|
1 | | -# Elastic Langchain Sample App |
2 | | - |
3 | | -This is a sample app that combines Elasticsearch, Langchain and a number of different LLMs to create a semantic search experience with ELSER. |
4 | | - |
5 | | - |
6 | | - |
7 | | -## 1. Download the Project |
8 | | - |
9 | | -Download the project from Github and extract the `workplace-search` folder. |
10 | | - |
11 | | -```bash |
12 | | -curl https://codeload.github.com/elastic/elasticsearch-labs/tar.gz/main | \ |
13 | | -tar -xz --strip=2 elasticsearch-labs-main/example-apps/workplace-search |
14 | | -``` |
15 | | - |
16 | | -## 2. Connecting to Elasticsearch |
17 | | - |
18 | | -This app requires the following environment variables to be set to connect to Elasticsearch |
19 | | - |
20 | | -```sh |
21 | | -export ELASTIC_CLOUD_ID=... |
22 | | -export ELASTIC_USERNAME=... |
23 | | -export ELASTIC_PASSWORD=... |
24 | | -``` |
25 | | - |
26 | | -Note: |
27 | | - |
28 | | -- If you don't have an Elastic Cloud deployment, sign up [here](https://cloud.elastic.co/registration?utm_source=github&utm_content=elasticsearch-labs-samples) for a free trial. |
29 | | - |
30 | | - 1. Go to the [Create deployment](https://cloud.elastic.co/deployments/create) page |
31 | | - 2. Select **Create deployment** and follow the instructions |
32 | | - |
33 | | -### Change the Elasticsearch index and chat_history index |
34 | | - |
35 | | -By default, the app will use the `workplace-app-docs` index and the chat history index will be `workplace-app-docs-chat-history`. If you want to change these, you can set the following environment variables: |
36 | | - |
37 | | -```sh |
38 | | -ES_INDEX=workplace-app-docs |
39 | | -ES_INDEX_CHAT_HISTORY=workplace-app-docs-chat-history |
40 | | -``` |
41 | | - |
42 | | -## 3. Connecting to LLM |
43 | | - |
44 | | -We support three LLM providers: Azure, OpenAI and Bedrock. |
45 | | - |
46 | | -To use one of them, you need to set the `LLM_TYPE` environment variable: |
47 | | - |
48 | | -```sh |
49 | | -export LLM_TYPE=azure |
50 | | -``` |
51 | | - |
52 | | -### OpenAI |
53 | | - |
54 | | -To use OpenAI LLM, you will need to provide the OpenAI key via `OPENAI_API_KEY` environment variable: |
55 | | - |
56 | | -```sh |
57 | | -export LLM_TYPE=openai |
58 | | -export OPENAI_API_KEY=... |
59 | | -``` |
60 | | - |
61 | | -You can get your OpenAI key from the [OpenAI dashboard](https://platform.openai.com/account/api-keys). |
62 | | - |
63 | | -### Azure OpenAI |
64 | | - |
65 | | -If you are using Azure LLM, you will need to set the following environment variables: |
66 | | - |
67 | | -```sh |
68 | | -export LLM_TYPE=azure |
69 | | -export OPENAI_VERSION=... # e.g. 2023-05-15 |
70 | | -export OPENAI_BASE_URL=... |
71 | | -export OPENAI_API_KEY=... |
72 | | -export OPENAI_ENGINE=... # deployment name in Azure |
73 | | -``` |
74 | | - |
75 | | -### Bedrock LLM |
76 | | - |
77 | | -To use Bedrock LLM you need to set the following environment variables in order to AWS. |
78 | | - |
79 | | -```sh |
80 | | -export LLM_TYPE=bedrock |
81 | | -export AWS_ACCESS_KEY=... |
82 | | -export AWS_SECRET_KEY=... |
83 | | -export AWS_REGION=... # e.g. us-east-1 |
84 | | -export AWS_MODEL_ID=... # Default is anthropic.claude-v2 |
85 | | -``` |
86 | | - |
87 | | -#### AWS Config |
88 | | - |
89 | | -Optionally, you can connect to AWS via the config file in `~/.aws/config` described here: |
90 | | -https://boto3.amazonaws.com/v1/documentation/api/latest/guide/credentials.html#configuring-credentials |
91 | | - |
92 | | -``` |
93 | | -[default] |
94 | | -aws_access_key_id=... |
95 | | -aws_secret_access_key=... |
96 | | -region=... |
97 | | -``` |
98 | | - |
99 | | -### Vertex AI |
100 | | - |
101 | | -To use Vertex AI you need to set the following environment variables. More infos [here](https://python.langchain.com/docs/integrations/llms/google_vertex_ai_palm). |
102 | | - |
103 | | -```sh |
104 | | - export LLM_TYPE=vertex |
105 | | - export VERTEX_PROJECT_ID=<gcp-project-id> |
106 | | - export VERTEX_REGION=<gcp-region> # Default is us-central1 |
107 | | - export GOOGLE_APPLICATION_CREDENTIALS=<path-json-service-account> |
108 | | -``` |
109 | | - |
110 | | -## 3. Ingest Data |
111 | | - |
112 | | -You can index the sample data from the provided .json files in the `data` folder: |
113 | | - |
114 | | -```sh |
115 | | -python data/index-data.py |
116 | | -``` |
117 | | - |
118 | | -by default, this will index the data into the `workplace-app-docs` index. You can change this by setting the `ES_INDEX` environment variable. |
119 | | - |
120 | | -### Indexing your own data |
121 | | - |
122 | | -`index-data.py` is a simple script that uses Langchain to index data into Elasticsearch, using the `JSONLoader` and `CharacterTextSplitter` to split the large documents into passages. Modify this script to index your own data. |
123 | | - |
124 | | -Langchain offers many different ways to index data, if you cant just load it via JSONLoader. See the [Langchain documentation](https://python.langchain.com/docs/modules/data_connection/document_loaders) |
125 | | - |
126 | | -Remember to keep the `ES_INDEX` environment variable set to the index you want to index into and to query from. |
127 | | - |
128 | | -## Running the App |
129 | | - |
130 | | -Once you have indexed data into the Elasticsearch index, there are two ways to run the app: via Docker or locally. Docker is advised for testing & production use. Locally is advised for development. |
131 | | - |
132 | | -### Through Docker |
133 | | - |
134 | | -Build the Docker image and run it with the following environment variables. |
135 | | - |
136 | | -```sh |
137 | | -docker build -f Dockerfile -t workplace-search-app . |
138 | | -``` |
139 | | - |
140 | | -Then run it with the following environment variables. In the example below, we are using OpenAI LLM. |
141 | | - |
142 | | -If you're using one of the other LLMs, you will need to set the appropriate environment variables via `-e` flag. |
143 | | - |
144 | | -```sh |
145 | | -docker run -p 4000:4000 \ |
146 | | - -e "ELASTIC_CLOUD_ID=<cloud_id>" \ |
147 | | - -e "ELASTIC_USERNAME=elastic" \ |
148 | | - -e "ELASTIC_PASSWORD=<password>" \ |
149 | | - -e "LLM_TYPE=openai" \ |
150 | | - -e "OPENAI_API_KEY=<openai_key>" \ |
151 | | - -d workplace-search-app |
152 | | -``` |
153 | | - |
154 | | -### Locally (for development) |
155 | | - |
156 | | -With the environment variables set, you can run the following commands to start the server and frontend. |
157 | | - |
158 | | -#### Pre-requisites |
159 | | - |
160 | | -- Python 3.8+ |
161 | | -- Node 14+ |
162 | | - |
163 | | -#### Install the dependencies |
164 | | - |
165 | | -For Python we recommend using a virtual environment. |
166 | | - |
167 | | -_ℹ️ Here's a good [primer](https://realpython.com/python-virtual-environments-a-primer) on virtual environments from Real Python._ |
168 | | - |
169 | | -```sh |
170 | | -# Create a virtual environment |
171 | | -python -m venv .venv |
172 | | - |
173 | | -# Activate the virtual environment |
174 | | -source .venv/bin/activate |
175 | | -``` |
176 | | - |
177 | | -```sh |
178 | | -# Install Python dependencies |
179 | | -pip install -r requirements.txt |
180 | | - |
181 | | -# Install Node dependencies |
182 | | -cd frontend && yarn |
183 | | -``` |
184 | | - |
185 | | -#### Run API and frontend |
186 | | - |
187 | | -```sh |
188 | | -# Launch API app |
189 | | -python api/app.py |
190 | | - |
191 | | -# In a separate terminal launch frontend app |
192 | | -cd frontend && yarn start |
193 | | -``` |
194 | | - |
195 | | -You can now access the frontend at http://localhost:3000. Changes are automatically reloaded. |
| 1 | +This app has now moved to [https://github.com/elastic/elasticsearch-labs/tree/main/example-apps/chatbot-rag-app] |
0 commit comments