From a4992ffadaf8a62c0a9f174de71b5f1a624a90cc Mon Sep 17 00:00:00 2001
From: Shaurya Rohatgi <shauryr@gmail.com>
Date: Tue, 12 Dec 2023 18:44:35 -0500
Subject: [PATCH] fix: to rag-semi-structured template (#14568)

**Description:**

Fixes to rag-semi-structured template.

- Added required libraries
- pdfminer was causing issues when installing with pip. pdfminer.six
works best
- Changed the pdf name for demo from llama2 to llava


<!-- Thank you for contributing to LangChain!

Replace this entire comment with:
  - **Description:** a description of the change,
  - **Issue:** the issue # it fixes (if applicable),
  - **Dependencies:** any dependencies required for this change,
- **Tag maintainer:** for a quicker response, tag the relevant
maintainer (see below),
- **Twitter handle:** we announce bigger features on Twitter. If your PR
gets announced, and you'd like a mention, we'll gladly shout you out!

Please make sure your PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.

See contribution guidelines for more information on how to write/run
tests, lint, etc:

https://github.com/langchain-ai/langchain/blob/master/.github/CONTRIBUTING.md

If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use. It lives in `docs/extras`
directory.

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.
 -->
---
 templates/rag-semi-structured/pyproject.toml              | 8 +++++++-
 .../rag-semi-structured/rag_semi_structured/chain.py      | 2 +-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/templates/rag-semi-structured/pyproject.toml b/templates/rag-semi-structured/pyproject.toml
index 78c6c74829..de10e6e57e 100644
--- a/templates/rag-semi-structured/pyproject.toml
+++ b/templates/rag-semi-structured/pyproject.toml
@@ -8,7 +8,7 @@ authors = [
 readme = "README.md"
 
 [tool.poetry.dependencies]
-python = ">=3.8.1,<4.0"
+python = ">=3.9,<3.11"
 langchain = ">=0.0.325"
 tiktoken = ">=0.5.1"
 chromadb = ">=0.4.14"
@@ -16,6 +16,12 @@ openai = "<2"
 unstructured = ">=0.10.19"
 pdf2image = ">=1.16.3"
 pdfminer = "^20191125"
+opencv-python = "^4.8.1.78"
+pandas = "^2.1.4"
+pytesseract = "^0.3.10"
+pdfminer-six = "^20221105"
+unstructured-pytesseract = "^0.3.12"
+unstructured-inference = "^0.7.18"
 
 [tool.poetry.group.dev.dependencies]
 langchain-cli = ">=0.0.15"
diff --git a/templates/rag-semi-structured/rag_semi_structured/chain.py b/templates/rag-semi-structured/rag_semi_structured/chain.py
index 488a753c88..8c74db3d07 100644
--- a/templates/rag-semi-structured/rag_semi_structured/chain.py
+++ b/templates/rag-semi-structured/rag_semi_structured/chain.py
@@ -16,7 +16,7 @@ from unstructured.partition.pdf import partition_pdf
 # Path to docs
 path = "docs"
 raw_pdf_elements = partition_pdf(
-    filename=path + "LLaMA2.pdf",
+    filename=path + "/LLaVA.pdf",
     # Unstructured first finds embedded image blocks
     extract_images_in_pdf=False,
     # Use layout model (YOLOX) to get bounding boxes (for tables) and find titles