Convert any Text Data into a Knowledge Graph (using LLAMA3 + GROQ)
I shared the most efficient way to convert any text data into a knowledge graph using LLAMA3 + GROQ. It's free and straightforward. No need any GPU, you could run it in a standard device.
Basic Tutorial: • The easiest way to cha...
Chapter:
00:00:00 - Intro
00:00:44 - How to load any text data?
00:01:35 - Data Overview
00:02:15 - Map Reduce Summarization
00:03:11 - Should we use spacy-llm?
00:04:53 - Key insights: define entities, relations and few shot example
00:06:12 - Using LLAMA3 & GROQ to convert text into a knowledge graph
00:06:30 - GROQ set up
00:06:50 - How to extract entities and relationships?
00:10:50 - How to convert extracted entities and relationships into a Cypher Query?
00:12:40 - How to insert generated Cypher Query to Neo4J database?
00:13:05 - Result Overview
00:13:35 - Outro
Everything you'll need:
Github repo: github.com/projectwilsen/Know...
GROQ API: console.groq.com/keys
#llm #llama3 #knowledgegraph #langchain #groq #neo4j #python
Пікірлер: 25
Excellent effort, great explanation, nicely paced, great idea to build, and showing the process of how you got here is also great. Majority of the videos out there are how to invoke an API on OpenAI which has limited educational value but your video is amazing. Great effort!
@geralduswilsen
2 ай бұрын
Thank you for your kind words! Hope it is helpful!
Nice work Geraldus !
@geralduswilsen
2 ай бұрын
Thank you Pierre!
Excellent!
@geralduswilsen
2 ай бұрын
Many thanks!
Great guide! Next would be great to consider for to integrate new information into existing KG
@geralduswilsen
2 ай бұрын
Thanks for the feedback! I'll keep it in mind for the next videos
Very cool!
@geralduswilsen
2 ай бұрын
Thank you Tomaz!
Hey, this channel is dope
@geralduswilsen
2 ай бұрын
Thank you!
Thank you for sharing this deep dive! Is there a way to find a schema to convert a book (that has chapters, and such) to KG?
Great!
@geralduswilsen
2 ай бұрын
Thank you!
The manual coreference resolution part implied a challenge. Did you try some prompting to work around it
@geralduswilsen
2 ай бұрын
Hey! I haven't tried using other prompting strategies to solve this challenge, but I would like to explore them further next time. It's also a great point to mention that I process each line individually, which might have caused the llm to miss the context. If we process correlated sentences together (for example, sentences 1 & 2) in one run, we might obtain different results, as I believe the llm would grasp the context better in that case.
@xuantungnguyen9719
2 ай бұрын
@@geralduswilsen Say if this text2graph thing worked out would you mind do a video of how to scale it up to cross-documents, even make a full blown API out of it :)
@geralduswilsen
2 ай бұрын
@@xuantungnguyen9719 sure, would love to do it! I'll try to explore further
nice video Geraldus, but you shouldnt be doing whatever processing you are doing on the audio (speeding it up?) It makes it very difficult to understand.
@geralduswilsen
Ай бұрын
Hey James, thank you so much for your feedback!
@contractorwolf
Ай бұрын
@@geralduswilsen no problem Geraldus, i like your content. Glad you didnt take it persoanlly
this seems ai genatated
@geralduswilsen
2 ай бұрын
Hey, hope it helpful!