:13b",
                      base_url="http://localhost:11434",
                      temperature=0)

[3] %%capture
     !pip install -q langchain-openai langchain playwright beautifulsoup4
     !playwright install


[4] import nest_asyncio
     nest_asyncio.apply()


[5] from langchain.chains import create_extraction_chain
     schema = {
          "properties": {
           "news_article_title": {"type": "string"},
           "news_article_summary": {"type": "string"},
              },
           "required": ["news_article_title", "news_article_summary"],
      }

     def extract(content: str, schema: dict):
      return create_extraction_chain(schema=schema, llm=llm, verbose=True).invoke(content)


[6] import pprint
     from langchain.text_splitter import RecursiveCharacterTextSplitter
     from langchain_community.document_loaders import AsyncChromiumLoader
     from langchain_community.document_transformers import BeautifulSoupTransformer

    def scrape_with_playwright(urls, schema):
         loader = AsyncChromiumLoader(urls)
         docs = loader.load()
         bs_transformer = BeautifulSoupTransformer()
         docs_transformed = bs_transformer.transform_documents(
                docs, tags_to_extract=["span"]
         )
         print("Extracting content with LLM")
         # Grab the first 1000 tokens of the site
         splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
                   chunk_size=1000,
                    chunk_overlap=0,
                     separators=["\n"]
          )
         splits = splitter.split_documents(docs_transformed)
         print("Number of splits:", len(splits))  # Add this debugging statement
         if splits:  # Check if splits list is not empty
                # Process the first split
                extracted_content = extract(schema=schema, content=splits[0].page_content) #  Line where error occurs
                pprint.pprint(extracted_content)
                return extracted_content
         else:
                 print("No splits found")  # Add this debugging statement
                 return None```

[7] urls = ["https://www.nytimes.com/"]
     extracted_content = scrape_with_playwright(urls, schema=schema) python

Error

But I am getting the following error:

ConnectionError: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/chat/ (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f7b19911300>: Failed to establish a new connection: [Errno 111] Connection refused'))
Originally created by @quartermaine on GitHub (Feb 27, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2783 ### Description I am attempting to replicate the [Langchain tutorial](https://python.langchain.com/docs/integrations/chat/ollama_functions) in order to use OllamaFunctions for web extraction, as also demonstrated [here](https://python.langchain.com/docs/use_cases/web_scraping#scraping-with-extraction) in a Google Colab environment. ### Code ```python [1] %%capture !pip install langchain_experimental [2] from langchain_experimental.llms.ollama_functions import OllamaFunctions lm = OllamaFunctions(model="llama2:13b", base_url="http://localhost:11434", temperature=0) [3] %%capture !pip install -q langchain-openai langchain playwright beautifulsoup4 !playwright install [4] import nest_asyncio nest_asyncio.apply() [5] from langchain.chains import create_extraction_chain schema = { "properties": { "news_article_title": {"type": "string"}, "news_article_summary": {"type": "string"}, }, "required": ["news_article_title", "news_article_summary"], } def extract(content: str, schema: dict): return create_extraction_chain(schema=schema, llm=llm, verbose=True).invoke(content) [6] import pprint from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain_community.document_loaders import AsyncChromiumLoader from langchain_community.document_transformers import BeautifulSoupTransformer def scrape_with_playwright(urls, schema): loader = AsyncChromiumLoader(urls) docs = loader.load() bs_transformer = BeautifulSoupTransformer() docs_transformed = bs_transformer.transform_documents( docs, tags_to_extract=["span"] ) print("Extracting content with LLM") # Grab the first 1000 tokens of the site splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder( chunk_size=1000, chunk_overlap=0, separators=["\n"] ) splits = splitter.split_documents(docs_transformed) print("Number of splits:", len(splits)) # Add this debugging statement if splits: # Check if splits list is not empty # Process the first split extracted_content = extract(schema=schema, content=splits[0].page_content) # Line where error occurs pprint.pprint(extracted_content) return extracted_content else: print("No splits found") # Add this debugging statement return None``` [7] urls = ["https://www.nytimes.com/"] extracted_content = scrape_with_playwright(urls, schema=schema) python ``` ### Error But I am getting the following error: ```python ConnectionError: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/chat/ (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f7b19911300>: Failed to establish a new connection: [Errno 111] Connection refused')) ```
GiteaMirror added the questionneeds more info labels 2026-04-12 11:39:08 -05:00
GiteaMirror commented 2026-04-12 11:39:11 -05:00
Author
Owner
Copy Link

@ecsricktorzynski commented on GitHub (Mar 9, 2024):

I am finding the same thing - I can use Ollama fine with Streamlit, but when I try to access Ollama through Langchain, I get this same exact error message.

<!-- gh-comment-id:1986766240 --> @ecsricktorzynski commented on GitHub (Mar 9, 2024): I am finding the same thing - I can use Ollama fine with Streamlit, but when I try to access Ollama through Langchain, I get this same exact error message.
GiteaMirror commented 2026-04-12 11:39:11 -05:00
Author
Owner
Copy Link

@jjmlovesgit commented on GitHub (Mar 22, 2024):

Friend -- a suggestion to try given limited view of the issue -- I have seen this when I did my Langchain -- make sure you start Ollama with "Ollama Serve" and you see it listening on the port...

C:\projects\DID\DID_LC_Ollama>ollama serve
time=2024-03-21T22:04:06.277-04:00 level=INFO source=images.go:806 msg="total blobs: 39"
time=2024-03-21T22:04:06.278-04:00 level=INFO source=images.go:813 msg="total unused blobs removed: 0"
time=2024-03-21T22:04:06.280-04:00 level=INFO source=routes.go:1110 msg="Listening on 127.0.0.1:11434 (version 0.1.29)"

<!-- gh-comment-id:2014910889 --> @jjmlovesgit commented on GitHub (Mar 22, 2024): Friend -- a suggestion to try given limited view of the issue -- I have seen this when I did my Langchain -- make sure you start Ollama with "Ollama Serve" and you see it listening on the port... C:\projects\DID\DID_LC_Ollama>ollama serve time=2024-03-21T22:04:06.277-04:00 level=INFO source=images.go:806 msg="total blobs: 39" time=2024-03-21T22:04:06.278-04:00 level=INFO source=images.go:813 msg="total unused blobs removed: 0" time=2024-03-21T22:04:06.280-04:00 level=INFO source=routes.go:1110 msg="Listening on 127.0.0.1:11434 (version 0.1.29)"
GiteaMirror commented 2026-04-12 11:39:12 -05:00
Author
Owner
Copy Link

@rdndsouza5 commented on GitHub (Apr 21, 2024):

Change the base url from localhost to whats there in ollama serve ie. llm = Ollama(model="llama2",base_url="http://127.0.0.1:11434")

<!-- gh-comment-id:2068179307 --> @rdndsouza5 commented on GitHub (Apr 21, 2024): Change the base url from localhost to whats there in ollama serve ie. llm = Ollama(model="llama2",base_url="http://127.0.0.1:11434")
GiteaMirror commented 2026-04-12 11:39:12 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Nov 6, 2024):

@quartermaine did you get it figured out?

<!-- gh-comment-id:2460531507 --> @dhiltgen commented on GitHub (Nov 6, 2024): @quartermaine did you get it figured out?
GiteaMirror commented 2026-04-12 11:39:13 -05:00
Author
Owner
Copy Link

@kikiyu commented on GitHub (Dec 12, 2024):

In my case,

model = OllamaLLM(model="llama3.1", base_url="http://localhost:11434")

solves the problem.

This is because Ollama is listening on IPV6 addresses, while 127.0.0.1 is an IPV4 address. I used netstat to check the address Ollama is listening on.

$ sudo netstat -tuln | grep 11434
tcp6       0      0 :::11434                :::*                    LISTEN
<!-- gh-comment-id:2537945641 --> @kikiyu commented on GitHub (Dec 12, 2024): In my case, ``` model = OllamaLLM(model="llama3.1", base_url="http://localhost:11434") ``` solves the problem. This is because Ollama is listening on IPV6 addresses, while 127.0.0.1 is an IPV4 address. I used netstat to check the address Ollama is listening on. ``` $ sudo netstat -tuln | grep 11434 tcp6 0 0 :::11434 :::* LISTEN ```
GiteaMirror commented 2026-04-12 11:39:14 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jan 12, 2025):

I'm going to go ahead and close the issue.

<!-- gh-comment-id:2585499961 --> @pdevine commented on GitHub (Jan 12, 2025): I'm going to go ahead and close the issue.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label needs more info question
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#1679
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?