llm_memory 0.1.7 → 0.1.8
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/Gemfile.lock +1 -1
- data/README.md +27 -6
- data/lib/llm_memory/hippocampus.rb +3 -3
- data/lib/llm_memory/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: baa56ad255b6c35f11a18779aa0e1bd3257b36fc53e1f6870cb5ae902dcb71a9
|
|
4
|
+
data.tar.gz: 1c03bea26b44ca3f74c7097155582087d645808756ba0e95e2f6767c912bd3f3
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: e698370bda45506cf5e5be841378d5e5ba0914890cdd09dc65f254cc838c6d009ae188ccf8d0253a0eea96fde20f8ff968a5eaadd2626b4f88f208eaf0ab4faa
|
|
7
|
+
data.tar.gz: f78e7cda1b8438c66f2bf672591cf819db1e1651a6528dd752c0ae9ddf7c3a7d8657de3c93d5e0f3c62478a76ec26bf944d13624809f1c45c44a00a7b88976ec
|
data/Gemfile.lock
CHANGED
data/README.md
CHANGED
|
@@ -14,7 +14,7 @@ This enables better integration with systems such as Rails and web services whil
|
|
|
14
14
|
|
|
15
15
|
## LLM Memory Components
|
|
16
16
|
|
|
17
|
-
|
|
18
18
|
|
|
19
19
|
1. LlmMemory::Wernicke: Responsible for loading external data (currently from files). More loader types are planned for future development.
|
|
20
20
|
|
|
@@ -61,6 +61,8 @@ To use LLM Memory, follow these steps:
|
|
|
61
61
|
5. Use LlmMemory::Hippocampus to search for relevant information based on user queries
|
|
62
62
|
6. Create and use ERB templates with LlmMemory::Broca to generate responses based on the information retrieved
|
|
63
63
|
|
|
64
|
+
For the details of each class, please refer to [API reference document](https://github.com/shohey1226/llm_memory/wiki/API-Reference).
|
|
65
|
+
|
|
64
66
|
```ruby
|
|
65
67
|
docs = LlmMemory::Wernicke.load(:file, "/tmp/a_directory")
|
|
66
68
|
# docs is just an array of hash.
|
|
@@ -111,9 +113,28 @@ message2 = broca.respond(query_str: query_str2, related_docs: related_docs)
|
|
|
111
113
|
|
|
112
114
|
The table below provides a list of plugins utilized by llm_memory. The aim is to keep the core llm_memory lightweight while allowing for easy extensibility through the use of plugins.
|
|
113
115
|
|
|
114
|
-
|
|
115
|
-
|
|
116
|
-
|
|
116
|
+
Install the plugin and update the method.
|
|
117
|
+
|
|
118
|
+
For example, if you wan to use pgvector. then,
|
|
119
|
+
|
|
120
|
+
```
|
|
121
|
+
$ bundle add llm_memory_pgvector
|
|
122
|
+
```
|
|
123
|
+
|
|
124
|
+
Then, load it instead of `:redis` (default is redis).
|
|
125
|
+
|
|
126
|
+
```ruby
|
|
127
|
+
# may need to have require depending on the project
|
|
128
|
+
# require llm_memory_pgvector
|
|
129
|
+
hippocamups = LlmMemory::Hippocampus.new(store: :pgvector)`
|
|
130
|
+
```
|
|
131
|
+
|
|
132
|
+
Please refer to the links for the details.
|
|
133
|
+
|
|
134
|
+
| Plugin Name | Type | Module | Link |
|
|
135
|
+
| ----------------------- | ------ | ----------- | ------------------------------------------------------------- |
|
|
136
|
+
| llm_memory_gmail_loader | Loader | Wernicke | [link](https://github.com/shohey1226/llm_memory_gmail_loader) |
|
|
137
|
+
| llm_memory_pgvector | Store | Hippocampus | [link](https://github.com/shohey1226/llm_memory_pgvector) |
|
|
117
138
|
|
|
118
139
|
## Development
|
|
119
140
|
|
|
@@ -123,7 +144,7 @@ To install this gem onto your local machine, run `bundle exec rake install`. To
|
|
|
123
144
|
|
|
124
145
|
## Contributing
|
|
125
146
|
|
|
126
|
-
Bug reports and pull requests are welcome on GitHub at https://github.com/
|
|
147
|
+
Bug reports and pull requests are welcome on GitHub at https://github.com/shohey1226/llm_memory. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [code of conduct](https://github.com/shohey1226/llm_memory/blob/master/CODE_OF_CONDUCT.md).
|
|
127
148
|
|
|
128
149
|
## License
|
|
129
150
|
|
|
@@ -131,4 +152,4 @@ The gem is available as open source under the terms of the [MIT License](https:/
|
|
|
131
152
|
|
|
132
153
|
## Code of Conduct
|
|
133
154
|
|
|
134
|
-
Everyone interacting in the LlmMemory project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/
|
|
155
|
+
Everyone interacting in the LlmMemory project's codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/shohey1226/llm_memory/blob/master/CODE_OF_CONDUCT.md).
|
|
@@ -10,7 +10,7 @@ module LlmMemory
|
|
|
10
10
|
embedding_name: :openai,
|
|
11
11
|
chunk_size: 1024,
|
|
12
12
|
chunk_overlap: 50,
|
|
13
|
-
|
|
13
|
+
store: :redis,
|
|
14
14
|
index_name: "llm_memory"
|
|
15
15
|
)
|
|
16
16
|
LlmMemory.configure
|
|
@@ -19,8 +19,8 @@ module LlmMemory
|
|
|
19
19
|
raise "Embedding '#{embedding_name}' not found." unless embedding_class
|
|
20
20
|
@embedding_instance = embedding_class.new
|
|
21
21
|
|
|
22
|
-
store_class = StoreManager.stores[
|
|
23
|
-
raise "Store '#{
|
|
22
|
+
store_class = StoreManager.stores[store]
|
|
23
|
+
raise "Store '#{store}' not found." unless store_class
|
|
24
24
|
@store = store_class.new(index_name: index_name)
|
|
25
25
|
|
|
26
26
|
# char count, not word count
|
data/lib/llm_memory/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: llm_memory
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.1.
|
|
4
|
+
version: 0.1.8
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Shohei Kameda
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: exe
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2023-05-
|
|
11
|
+
date: 2023-05-18 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: tokenizers
|