feat(langchain): add langchain application chat pdf

.dockerignore

@@ -59,6 +59,7 @@ fluent-bit/write-dummy-log-to-kafka/data
 grafana/hm-panel-plugin/.config
 graph-neural-network/dataset
 graph-neural-network/wandb
+hm-langchain/applications/*/data
 hm-keydb/dump.rdb
 # hm-keydb/modules
 hm-mlflow/experiments/*/data

.github/workflows/.static-type-check.yml

@@ -113,6 +113,7 @@ jobs:
           poetry run poe static-type-check-python -- --package=hm-airflow
           poetry run poe static-type-check-python -- --package=hm-kubeflow.pipelines.calculate
           poetry run poe static-type-check-python -- --package=hm-kubeflow.pipelines.classify-mnist
+          poetry run poe static-type-check-python -- --package=hm-langchain.applications.chat-pdf
           poetry run poe static-type-check-python -- --package=hm-locust
           poetry run poe static-type-check-python -- --package=hm-mlflow.experiments.classify-mnist
           poetry run poe static-type-check-python -- --package=hm-mlflow.experiments.predict-diabetes

.gitignore

@@ -59,6 +59,7 @@ fluent-bit/write-dummy-log-to-kafka/data
 # grafana/hm-panel-plugin/.config
 graph-neural-network/dataset
 graph-neural-network/wandb
+hm-langchain/applications/*/data
 hm-keydb/dump.rdb
 hm-keydb/modules
 hm-mlflow/experiments/*/data
@@ -120,4 +121,3 @@ web/coverage
 web/public/sitemap.xml
 web/storybook-static
 web/tmp
-

.markdownlint-cli2.jsonc

@@ -68,6 +68,7 @@
     "grafana/hm-panel-plugin/.config",
     "graph-neural-network/dataset",
     "graph-neural-network/wandb",
+    "hm-langchain/applications/*/data",
     "hm-keydb/dump.rdb",
     "hm-keydb/modules",
     "hm-mlflow/experiments/*/data",

.prettierignore

@@ -59,6 +59,7 @@ fluent-bit/write-dummy-log-to-kafka/data
 grafana/hm-panel-plugin/.config
 graph-neural-network/dataset
 graph-neural-network/wandb
+hm-langchain/applications/*/data
 hm-keydb/dump.rdb
 hm-keydb/modules
 hm-mlflow/experiments/*/data

.rubocop.yml

@@ -63,6 +63,7 @@ AllCops:
     - 'grafana/hm-panel-plugin/.config/**/*'
     - 'graph-neural-network/dataset/**/*'
     - 'graph-neural-network/wandb/**/*'
+    - 'hm-langchain/applications/*/data/**/*'
     - 'hm-keydb/dump.rdb'
     - 'hm-keydb/modules/**/*'
     - 'hm-mlflow/experiments/*/data/**/*'

.ruff.toml

@@ -61,6 +61,7 @@ exclude = [
   "grafana/hm-panel-plugin/.config",
   "graph-neural-network/dataset",
   "graph-neural-network/wandb",
+  "hm-langchain/applications/*/data",
   "hm-keydb/dump.rdb",
   "hm-keydb/modules",
   "hm-mlflow/experiments/*/data",

.solhintignore

@@ -59,6 +59,7 @@ fluent-bit/write-dummy-log-to-kafka/data
 grafana/hm-panel-plugin/.config
 graph-neural-network/dataset
 graph-neural-network/wandb
+hm-langchain/applications/*/data
 hm-keydb/dump.rdb
 hm-keydb/modules
 hm-mlflow/experiments/*/data

.stylelintignore

@@ -59,6 +59,7 @@ fluent-bit/write-dummy-log-to-kafka/data
 grafana/hm-panel-plugin/.config
 graph-neural-network/dataset
 graph-neural-network/wandb
+hm-langchain/applications/*/data
 hm-keydb/dump.rdb
 hm-keydb/modules
 hm-mlflow/experiments/*/data

.yamllint.yaml

@@ -64,6 +64,7 @@ ignore: |
   grafana/hm-panel-plugin/.config
   graph-neural-network/dataset
   graph-neural-network/wandb
+  hm-langchain/applications/*/data
   hm-keydb/dump.rdb
   hm-keydb/modules
   hm-mlflow/experiments/*/data

Makefile

@@ -242,6 +242,7 @@ static-type-check-python:
 	poetry run poe static-type-check-python -- --package=hm-airflow
 	poetry run poe static-type-check-python -- --package=hm-kubeflow.pipelines.calculate
 	poetry run poe static-type-check-python -- --package=hm-kubeflow.pipelines.classify-mnist
+	poetry run poe static-type-check-python -- --package=hm-langchain.applications.chat-pdf
 	poetry run poe static-type-check-python -- --package=hm-locust
 	poetry run poe static-type-check-python -- --package=hm-mlflow.experiments.classify-mnist
 	poetry run poe static-type-check-python -- --package=hm-mlflow.experiments.predict-diabetes

README.md

@@ -57,7 +57,7 @@ The diagram illustrates the repository's architecture, which is considered overl
 
 (The diagram here may take a moment to load. Please wait patiently.)
 
-![Architecture](https://github.com/hongbo-miao/hongbomiao.com/assets/3375461/6954cd1e-af89-4c91-83bb-c9f6409dd6ad)
+![Architecture](https://github.com/hongbo-miao/hongbomiao.com/assets/3375461/1992a3c5-3c30-491b-9c52-4f84135b4b32)
 
 ## 📦 Setup
 
@@ -157,6 +157,7 @@ make kubernetes-clean
 - **Tenacity** - General-purpose retrying library
 - **pytest** - Unit testing
 - **pydantic** - Data validation
+- **pypdf** - PDF library
 - **Poetry** - Python package management
   - **Poe the Poet** - Poetry task runner
 
@@ -213,6 +214,7 @@ make kubernetes-clean
 - **Prometheus** - Time-series database
 - **Apache Cassandra** - Distributed wide-column NoSQL database
 - **Qdrant** - Distributed vector database
+- **Chroma** - Distributed vector database
 - **Dgraph** - Distributed graph database
 - **Elasticsearch** - Distributed document-oriented search engine
   - **Kibana** - Elasticsearch visualization
@@ -270,6 +272,8 @@ make kubernetes-clean
 - **Metabase** - Data visualization
 - **PyTorch** - Machine learning framework
   - **PyTorch Geometric** - PyTorch geometric deep learning extension
+- **LangChang** - Large language model (LLM) framework
+- **GPT4All** - Large language models
 - **OGB** - Open graph benchmark
 - **Rasa** - Machine learning framework for automated text and voice-based conversations
 - **CML** - Continuous machine learning

hm-langchain/applications/chat-pdf/Makefile

@@ -0,0 +1,13 @@
+poetry-env-use:
+	poetry env use 3.11
+poetry-update-lock-file:
+	poetry lock --no-update
+poetry-install:
+	poetry install --no-root
+poetry-add:
+	poetry add xxx
+poetry-add-dev:
+	poetry add xxx --group=dev
+
+poetry-run-dev:
+	poetry run poe dev