diff --git a/Content/20231012140139-large_language_models.org b/Content/20231012140139-large_language_models.org
index aa53cb0..c25f28b 100644
--- a/Content/20231012140139-large_language_models.org
+++ b/Content/20231012140139-large_language_models.org
@@ -161,5 +161,8 @@ The scaling laws for Large Language Models (LLMs) describe how changes in differ
 - *Temperature, Top-k, and Top-p Sampling*:
   - These hyperparameters work together to modulate the randomness and quality of the generated text during inference.
 
+** [[id:4f197b8c-7f2c-442f-9350-ef1f83cd8701][Low Rank Adaptation]]
+** [[id:02b7c7eb-2ba2-43b8-8cdb-c5e7d201596a][RLHF]]
+* Resources
 ** Book: Building LLMs for production
  - https://towardsai.net/book
diff --git a/Content/20240818170034-llammaindex.org b/Content/20240818170034-llammaindex.org
index a00af69..3d76780 100644
--- a/Content/20240818170034-llammaindex.org
+++ b/Content/20240818170034-llammaindex.org
@@ -4,7 +4,10 @@
 #+title: Llammaindex
 #+filetags: :ai:tool:
 
+*
 * Relevant Nodes
 ** [[id:d9d30a75-f1aa-4ca0-8480-cb617afe29ab][Deep Lake Vector Stores]]
+** [[id:29c7a4c9-2699-4c8c-b2f2-a8e9bd5731ce][Ragas]]
+** [[id:a8c2f397-3380-4aae-a771-63a4b688d4fe][DeepEval]]
 * Resources
 - https://www.llamaindex.ai/
diff --git a/Content/20241120170558-golden_datasets.org b/Content/20241120170558-golden_datasets.org
new file mode 100644
index 0000000..3438ca0
--- /dev/null
+++ b/Content/20241120170558-golden_datasets.org
@@ -0,0 +1,5 @@
+:PROPERTIES:
+:ID:       a8bec6b4-f0ca-4c93-bbf0-a187935dd57b
+:END:
+#+title: Golden Datasets
+#+filetags: :ai:data:
diff --git a/Content/20241120170737-ragas.org b/Content/20241120170737-ragas.org
new file mode 100644
index 0000000..f2ae48d
--- /dev/null
+++ b/Content/20241120170737-ragas.org
@@ -0,0 +1,9 @@
+:PROPERTIES:
+:ID:       29c7a4c9-2699-4c8c-b2f2-a8e9bd5731ce
+:END:
+#+title: Ragas
+#+filetags: :tool:ai:
+
+* Resources
+ - https://github.com/explodinggradients/ragas/tree/main
+ - https://docs.ragas.io/en/stable/
diff --git a/Content/20241120171009-deep_eval.org b/Content/20241120171009-deep_eval.org
new file mode 100644
index 0000000..c173a15
--- /dev/null
+++ b/Content/20241120171009-deep_eval.org
@@ -0,0 +1,8 @@
+:PROPERTIES:
+:ID:       a8c2f397-3380-4aae-a771-63a4b688d4fe
+:END:
+#+title: DeepEval
+#+filetags: :tool:ai:
+
+* Resources
+ -  https://github.com/confident-ai/deepeval
diff --git a/Content/20241121103238-autogpt.org b/Content/20241121103238-autogpt.org
new file mode 100644
index 0000000..8939c93
--- /dev/null
+++ b/Content/20241121103238-autogpt.org
@@ -0,0 +1,9 @@
+:PROPERTIES:
+:ID:       663bd13a-1f02-4e96-a56f-1257ff5a162b
+:END:
+#+title: AutoGPT
+#+filetags: :tool:ai:
+
+
+* Resources
+  - https://agpt.co/blog/introducing-the-autogpt-platform
diff --git a/Content/20241121112417-rlhf.org b/Content/20241121112417-rlhf.org
new file mode 100644
index 0000000..f7af231
--- /dev/null
+++ b/Content/20241121112417-rlhf.org
@@ -0,0 +1,13 @@
+:PROPERTIES:
+:ID:       02b7c7eb-2ba2-43b8-8cdb-c5e7d201596a
+:ROAM_ALIASES: "Reinforcement Learning from Human Feedback"
+:END:
+#+title: RLHF
+#+filetags: :rl:ai:
+
+
+* Relevant Nodes
+** [[id:64e7e0eb-ab1f-42db-b027-fc8069a65f3d][Direct Preference Optimization]]
+** [[id:54f1b3b2-28ba-485b-947a-98c48ae41caa][RLAIF]]
+* Resources
+ - https://openai.com/index/instruction-following/
diff --git a/Content/20241121112433-low_rank_adaptation.org b/Content/20241121112433-low_rank_adaptation.org
new file mode 100644
index 0000000..9eb93e0
--- /dev/null
+++ b/Content/20241121112433-low_rank_adaptation.org
@@ -0,0 +1,6 @@
+:PROPERTIES:
+:ID:       4f197b8c-7f2c-442f-9350-ef1f83cd8701
+:ROAM_ALIASES: "Quantized Low-Rank Adaptation" QLoRa LoRA
+:END:
+#+title: Low Rank Adaptation
+#+filetags: :ai:
diff --git a/Content/20241121113422-direct_preference_optimization.org b/Content/20241121113422-direct_preference_optimization.org
new file mode 100644
index 0000000..e0caf58
--- /dev/null
+++ b/Content/20241121113422-direct_preference_optimization.org
@@ -0,0 +1,6 @@
+:PROPERTIES:
+:ID:       64e7e0eb-ab1f-42db-b027-fc8069a65f3d
+:ROAM_ALIASES: DPO
+:END:
+#+title: Direct Preference Optimization
+#+filetags: :ai:
diff --git a/Content/20241121113552-rlaif.org b/Content/20241121113552-rlaif.org
new file mode 100644
index 0000000..a6fc45d
--- /dev/null
+++ b/Content/20241121113552-rlaif.org
@@ -0,0 +1,5 @@
+:PROPERTIES:
+:ID:       54f1b3b2-28ba-485b-947a-98c48ae41caa
+:ROAM_ALIASES: "Reinforcement Learning from AI Feedback"
+:END:
+#+title: RLAIF