Feat/chroma

.env.example

@@ -1,6 +1,3 @@
 OPENAI_API_KEY=
 
-# Update these with your Supabase details from your project settings > API and dashboard settings
-PINECONE_API_KEY=
-PINECONE_ENVIRONMENT=
-PINECONE_INDEX_NAME=
+COLLECTION_NAME=

README.md

@@ -1,12 +1,8 @@
-# GPT-4 & LangChain - Create a ChatGPT Chatbot for Your PDF Files
+# GPT-4, LangChain & Chroma - Create a ChatGPT Chatbot for Your PDF Files
 
 Use the new GPT-4 api to build a chatGPT chatbot for multiple Large PDF files.
 
-Tech stack used includes LangChain, Pinecone, Typescript, Openai, and Next.js. LangChain is a framework that makes it easier to build scalable AI/LLM apps and chatbots. Pinecone is a vectorstore for storing embeddings and your PDF in text to later retrieve similar docs.
-
-[Tutorial video](https://www.youtube.com/watch?v=ih9PBGVVOO4)
-
-[Join the discord if you have questions](https://discord.gg/E4Mc77qwjm)
+Tech stack used includes LangChain, Chroma, Typescript, Openai, and Next.js. LangChain is a framework that makes it easier to build scalable AI/LLM apps and chatbots. Chroma is a vectorstore for storing embeddings and your PDF in text to later retrieve similar docs.
 
 The visual guide of this repo and tutorial is in the `visual guide` folder.
 
@@ -16,14 +12,15 @@ Prelude: Please make sure you have already downloaded node on your system and th
 
 ## Development
 
-1. Clone the repo or download the ZIP
+1. Install [Docker Desktop](https://www.docker.com/products/docker-desktop/) for your platform.
+
+2. Clone the repo or download the ZIP
 
 ```
 git clone [github https url]
 ```
 
-
-2. Install packages
+3. Install packages
 
 First run `npm install yarn -g` to install yarn globally (if you haven't already).
 
@@ -32,30 +29,32 @@ Then run:
 ```
 yarn install
 ```
+
 After installation, you should now see a `node_modules` folder.
 
-3. Set up your `.env` file
+4. Set up your `.env` file
 
 - Copy `.env.example` into `.env`
   Your `.env` file should look like this:
 
 ```
 OPENAI_API_KEY=
-
-PINECONE_API_KEY=
-PINECONE_ENVIRONMENT=
-
-PINECONE_INDEX_NAME=
+COLLECTION_NAME=
 
 ```
 
 - Visit [openai](https://help.openai.com/en/articles/4936850-where-do-i-find-my-secret-api-key) to retrieve API keys and insert into your `.env` file.
-- Visit [pinecone](https://pinecone.io/) to create and retrieve your API keys, and also retrieve your environment and index name from the dashboard.
-
-4. In the `config` folder, replace the `PINECONE_NAME_SPACE` with a `namespace` where you'd like to store your embeddings on Pinecone when you run `npm run ingest`. This namespace will later be used for queries and retrieval.
+- Choose a collection name where you'd like to store your embeddings in Chroma. This collection will later be used for queries and retrieval.
+- [Chroma details](https://docs.trychroma.com/getting-started)
 
 5. In `utils/makechain.ts` chain change the `QA_PROMPT` for your own usecase. Change `modelName` in `new OpenAI` to `gpt-4`, if you have access to `gpt-4` api. Please verify outside this repo that you have access to `gpt-4` api, otherwise the application will not work.
 
+6. In a new terminal window, run Chroma in the Docker container:
+
+```
+docker run -p 8000:8000 ghcr.io/chroma-core/chroma:0.3.21
+```
+
 ## Convert your PDF files to embeddings
 
 **This repo can load multiple PDF files**
@@ -64,11 +63,9 @@ PINECONE_INDEX_NAME=
 
 2. Run the script `npm run ingest` to 'ingest' and embed your docs. If you run into errors troubleshoot below.
 
-3. Check Pinecone dashboard to verify your namespace and vectors have been added.
-
 ## Run the app
 
-Once you've verified that the embeddings and content have been successfully added to your Pinecone, you can run the app `npm run dev` to launch the local dev environment, and then type a question in the chat interface.
+Once you've verified that the embeddings and content have been successfully added to Chroma db, you can run the app `npm run dev` to launch the local dev environment, and then type a question in the chat interface.
 
 ## Troubleshooting
 
@@ -79,21 +76,8 @@ In general, keep an eye out in the `issues` and `discussions` section of this re
 - Make sure you're running the latest Node version. Run `node -v`
 - Try a different PDF or convert your PDF to text first. It's possible your PDF is corrupted, scanned, or requires OCR to convert to text.
 - `Console.log` the `env` variables and make sure they are exposed.
-- Make sure you're using the same versions of LangChain and Pinecone as this repo.
 - Check that you've created an `.env` file that contains your valid (and working) API keys, environment and index name.
 - If you change `modelName` in `OpenAI`, make sure you have access to the api for the appropriate model.
 - Make sure you have enough OpenAI credits and a valid card on your billings account.
 - Check that you don't have multiple OPENAPI keys in your global environment. If you do, the local `env` file from the project will be overwritten by systems `env` variable.
 - Try to hard code your API keys into the `process.env` variables if there are still issues.
-
-**Pinecone errors**
-
-- Make sure your pinecone dashboard `environment` and `index` matches the one in the `pinecone.ts` and `.env` files.
-- Check that you've set the vector dimensions to `1536`.
-- Make sure your pinecone namespace is in lowercase.
-- Pinecone indexes of users on the Starter(free) plan are deleted after 7 days of inactivity. To prevent this, send an API request to Pinecone to reset the counter before 7 days.
-- Retry from scratch with a new Pinecone project, index, and cloned repo.
-
-## Credit
-
-Frontend of this repo is inspired by [langchain-chat-nextjs](https://github.com/zahidkhawaja/langchain-chat-nextjs)

config/chroma.ts

@@ -0,0 +1,7 @@
+if (!process.env.COLLECTION_NAME) {
+  throw new Error('Missing collection name name in .env file');
+}
+
+const COLLECTION_NAME = process.env.COLLECTION_NAME ?? '';
+
+export { COLLECTION_NAME };

package.json

@@ -1,6 +1,6 @@
 {
   "name": "gpt4-langchain-pdf-chatbot",
-  "version": "0.1.0",
+  "version": "0.2.0",
   "private": true,
   "license": "MIT",
   "author": "Mayooear<twitter:@mayowaoshin>",
@@ -18,6 +18,7 @@
     "@microsoft/fetch-event-source": "^2.0.1",
     "@pinecone-database/pinecone": "0.0.12",
     "@radix-ui/react-accordion": "^1.1.1",
+    "chromadb": "1.4.1",
     "clsx": "^1.2.1",
     "dotenv": "^16.0.3",
     "langchain": "0.0.55",
@@ -49,7 +50,7 @@
   "keywords": [
     "starter",
     "gpt4",
-    "pinecone",
+    "chroma",
     "typescript",
     "nextjs",
     "langchain",

pages/api/chat.ts

@@ -1,9 +1,8 @@
 import type { NextApiRequest, NextApiResponse } from 'next';
 import { OpenAIEmbeddings } from 'langchain/embeddings/openai';
-import { PineconeStore } from 'langchain/vectorstores/pinecone';
 import { makeChain } from '@/utils/makechain';
-import { pinecone } from '@/utils/pinecone-client';
-import { PINECONE_INDEX_NAME, PINECONE_NAME_SPACE } from '@/config/pinecone';
+import { COLLECTION_NAME } from '@/config/chroma';
+import { Chroma } from 'langchain/vectorstores/chroma';
 
 export default async function handler(
   req: NextApiRequest,
@@ -26,15 +25,11 @@ export default async function handler(
   const sanitizedQuestion = question.trim().replaceAll('\n', ' ');
 
   try {
-    const index = pinecone.Index(PINECONE_INDEX_NAME);
-
     /* create vectorstore*/
-    const vectorStore = await PineconeStore.fromExistingIndex(
+    const vectorStore = await Chroma.fromExistingCollection(
       new OpenAIEmbeddings({}),
       {
-        pineconeIndex: index,
-        textKey: 'text',
-        namespace: PINECONE_NAME_SPACE, //namespace comes from your config folder
+        collectionName: COLLECTION_NAME,
       },
     );
 

pages/index.tsx

@@ -262,7 +262,8 @@ export default function Home() {
         </div>
         <footer className="m-auto p-4">
           <a href="https://twitter.com/mayowaoshin">
-            Powered by LangChainAI. Demo built by Mayo (Twitter: @mayowaoshin).
+            Powered by LangChainAI and Chroma. Demo built by Mayo (Twitter:
+            @mayowaoshin).
           </a>
         </footer>
       </Layout>

scripts/ingest-data.ts

@@ -1,10 +1,9 @@
 import { RecursiveCharacterTextSplitter } from 'langchain/text_splitter';
 import { OpenAIEmbeddings } from 'langchain/embeddings/openai';
-import { PineconeStore } from 'langchain/vectorstores/pinecone';
-import { pinecone } from '@/utils/pinecone-client';
 import { CustomPDFLoader } from '@/utils/customPDFLoader';
-import { PINECONE_INDEX_NAME, PINECONE_NAME_SPACE } from '@/config/pinecone';
 import { DirectoryLoader } from 'langchain/document_loaders/fs/directory';
+import { Chroma } from 'langchain/vectorstores/chroma';
+import { COLLECTION_NAME } from '@/config/chroma';
 
 /* Name of directory to retrieve your files from */
 const filePath = 'docs';
@@ -31,14 +30,18 @@ export const run = async () => {
     console.log('creating vector store...');
     /*create and store the embeddings in the vectorStore*/
     const embeddings = new OpenAIEmbeddings();
-    const index = pinecone.Index(PINECONE_INDEX_NAME); //change to your own index name
 
-    //embed the PDF documents
-    await PineconeStore.fromDocuments(docs, embeddings, {
-      pineconeIndex: index,
-      namespace: PINECONE_NAME_SPACE,
-      textKey: 'text',
-    });
+    let chroma = new Chroma(embeddings, { collectionName: COLLECTION_NAME });
+    await chroma.index?.reset();
+
+    // Ingest documents in batches of 100
+
+    for (let i = 0; i < docs.length; i += 100) {
+      const batch = docs.slice(i, i + 100);
+      await Chroma.fromDocuments(batch, embeddings, {
+        collectionName: COLLECTION_NAME,
+      });
+    }
   } catch (error) {
     console.log('error', error);
     throw new Error('Failed to ingest your data');

utils/makechain.ts

@@ -1,6 +1,6 @@
 import { OpenAI } from 'langchain/llms/openai';
-import { PineconeStore } from 'langchain/vectorstores/pinecone';
 import { ConversationalRetrievalQAChain } from 'langchain/chains';
+import { Chroma } from 'langchain/vectorstores/chroma';
 
 const CONDENSE_PROMPT = `Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.
 
@@ -18,7 +18,7 @@ If the question is not related to the context, politely respond that you are tun
 Question: {question}
 Helpful answer in markdown:`;
 
-export const makeChain = (vectorstore: PineconeStore) => {
+export const makeChain = (vectorstore: Chroma) => {
   const model = new OpenAI({
     temperature: 0, // increase temepreature to get more creative answers
     modelName: 'gpt-3.5-turbo', //change this to gpt-4 if you have access

yarn.lock

@@ -881,6 +881,13 @@ chokidar@^3.5.3:
   optionalDependencies:
     fsevents "~2.3.2"
 
+chromadb@1.4.1:
+  version "1.4.1"
+  resolved "https://registry.yarnpkg.com/chromadb/-/chromadb-1.4.1.tgz#a81a826956051617fdd25299fc5d3132bcb9ebd6"
+  integrity sha512-vRcig4CJxJXs++cKMt9tHmk9YjQprxzLK9sVYD6iXfqRJBoXeoFzk/RS95Dz1J6/7aSfBwDsyx3AE2ePP9FnYA==
+  dependencies:
+    axios "^0.26.0"
+
 client-only@0.0.1:
   version "0.0.1"
   resolved "https://registry.yarnpkg.com/client-only/-/client-only-0.0.1.tgz#38bba5d403c41ab150bff64a95c85013cf73bca1"