vectara-agentic 0.1.3__tar.gz → 0.1.4__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of vectara-agentic might be problematic. Click here for more details.
- {vectara_agentic-0.1.3/vectara_agentic.egg-info → vectara_agentic-0.1.4}/PKG-INFO +5 -7
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/README.md +4 -5
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/setup.py +1 -2
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4/vectara_agentic.egg-info}/PKG-INFO +5 -7
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/LICENSE +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/MANIFEST.in +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/requirements.txt +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/setup.cfg +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/tests/test_agent.py +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/tests/test_tools.py +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic/__init__.py +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic/_callback.py +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic/_prompts.py +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic/agent.py +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic/tools.py +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic/tools_catalog.py +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic/types.py +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic/utils.py +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic.egg-info/SOURCES.txt +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic.egg-info/dependency_links.txt +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic.egg-info/requires.txt +0 -0
- {vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic.egg-info/top_level.txt +0 -0
|
@@ -1,11 +1,10 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: vectara_agentic
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.4
|
|
4
4
|
Summary: A Python package for creating AI Assistants and AI Agents with Vectara
|
|
5
5
|
Home-page: https://github.com/vectara/py-vectara-agentic
|
|
6
6
|
Author: Ofer Mendelevitch
|
|
7
7
|
Author-email: ofer@vectara.com
|
|
8
|
-
License: Apache-2.0
|
|
9
8
|
Project-URL: Documentation, https://vectara.github.io/vectara-agentic-docs/
|
|
10
9
|
Keywords: LLM,NLP,RAG,Agentic-RAG
|
|
11
10
|
Classifier: Programming Language :: Python :: 3
|
|
@@ -48,7 +47,7 @@ Requires-Dist: python-dotenv==1.0.1
|
|
|
48
47
|
[](https://discord.com/invite/GFb8gMz6UH)
|
|
49
48
|
|
|
50
49
|
|
|
51
|
-
The idea of LLM-based agents
|
|
50
|
+
The idea of LLM-based agents is to use the LLM for building sophisticated AI assistants:
|
|
52
51
|
- The LLM is used for reasoning and coming up with a game-plan for how to respond to the user query.
|
|
53
52
|
- There are 1 or more "tools" provided to the agent. These tools can be used by the LLM to execute its plan.
|
|
54
53
|
|
|
@@ -67,7 +66,7 @@ The idea of LLM-based agents it to use the LLM for building sophisticated AI ass
|
|
|
67
66
|
|
|
68
67
|
### Install vectara-agentic
|
|
69
68
|
|
|
70
|
-
- `
|
|
69
|
+
- `pip install vectara-agentic`
|
|
71
70
|
|
|
72
71
|
### Create your AI assistant
|
|
73
72
|
|
|
@@ -82,7 +81,7 @@ vec_factory = VectaraToolFactory(vectara_api_key=os.environ['VECTARA_API_KEY'],
|
|
|
82
81
|
vectara_customer_id=os.environ['VECTARA_CUSTOMER_ID'],
|
|
83
82
|
vectara_corpus_id=os.environ['VECTARA_CORPUS_ID'])
|
|
84
83
|
```
|
|
85
|
-
The
|
|
84
|
+
The Vectara tool factory has a useful helper function called `create_rag_tool` which automates the creation of a
|
|
86
85
|
tool to query Vectara RAG.
|
|
87
86
|
|
|
88
87
|
For example if my Vectara corpus includes financial information from company
|
|
@@ -112,8 +111,7 @@ this tool in the most effective way.
|
|
|
112
111
|
The `tool_filter_template` provides the template filtering expression the tool should use when calling Vectara.
|
|
113
112
|
|
|
114
113
|
You can of course create more than one Vectara tool; tools may point at different corpora or may have different parameters for search
|
|
115
|
-
or generation.
|
|
116
|
-
in the service of the agent, so should be differentiated.
|
|
114
|
+
or generation.
|
|
117
115
|
|
|
118
116
|
#### Step 2: Create Other Tools, as needed
|
|
119
117
|
|
|
@@ -7,7 +7,7 @@
|
|
|
7
7
|
[](https://discord.com/invite/GFb8gMz6UH)
|
|
8
8
|
|
|
9
9
|
|
|
10
|
-
The idea of LLM-based agents
|
|
10
|
+
The idea of LLM-based agents is to use the LLM for building sophisticated AI assistants:
|
|
11
11
|
- The LLM is used for reasoning and coming up with a game-plan for how to respond to the user query.
|
|
12
12
|
- There are 1 or more "tools" provided to the agent. These tools can be used by the LLM to execute its plan.
|
|
13
13
|
|
|
@@ -26,7 +26,7 @@ The idea of LLM-based agents it to use the LLM for building sophisticated AI ass
|
|
|
26
26
|
|
|
27
27
|
### Install vectara-agentic
|
|
28
28
|
|
|
29
|
-
- `
|
|
29
|
+
- `pip install vectara-agentic`
|
|
30
30
|
|
|
31
31
|
### Create your AI assistant
|
|
32
32
|
|
|
@@ -41,7 +41,7 @@ vec_factory = VectaraToolFactory(vectara_api_key=os.environ['VECTARA_API_KEY'],
|
|
|
41
41
|
vectara_customer_id=os.environ['VECTARA_CUSTOMER_ID'],
|
|
42
42
|
vectara_corpus_id=os.environ['VECTARA_CORPUS_ID'])
|
|
43
43
|
```
|
|
44
|
-
The
|
|
44
|
+
The Vectara tool factory has a useful helper function called `create_rag_tool` which automates the creation of a
|
|
45
45
|
tool to query Vectara RAG.
|
|
46
46
|
|
|
47
47
|
For example if my Vectara corpus includes financial information from company
|
|
@@ -71,8 +71,7 @@ this tool in the most effective way.
|
|
|
71
71
|
The `tool_filter_template` provides the template filtering expression the tool should use when calling Vectara.
|
|
72
72
|
|
|
73
73
|
You can of course create more than one Vectara tool; tools may point at different corpora or may have different parameters for search
|
|
74
|
-
or generation.
|
|
75
|
-
in the service of the agent, so should be differentiated.
|
|
74
|
+
or generation.
|
|
76
75
|
|
|
77
76
|
#### Step 2: Create Other Tools, as needed
|
|
78
77
|
|
|
@@ -8,8 +8,7 @@ def read_requirements():
|
|
|
8
8
|
|
|
9
9
|
setup(
|
|
10
10
|
name="vectara_agentic",
|
|
11
|
-
version="0.1.
|
|
12
|
-
license="Apache-2.0",
|
|
11
|
+
version="0.1.4",
|
|
13
12
|
author="Ofer Mendelevitch",
|
|
14
13
|
author_email="ofer@vectara.com",
|
|
15
14
|
description="A Python package for creating AI Assistants and AI Agents with Vectara",
|
|
@@ -1,11 +1,10 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: vectara_agentic
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.4
|
|
4
4
|
Summary: A Python package for creating AI Assistants and AI Agents with Vectara
|
|
5
5
|
Home-page: https://github.com/vectara/py-vectara-agentic
|
|
6
6
|
Author: Ofer Mendelevitch
|
|
7
7
|
Author-email: ofer@vectara.com
|
|
8
|
-
License: Apache-2.0
|
|
9
8
|
Project-URL: Documentation, https://vectara.github.io/vectara-agentic-docs/
|
|
10
9
|
Keywords: LLM,NLP,RAG,Agentic-RAG
|
|
11
10
|
Classifier: Programming Language :: Python :: 3
|
|
@@ -48,7 +47,7 @@ Requires-Dist: python-dotenv==1.0.1
|
|
|
48
47
|
[](https://discord.com/invite/GFb8gMz6UH)
|
|
49
48
|
|
|
50
49
|
|
|
51
|
-
The idea of LLM-based agents
|
|
50
|
+
The idea of LLM-based agents is to use the LLM for building sophisticated AI assistants:
|
|
52
51
|
- The LLM is used for reasoning and coming up with a game-plan for how to respond to the user query.
|
|
53
52
|
- There are 1 or more "tools" provided to the agent. These tools can be used by the LLM to execute its plan.
|
|
54
53
|
|
|
@@ -67,7 +66,7 @@ The idea of LLM-based agents it to use the LLM for building sophisticated AI ass
|
|
|
67
66
|
|
|
68
67
|
### Install vectara-agentic
|
|
69
68
|
|
|
70
|
-
- `
|
|
69
|
+
- `pip install vectara-agentic`
|
|
71
70
|
|
|
72
71
|
### Create your AI assistant
|
|
73
72
|
|
|
@@ -82,7 +81,7 @@ vec_factory = VectaraToolFactory(vectara_api_key=os.environ['VECTARA_API_KEY'],
|
|
|
82
81
|
vectara_customer_id=os.environ['VECTARA_CUSTOMER_ID'],
|
|
83
82
|
vectara_corpus_id=os.environ['VECTARA_CORPUS_ID'])
|
|
84
83
|
```
|
|
85
|
-
The
|
|
84
|
+
The Vectara tool factory has a useful helper function called `create_rag_tool` which automates the creation of a
|
|
86
85
|
tool to query Vectara RAG.
|
|
87
86
|
|
|
88
87
|
For example if my Vectara corpus includes financial information from company
|
|
@@ -112,8 +111,7 @@ this tool in the most effective way.
|
|
|
112
111
|
The `tool_filter_template` provides the template filtering expression the tool should use when calling Vectara.
|
|
113
112
|
|
|
114
113
|
You can of course create more than one Vectara tool; tools may point at different corpora or may have different parameters for search
|
|
115
|
-
or generation.
|
|
116
|
-
in the service of the agent, so should be differentiated.
|
|
114
|
+
or generation.
|
|
117
115
|
|
|
118
116
|
#### Step 2: Create Other Tools, as needed
|
|
119
117
|
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{vectara_agentic-0.1.3 → vectara_agentic-0.1.4}/vectara_agentic.egg-info/dependency_links.txt
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|