Mikiko Bazeley commited on
Commit
5fb28fd
·
1 Parent(s): 869335e

Added additional env vars & Airbnb data

Browse files
HW.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # HW 7: Solutions
2
+
3
+ ## Deliverables
4
+
5
+ * Completed Notebook
6
+ * Chainlit Application in a Hugging Face Space Powered by Hugging Face Endpoints
7
+ * Screenshot of endpoint usage
8
+
9
+ ### Completed notebook
10
+
11
+ [Located here](./Completed_BazeleyMikiko_Open_Source_RAG_Leveraging_Hugging_Face_Endpoints_through_LangChain.ipynb)
12
+ [Also on HF space](https://huggingface.co/spaces/mmbazel/AIE3-Demo-Wk4Day1/blob/main/%5BCompleted%5D%20BazeleyMikiko_Open_Source_RAG_Leveraging_Hugging_Face_Endpoints_through_LangChain.ipynb)
13
+
14
+ ### Chainlit Application
15
+
16
+ [Link to Chainlit App in HuggingFace Space](https://huggingface.co/spaces/mmbazel/AIE3-Demo-Wk4Day1)
17
+
18
+
19
+ ### Screenshots
20
+ #### The chat
21
+ ![alt text](img/chat.png)
22
+
23
+ #### The trace
24
+ ![alt text](img/full_trace.png)
25
+
26
+ #### The endpoints
27
+ ![alt text](img/endpoints.png)
28
+
29
+ #### The LLM model endpoint
30
+ ![alt text](img/llm-endpoint.png)
31
+
32
+ #### The embeddings model endpoint
33
+ ![alt text](img/embedding-endpoint.png)
34
+
35
+ ### The Loom video
36
+ https://www.loom.com/share/162d71e4d445442faa40dba76f4cbf13
37
+
38
+
39
+ ### Lessons Learned & Open Questions
40
+
41
+ #### Lessons
42
+ 1. Learning how to translate notebook code into scripts.
43
+ 2. Learning/reminder that HF spaces can be used in dev mode and connected to VSCode.
44
+ 3. Learning how to setup LCEL RAG Chain.
45
+ - Understand how to deploy open-source LLMs & embedding models to scalable endpoints for production-grade LLM & RAG applications
46
+ - Build a RAG application with LCEL
47
+ - Build a front-end UI for RAG applications with Chainlit
48
+
49
+ #### Questions
50
+ 1. What are the challenges using LangChain in production - see lots of folks complaining about it on LinkedIn and Twitter.
51
+ 2. What complex RAG looks like.
52
+ 3. Have a basic understanding of the metrics used to monitor performance but still a novice with regards to LLM evals.
53
+
data/fdb60f7d-e616-43dc-86ef-e33d3a9bdd05.pdf ADDED
Binary file (596 kB). View file