Skip to content

Enable running using local Ollama #65

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
vivganes wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Enable running using local Ollama #65

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 15 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,13 @@ You can press the 'reverse' button to give input as Natural Language and get SQL
OPENAI_API_KEY=$YOUR_API_KEY
```

Optionally, if you would like to point to a custom OPENAI compatible API endpoint and model name, you can input it in the `.env` file. For example, if you would like to run locally using Ollama using `llama3.2` model, you could add

```bash
OPENAI_API_ENDPOINT_URL=http://localhost:11434
MODEL_ID=llama3.2
```

5. Start the development server:

```bash
Expand All @@ -74,12 +81,19 @@ You can press the 'reverse' button to give input as Natural Language and get SQL
git clone https://github.com/whoiskatrin/sql-translator.git
```

2. Input your OPENAI API key in the .env.production file, you can get your API key [here](https://beta.openai.com/account/api-keys):
2. Input your OPENAI API key in the `.env.production` file, you can get your API key [here](https://beta.openai.com/account/api-keys):

```bash
OPENAI_API_KEY=$YOUR_API_KEY
```

Optionally, if you would like to point to a custom OPENAI compatible API endpoint and model name, you can input it in the `.env.production` file. For example, if you would like to run locally using Ollama using `llama3.2` model, you could add

```bash
OPENAI_API_ENDPOINT_URL=http://host.docker.internal:11434
MODEL_ID=llama3.2
```

3. Start the development server:

```bash
Expand Down
1 change: 1 addition & 0 deletions pages/api/sql-to-human.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ export default async function handler(
try {
const outputText = await translateToHuman(
inputText,
process.env.OPENAI_API_ENDPOINT_URL || "https://api.openai.com",
process.env.OPENAI_API_KEY
);
res.status(200).json({ outputText });
Expand Down
1 change: 1 addition & 0 deletions pages/api/translate.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ export default async function handler(
try {
const result = await translateToSQL(
inputText,
process.env.OPENAI_API_ENDPOINT_URL || "https://api.openai.com",
process.env.OPENAI_API_KEY,
tableSchema
);
Expand Down
6 changes: 3 additions & 3 deletions src/translateToHuman.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,12 +1,12 @@
import fetch from "isomorphic-unfetch";

const translateToHuman = async (query, apiKey) => {
const translateToHuman = async (query, apiEndPointURL, apiKey) => {
// Validate inputs
if (!query || !apiKey) {
throw new Error("Missing query or API key.");
}

const response = await fetch("https://api.openai.com/v1/completions", {
const response = await fetch(`${apiEndPointURL}/v1/completions`, {
method: "POST",
headers: {
"Content-Type": "application/json",
Expand All @@ -18,7 +18,7 @@ const translateToHuman = async (query, apiKey) => {
max_tokens: 2048,
n: 1,
stop: "\\n",
model: "text-davinci-003",
model: process.env.MODEL_ID || "text-davinci-003",
frequency_penalty: 0.5,
presence_penalty: 0.5,
logprobs: 10,
Expand Down
6 changes: 3 additions & 3 deletions src/translateToSQL.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
import fetch from "isomorphic-unfetch";

const translateToSQL = async (query, apiKey, tableSchema = "") => {
const translateToSQL = async (query, apiEndPointURL, apiKey, tableSchema = "") => {

// Validate inputs
if (!query || !apiKey) {
Expand All @@ -10,7 +10,7 @@ const translateToSQL = async (query, apiKey, tableSchema = "") => {
const prompt = `Translate this natural language query into SQL without changing the case of the entries given by me:\n\n"${query}"\n\n${tableSchema ? `Use this table schema:\n\n${tableSchema}\n\n` : ''}SQL Query:`;

console.log(prompt);
const response = await fetch("https://api.openai.com/v1/completions", {
const response = await fetch(`${apiEndPointURL}/v1/completions`, {
method: "POST",
headers: {
"Content-Type": "application/json",
Expand All @@ -22,7 +22,7 @@ const translateToSQL = async (query, apiKey, tableSchema = "") => {
max_tokens: 2048,
n: 1,
stop: "\\n",
model: "gpt-3.5-turbo-instruct",
model: process.env.MODEL_ID || "gpt-3.5-turbo-instruct",
frequency_penalty: 0.5,
presence_penalty: 0.5,
logprobs: 10,
Expand Down