Merge pull request #28 from FullStackWithLawrence/next

Langchain integration

Author: lpm0073

.mergify.yml

@@ -1,3 +1,6 @@
+# see:
+#  - https://github.com/FullStackWithLawrence/aws-openai/settings/installations
+#  - https://docs.mergify.com/getting-started/
 pull_request_rules:
   - name: automatic approve dependabot pull requests
     conditions:

.pre-commit-config.yaml

@@ -3,11 +3,11 @@ default_language_version:
   python: python3.11
 repos:
   - repo: https://github.com/psf/black
-    rev: 23.7.0
+    rev: 23.10.1
     hooks:
     - id: black
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0
+    rev: v4.5.0
     hooks:
       # See https://pre-commit.com/hooks.html for more hooks
       #- id: check-added-large-files
@@ -35,3 +35,9 @@ repos:
     #  - id: shellcheck
     #  - id: yapf
     #  - id: markdown-link-check
+  - repo: https://github.com/alessandrojcm/commitlint-pre-commit-hook
+    rev: v9.5.0
+    hooks:
+      - id: commitlint
+        stages: [commit-msg]
+        additional_dependencies: ['@commitlint/config-angular']

CHANGELOG.md

@@ -1,4 +1,12 @@
-# [0.4.0](https://github.com/FullStackWithLawrence/aws-openai/compare/v0.3.1...v0.4.0) (2023-11-03)
+# CHANGE LOG
+
+All notable changes to this project will be documented in this file.
+
+The format is based on [Keep a Changelog](http://keepachangelog.com/)
+and this project adheres to [Semantic Versioning](http://semver.org/).
+
+
+## [0.4.0](https://github.com/FullStackWithLawrence/aws-openai/compare/v0.3.1...v0.4.0) (2023-11-03)
 
 
 ### Bug Fixes
@@ -22,13 +30,6 @@
 
 * revert to secrets.PAT ([7342489](https://github.com/FullStackWithLawrence/aws-openai/commit/7342489ef7b7537419cc12732c1739a9fc3b42a8))
 
-# CHANGE LOG
-
-All notable changes to this project will be documented in this file.
-
-The format is based on [Keep a Changelog](http://keepachangelog.com/)
-and this project adheres to [Semantic Versioning](http://semver.org/).
-
 ## [0.3.0] (2023-11-01)
 
 The YouTube video for this release: [AWS Lamba Layers: When and How to use them](https://youtu.be/5Jf34t_UlZA)

README.md

@@ -9,7 +9,6 @@ A [React](https://react.dev/) + [AWS Serverless](https://aws.amazon.com/serverle
 
 ![React front end](https://github.com/FullStackWithLawrence/aws-openai/blob/main/doc/front-end.png)
 
-
 **IMPORTANT DISCLAIMER: AWS' Lambda service has a hard 29-second timeout. OpenAI API calls often take longer than this, in which case the AWS API Gateway endpoint will return a 504 "Gateway timeout error" response to the React client. This happens frequently with apps created using chatgpt-4. Each of the 30 OpenAI API example applications are nonetheless implemented exactly as they are specified in the official documentation.**
 
 ## ReactJS chat application
@@ -18,7 +17,7 @@ Complete documentation is located [here](./client/).
 
 React app that leverages [Vite.js](https://github.com/FullStackWithLawrence/aws-openai), [@chatscope/chat-ui-kit-react](https://www.npmjs.com/package/@chatscope/chat-ui-kit-react), and [react-pro-sidebar](https://www.npmjs.com/package/react-pro-sidebar).
 
-### Key features
+### Webapp Key features
 
 - robust, highly customizable chat features
 - A component model for implementing your own highly personalized OpenAI apps
@@ -36,7 +35,7 @@ Complete documentation is located [here](./api/).
 
 A REST API implementing each of the [30 example applications](https://platform.openai.com/examples) from the official [OpenAI API Documentation](https://platform.openai.com/docs/api-reference/making-requests?lang=python) using a modularized Terraform approach. Leverages OpenAI's suite of AI models, including [GPT-3.5](https://platform.openai.com/docs/models/gpt-3-5), [GPT-4](https://platform.openai.com/docs/models/gpt-4), [DALL·E](https://platform.openai.com/docs/models/dall-e), [Whisper](https://platform.openai.com/docs/models/whisper), [Embeddings](https://platform.openai.com/docs/models/embeddings), and [Moderation](https://platform.openai.com/docs/models/moderation).
 
-### Key features
+### API Key features
 
 - Built on the [OpenAI API Python Library](https://pypi.org/project/openai/)
 - Customizable. [Modularized endpoints](./terraform/apigateway_endpoints.tf) that only take a few lines of code each.
@@ -66,6 +65,27 @@ A REST API implementing each of the [30 example applications](https://platform.o
 
 Detailed documentation for each endpoint is available here: [Documentation](./doc/examples/)
 
+## Examples of Code Management Best Practices
+
+This repo is referenced by multiple YouTube videos, including various tutorials about good coding practices and good code management. Of note:
+
+- [python-dotenv](https://pypi.org/project/python-dotenv/) for storing sensitive data for local development
+- [.gitignore](./.gitignore)  ensures that no sensitive nor useless data accidentally gets pushed to GitHub.
+- [tox.ini](./tox.ini) file for configuring behaviors of Python testing tools
+- [GitHub Actions](https://github.com/features/actions) automates unit testing, semantic release rule checking, and dependabot actions.
+- [GitHub Secrets](https://github.com/FullStackWithLawrence/aws-openai/settings/secrets/actions) to provide sensitive data to Github Actions workflows
+- [GitHub Issues](https://github.com/features/issues)
+- [Makefile](./Makefile) automates procedures like init, build, test, release and linting for Python, ReactJS and Terraform.
+- [pre-commit](https://pre-commit.com/) automatically enforces a multitude of code quality, coding style and security policies.
+- [Dependabot](https://github.com/dependabot) automatically updates the version pins of code library dependencies for Python, ReactJS and Terraform.
+- [Unit Tests](https://docs.pytest.org/) are automated and can be invoked
+  - manually from the command line
+  - manually from GitHub Actions
+  - automatically by Dependabot.
+- [Mergify](https://mergify.com/) automates processing of bot-created pull requests
+- [Semantic Release](https://github.com/semantic-release/semantic-release) automates version releases as well as maintains the [CHANGELOG](./CHANGELOG.md) for the repo.
+- [Change Log](http://keepachangelog.com/)
+
 ## Support
 
 To get community support, go to the official [Issues Page](https://github.com/FullStackWithLawrence/aws-openai/issues) for this project.

api/README.md

@@ -122,7 +122,15 @@ Example valid request body:
         {
             "role": "user",
             "content": "what is quantum computing?"
-        }
+        },
+        {
+          "role": "assistant",
+          "content": "Quantum computing involves teeny tiny itsy bitsy atomic stuff"
+        },
+        {
+            "role": "user",
+            "content": "What??? I don't understand. Please provide a better explanation."
+        },
     ]
 }
 ```

api/terraform/apigateway_endpoints.tf

@@ -350,6 +350,8 @@ module "default_vr_fitness" {
 ###############################################################################
 # 15. see https://platform.openai.com/examples/default-marv-sarcastic-chat
 #     Marv is a factual chatbot that is also sarcastic.
+#
+#     Note: migrated to Langchain in v0.5.0
 ###############################################################################
 module "default_marv_sarcastic_chat" {
   source    = "./endpoint"
@@ -366,8 +368,8 @@ module "default_marv_sarcastic_chat" {
   aws_region                                 = var.aws_region
   aws_api_gateway_rest_api_parent_id         = aws_api_gateway_resource.examples.id
   aws_api_gateway_rest_api_id                = aws_api_gateway_rest_api.openai.id
-  aws_lambda_function_openai_text_invoke_arn = aws_lambda_function.lambda_openai.invoke_arn
-  aws_lambda_function_openai_text            = aws_lambda_function.lambda_openai.function_name
+  aws_lambda_function_openai_text_invoke_arn = aws_lambda_function.lambda_langchain.invoke_arn
+  aws_lambda_function_openai_text            = aws_lambda_function.lambda_langchain.function_name
   aws_iam_role_arn                           = aws_iam_role.apigateway.arn
 }
 

api/terraform/lambda_langchain.tf

@@ -79,6 +79,7 @@ resource "aws_lambda_function" "lambda_langchain" {
   memory_size      = var.lambda_memory_size
   timeout          = var.lambda_timeout
   handler          = "lambda_handler.handler"
+  architectures    = var.compatible_architectures
   filename         = data.archive_file.lambda_langchain.output_path
   source_code_hash = data.archive_file.lambda_langchain.output_base64sha256
   layers           = [aws_lambda_layer_version.genai.arn]

api/terraform/lambda_layer.tf

@@ -11,9 +11,9 @@ locals {
   layer_slug              = "genai"
   layer_name              = "layer_${local.layer_slug}"
   layer_source_directory  = "${path.module}/python/${local.layer_name}"
-  layer_packaging_script  = "${local.layer_source_directory}/create_pkg.sh"
+  layer_packaging_script  = "${local.layer_source_directory}/create_container.sh"
   layer_package_folder    = local.layer_slug
-  layer_dist_package_name = "${local.layer_name}_dst"
+  layer_dist_package_name = "${local.layer_name}_dst.zip"
 }
 
 ###############################################################################
@@ -25,11 +25,14 @@ resource "null_resource" "package_layer_genai" {
     redeployment = sha1(jsonencode([
       "${path.module}/lambda_layer.tf",
       file("${local.layer_packaging_script}"),
+      file("${local.layer_source_directory}/Dockerfile"),
+      file("${local.layer_source_directory}/create_container.sh"),
       file("${local.layer_source_directory}/requirements.txt"),
       file("${local.layer_source_directory}/openai_utils/__init__.py"),
       file("${local.layer_source_directory}/openai_utils/const.py"),
       file("${local.layer_source_directory}/openai_utils/utils.py"),
       file("${local.layer_source_directory}/openai_utils/validators.py"),
+      fileexists("${local.layer_source_directory}/${local.layer_dist_package_name}") ? filebase64("${local.layer_source_directory}/${local.layer_dist_package_name}") : null
     ]))
   }
 
@@ -38,28 +41,23 @@ resource "null_resource" "package_layer_genai" {
     command     = local.layer_packaging_script
 
     environment = {
-      LAYER_NAME       = local.layer_slug
       SOURCE_CODE_PATH = local.layer_source_directory
-      PACKAGE_FOLDER   = "python"
       RUNTIME          = var.lambda_python_runtime
+      CONTAINER_NAME   = local.layer_name
+      PACKAGE_NAME     = local.layer_dist_package_name
     }
   }
 }
 
-data "archive_file" "layer_genai" {
-  # see https://registry.terraform.io/providers/hashicorp/archive/latest/docs/data-sources/file
-  source_dir  = "${local.layer_source_directory}/archive/"
-  output_path = "${local.layer_source_directory}/${local.layer_dist_package_name}.zip"
-  type        = "zip"
-  depends_on  = [null_resource.package_layer_genai]
-}
-
 resource "aws_lambda_layer_version" "genai" {
-  filename                 = data.archive_file.layer_genai.output_path
-  source_code_hash         = fileexists(data.archive_file.layer_genai.output_path) ? filebase64sha256(data.archive_file.layer_genai.output_path) : null
+  filename                 = "${local.layer_source_directory}/${local.layer_dist_package_name}"
+  source_code_hash         = fileexists("${local.layer_source_directory}/${local.layer_dist_package_name}") ? filebase64sha256("${local.layer_source_directory}/${local.layer_dist_package_name}") : null
   layer_name               = local.layer_slug
-  compatible_architectures = ["x86_64", "arm64"]
+  compatible_architectures = var.compatible_architectures
   compatible_runtimes      = [var.lambda_python_runtime]
+  lifecycle {
+    create_before_destroy = true
+  }
   depends_on = [
     null_resource.package_layer_genai
   ]

api/terraform/lambda_openai_v2.tf

@@ -79,6 +79,7 @@ resource "aws_lambda_function" "lambda_openai_v2_" {
   memory_size      = var.lambda_memory_size
   timeout          = var.lambda_timeout
   handler          = "lambda_handler.handler"
+  architectures    = var.compatible_architectures
   filename         = data.archive_file.lambda_openai_v2_.output_path
   source_code_hash = data.archive_file.lambda_openai_v2_.output_base64sha256
   layers           = [aws_lambda_layer_version.genai.arn]