Hamza/Chatbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Hamza 2026-05-21 11:07:05 +02:00
parent 8b9fcd1b30
commit b71b14b55a
1 changed files with 0 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
README.md
View File

@ -18,7 +18,6 @@
- [Step 4: Faiss Vector Store](#step-4-faiss-vector-store)
- [Step 5: Ollama Chat Model](#step-5-ollama-chat-model)
- [Step 6: Buffer Memory](#step-6-buffer-memory)
- [Step 7: Conversational Retrieval QA Chain](#step-7-conversational-retrieval-qa-chain)
7. [Upsert Documents](#upsert-documents)
8. [Using Cloud LLM APIs (Optional)](#using-cloud-llm-apis-optional)
9. [Deploy Chatbot to Users](#deploy-chatbot-to-users)
@ -279,21 +278,6 @@ Connect the **BufferMemory** output to the **Memory** input of the QA Chain.
---
### Step 7: Conversational Retrieval QA Chain
Search for **"Conversational Retrieval QA Chain"** and drag it onto the canvas.
Connect:
- **ChatOllama** → **Chat Model**
- **Faiss Retriever** → **Vector Store Retriever**
- **BufferMemory** → **Memory**
Leave **Input Moderation** and **Return Source Documents** as optional based on your needs.
**Save the flow** using the save button (top right).
---
## Upsert Documents
Before the chatbot can answer questions, you must index your documents into the vector store.