run-llama/llama_cloud_services
1
0
Fork 0
mirror of https://github.com/run-llama/llama_cloud_services.git synced 2026-08-27 01:15:06 -04:00
Code Issues 352 Packages Projects Releases 10 Wiki Activity

Reading a scanned image in pdf , returning "NO_CONTENT_HERE" #79

New Issue
Open
opened 2026-02-16 00:16:49 -05:00 by yindo · 3 comments
yindo commented 2026-02-16 00:16:49 -05:00
Owner
Copy Link
Copy Source

Originally created by @swathithiyan on GitHub (Apr 8, 2024).

  1. I was using llama parse cloud to read the content from the scanned image in pdf. Llama parse was able to decode the text from the scanned image.
    2)But starting from today I see that , llama parse not able to decode the text, its returning "NO_CONTENT_HERE".

Below is the code:

import nest_asyncio
nest_asyncio.apply()
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_parse import LlamaParse
from langchain.text_splitter import SpacyTextSplitter
import os

class Document:
def init(self, page_content, metadata):
self.page_content = page_content
self.metadata = metadata

os.environ["OPENAI_API_KEY"] = ""
print("hello")
parser = LlamaParse(
api_key = '&****',# can also be set in your env as LLAMA_CLOUD_API_KEY
result_type="markdown" # "markdown" and "text" are available
)
file_extractor = {".pdf": parser}
documents = SimpleDirectoryReader("./data", file_extractor=file_extractor).load_data()
#documents = parser.load_data("./data/LLP_27oct2008.pdf")
content = ""
for doc in documents:
content = doc.text

content = content.split('---')
print(len(content))
page_no = 1
page_to_content_map = {}
for tex in content:
page_to_content_map[page_no] = tex
page_no +=1

documents = []
for page in page_to_content_map:
metadata = {'page':page-1,'source':'LLP_27oct2008.pdf'}
page_content = page_to_content_map[page]
doc = Document(page_content=page_content, metadata=metadata)
documents.append(doc)

text_splitter = SpacyTextSplitter(chunk_size=500)
docs = text_splitter.split_documents(documents)
print(docs)

The PDF file am parsing has only scanned images.

Originally created by @swathithiyan on GitHub (Apr 8, 2024). 1) I was using llama parse cloud to read the content from the scanned image in pdf. Llama parse was able to decode the text from the scanned image. 2)But starting from today I see that , llama parse not able to decode the text, its returning "NO_CONTENT_HERE". Below is the code: import nest_asyncio nest_asyncio.apply() from llama_index.core import VectorStoreIndex, SimpleDirectoryReader from llama_parse import LlamaParse from langchain.text_splitter import SpacyTextSplitter import os class Document: def __init__(self, page_content, metadata): self.page_content = page_content self.metadata = metadata os.environ["OPENAI_API_KEY"] = "********************" print("hello") parser = LlamaParse( api_key = '&************************',# can also be set in your env as LLAMA_CLOUD_API_KEY result_type="markdown" # "markdown" and "text" are available ) file_extractor = {".pdf": parser} documents = SimpleDirectoryReader("./data", file_extractor=file_extractor).load_data() #documents = parser.load_data("./data/LLP_27oct2008.pdf") content = "" for doc in documents: content = doc.text content = content.split('---') print(len(content)) page_no = 1 page_to_content_map = {} for tex in content: page_to_content_map[page_no] = tex page_no +=1 documents = [] for page in page_to_content_map: metadata = {'page':page-1,'source':'LLP_27oct2008.pdf'} page_content = page_to_content_map[page] doc = Document(page_content=page_content, metadata=metadata) documents.append(doc) text_splitter = SpacyTextSplitter(chunk_size=500) docs = text_splitter.split_documents(documents) print(docs) The PDF file am parsing has only scanned images.
yindo commented 2026-02-16 00:16:49 -05:00
Author
Owner
Copy Link
Copy Source

@0xthierry commented on GitHub (Jun 4, 2024):

I'm facing the same problem 👀

@0xthierry commented on GitHub (Jun 4, 2024): I'm facing the same problem 👀
yindo commented 2026-02-16 00:16:49 -05:00
Author
Owner
Copy Link
Copy Source

@drewdru commented on GitHub (Oct 4, 2024):

Here how I fix it:

documents = LlamaParse(
    result_type="markdown",
    parsing_instructions="The document has images retrieve text from it and describe other content on it"
).load_data(temp_file_path)

It seems that parsing_instructions is required for OCR.

@drewdru commented on GitHub (Oct 4, 2024): Here how I fix it: ```python documents = LlamaParse( result_type="markdown", parsing_instructions="The document has images retrieve text from it and describe other content on it" ).load_data(temp_file_path) ``` It seems that `parsing_instructions` is required for OCR.
yindo commented 2026-02-16 00:16:49 -05:00
Author
Owner
Copy Link
Copy Source

@lefterisloukas commented on GitHub (Mar 9, 2025):

same here

@lefterisloukas commented on GitHub (Mar 9, 2025): same here
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
LlamaCloud
LlamaExtract
LlamaParse
bug
client
complex layout
documentation
duplicate
enhancement
figure
font
header footer
help wanted
ocr
parser
pdf_debug
pdf_debug
pull-request
Mirrored from GitHub Pull Request
 python-lib
question
server_issue
server_issue
ui
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#79
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?