github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #882] An updated langchain sample #26187

New Issue
Closed
opened 2026-04-22 02:14:59 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 02:14:59 -05:00
Owner
Copy Link

Originally created by @suoko on GitHub (Oct 23, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/882

Originally assigned to: @technovangelist on GitHub.

Below I wrote an extended sample for langchain which will import all PDF, TXT, DOCX and HTML files form /home/user/docs folder (it accepts only full paths).
You will need to pip install langchain pypdf chromadb tiktoken docx2txt unstructured

import sys
import os
from langchain.document_loaders import PyPDFLoader
from langchain.document_loaders import Docx2txtLoader
from langchain.document_loaders import TextLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.text_splitter import CharacterTextSplitter
from langchain.document_loaders import UnstructuredHTMLLoader

from langchain.llms import Ollama
ollama = Ollama(base_url='http://localhost:11434', 
model="llama2")
#model="starcoder")



#print(ollama("why is the sky blue"))


documents = []
for file in os.listdir("/home/user/docs"):
    if file.endswith(".pdf"):
        pdf_path = "/home/user/docs/" + file
        loader = PyPDFLoader(pdf_path)
        documents.extend(loader.load())
    elif file.endswith('.docx') or file.endswith('.doc'):
        doc_path = "/home/user/docs/" + file
        loader = Docx2txtLoader(doc_path)
        documents.extend(loader.load())
    elif file.endswith('.txt'):
        text_path = "/home/user/docs/" + file
        loader = TextLoader(text_path)
        documents.extend(loader.load())
    elif file.endswith('.html') or file.endswith('.htm'):
        text_path = "/home/user/docs/" + file
        loader = UnstructuredHTMLLoader(text_path)
        documents.extend(loader.load())


text_splitter = CharacterTextSplitter(chunk_size=1500, chunk_overlap=20)
all_splits = text_splitter.split_documents(documents)

from langchain.embeddings import GPT4AllEmbeddings
from langchain.vectorstores import Chroma
vectorstore = Chroma.from_documents(documents=all_splits, embedding=GPT4AllEmbeddings())

question="in case of problems with the inverter 3PH 10KTL-15KTL-V2, which steps do I have to follow ?"
docs = vectorstore.similarity_search(question)
len(docs)

from langchain.chains import RetrievalQA
qachain=RetrievalQA.from_chain_type(ollama, retriever=vectorstore.as_retriever())
print(qachain({"query": question}))
Originally created by @suoko on GitHub (Oct 23, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/882 Originally assigned to: @technovangelist on GitHub. Below I wrote an extended sample for langchain which will import all PDF, TXT, DOCX and HTML files form /home/user/docs folder (it accepts only full paths). You will need to `pip install langchain pypdf chromadb tiktoken docx2txt unstructured` ``` import sys import os from langchain.document_loaders import PyPDFLoader from langchain.document_loaders import Docx2txtLoader from langchain.document_loaders import TextLoader from langchain.text_splitter import RecursiveCharacterTextSplitter from langchain.text_splitter import CharacterTextSplitter from langchain.document_loaders import UnstructuredHTMLLoader from langchain.llms import Ollama ollama = Ollama(base_url='http://localhost:11434', model="llama2") #model="starcoder") #print(ollama("why is the sky blue")) documents = [] for file in os.listdir("/home/user/docs"): if file.endswith(".pdf"): pdf_path = "/home/user/docs/" + file loader = PyPDFLoader(pdf_path) documents.extend(loader.load()) elif file.endswith('.docx') or file.endswith('.doc'): doc_path = "/home/user/docs/" + file loader = Docx2txtLoader(doc_path) documents.extend(loader.load()) elif file.endswith('.txt'): text_path = "/home/user/docs/" + file loader = TextLoader(text_path) documents.extend(loader.load()) elif file.endswith('.html') or file.endswith('.htm'): text_path = "/home/user/docs/" + file loader = UnstructuredHTMLLoader(text_path) documents.extend(loader.load()) text_splitter = CharacterTextSplitter(chunk_size=1500, chunk_overlap=20) all_splits = text_splitter.split_documents(documents) from langchain.embeddings import GPT4AllEmbeddings from langchain.vectorstores import Chroma vectorstore = Chroma.from_documents(documents=all_splits, embedding=GPT4AllEmbeddings()) question="in case of problems with the inverter 3PH 10KTL-15KTL-V2, which steps do I have to follow ?" docs = vectorstore.similarity_search(question) len(docs) from langchain.chains import RetrievalQA qachain=RetrievalQA.from_chain_type(ollama, retriever=vectorstore.as_retriever()) print(qachain({"query": question})) ```
GiteaMirror commented 2026-04-22 02:15:00 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Oct 24, 2023):

Hi @suoko. Thanks for creating an issue! Would it be possible to create a PR that updates (preferable if one already exists) or creates a new example in examples/? I'll close this issue for now, but do feel free to create a PR and we can collaborate on it there

Thanks again!

<!-- gh-comment-id:1778199324 --> @jmorganca commented on GitHub (Oct 24, 2023): Hi @suoko. Thanks for creating an issue! Would it be possible to create a PR that updates (preferable if one already exists) or creates a new example in `examples/`? I'll close this issue for now, but do feel free to create a PR and we can collaborate on it there Thanks again!
GiteaMirror commented 2026-04-22 02:15:00 -05:00
Author
Owner
Copy Link

@mmenacer commented on GitHub (Nov 29, 2023):

Hi,

I'm doing the same here and instead of using a local model, i'm using Ollama Docker in an instance.
from langchain.llms import Ollama

ollama = Ollama(base_url='https://myollamalinkinhosted', 
model="llama2:70b")
)

I have this errors on print(qachain({"query": question}))

File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/base.py", line 312, in __call__
    raise e
  File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/base.py", line 306, in __call__
    self._call(inputs, run_manager=run_manager)
  File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/combine_documents/base.py", line 123, in _call
    output, extra_return_dict = self.combine_docs(
                                ^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/combine_documents/stuff.py", line 172, in combine_docs
    return self.llm_chain.predict(callbacks=callbacks, **inputs), {}
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/llm.py", line 293, in predict
    return self(kwargs, callbacks=callbacks)[self.output_key]
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/base.py", line 312, in __call__
    raise e
  File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/base.py", line 306, in __call__
    self._call(inputs, run_manager=run_manager)
  File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/llm.py", line 103, in _call
    response = self.generate([inputs], run_manager=run_manager)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/llm.py", line 115, in generate
    return self.llm.generate_prompt(
           ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.11/site-packages/langchain_core/language_models/llms.py", line 506, in generate_prompt
    return self.generate(prompt_strings, stop=stop, callbacks=callbacks, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.11/site-packages/langchain_core/language_models/llms.py", line 656, in generate
    output = self._generate_helper(
             ^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.11/site-packages/langchain_core/language_models/llms.py", line 543, in _generate_helper
    raise e
  File "/opt/homebrew/lib/python3.11/site-packages/langchain_core/language_models/llms.py", line 530, in _generate_helper
    self._generate(
  File "/opt/homebrew/lib/python3.11/site-packages/langchain/llms/ollama.py", line 241, in _generate
    final_chunk = super()._stream_with_aggregation(
                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.11/site-packages/langchain/llms/ollama.py", line 177, in _stream_with_aggregation
    for stream_resp in self._create_stream(prompt, stop, **kwargs):
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.11/site-packages/langchain/llms/ollama.py", line 161, in _create_stream
    optional_detail = response.json().get("error")
                      ^^^^^^^^^^^^^^^
  File "/opt/homebrew/lib/python3.11/site-packages/requests/models.py", line 975, in json
    raise RequestsJSONDecodeError(e.msg, e.doc, e.pos)
requests.exceptions.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
<!-- gh-comment-id:1831512857 --> @mmenacer commented on GitHub (Nov 29, 2023): Hi, I'm doing the same here and instead of using a local model, i'm using Ollama Docker in an instance. from langchain.llms import Ollama ``` ollama = Ollama(base_url='https://myollamalinkinhosted', model="llama2:70b") ) ``` I have this errors on print(qachain({"query": question})) ``` File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/base.py", line 312, in __call__ raise e File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/base.py", line 306, in __call__ self._call(inputs, run_manager=run_manager) File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/combine_documents/base.py", line 123, in _call output, extra_return_dict = self.combine_docs( ^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/combine_documents/stuff.py", line 172, in combine_docs return self.llm_chain.predict(callbacks=callbacks, **inputs), {} ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/llm.py", line 293, in predict return self(kwargs, callbacks=callbacks)[self.output_key] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/base.py", line 312, in __call__ raise e File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/base.py", line 306, in __call__ self._call(inputs, run_manager=run_manager) File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/llm.py", line 103, in _call response = self.generate([inputs], run_manager=run_manager) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/langchain/chains/llm.py", line 115, in generate return self.llm.generate_prompt( ^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/langchain_core/language_models/llms.py", line 506, in generate_prompt return self.generate(prompt_strings, stop=stop, callbacks=callbacks, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/langchain_core/language_models/llms.py", line 656, in generate output = self._generate_helper( ^^^^^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/langchain_core/language_models/llms.py", line 543, in _generate_helper raise e File "/opt/homebrew/lib/python3.11/site-packages/langchain_core/language_models/llms.py", line 530, in _generate_helper self._generate( File "/opt/homebrew/lib/python3.11/site-packages/langchain/llms/ollama.py", line 241, in _generate final_chunk = super()._stream_with_aggregation( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/langchain/llms/ollama.py", line 177, in _stream_with_aggregation for stream_resp in self._create_stream(prompt, stop, **kwargs): ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/langchain/llms/ollama.py", line 161, in _create_stream optional_detail = response.json().get("error") ^^^^^^^^^^^^^^^ File "/opt/homebrew/lib/python3.11/site-packages/requests/models.py", line 975, in json raise RequestsJSONDecodeError(e.msg, e.doc, e.pos) requests.exceptions.JSONDecodeError: Expecting value: line 1 column 1 (char 0) ```
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
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#26187
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?