Skip to content

Commit cbed79d

Browse files
RS-labhubRS-labhub
committed
fix: broken widgets in the notebooks
1 parent 9ccab40 commit cbed79d

23 files changed

+49399
-49363
lines changed

‎examples/Notebooks/NoteBook_Examples/agent_multistep_analysis_nb.ipynb‎

Lines changed: 196 additions & 196 deletions
Original file line numberDiff line numberDiff line change
@@ -1,198 +1,198 @@
11
{
2-
"nbformat": 4,
3-
"nbformat_minor": 0,
4-
"metadata": {
5-
"colab": {
6-
"provenance": [],
7-
"gpuType": "T4"
8-
},
9-
"kernelspec": {
10-
"name": "python3",
11-
"display_name": "Python 3"
12-
},
13-
"language_info": {
14-
"name": "python"
15-
},
16-
"accelerator": "GPU"
2+
"cells": [
3+
{
4+
"cell_type": "markdown",
5+
"metadata": {
6+
"id": "6sr3Gk8hNDaF"
7+
},
8+
"source": []
179
},
18-
"cells": [
19-
{
20-
"cell_type": "markdown",
21-
"source": [],
22-
"metadata": {
23-
"id": "6sr3Gk8hNDaF"
24-
}
25-
},
26-
{
27-
"cell_type": "markdown",
28-
"source": [
29-
"# If you are using Colab for free, we highly recommend you activate the T4 GPU\n",
30-
"# hardware accelerator. Our models are designed to run with at least 16GB\n",
31-
"# of RAM, activating T4 will grant the notebook 16GB of GDDR6 RAM as opposed\n",
32-
"# to the ~13GB Colab gives automatically.\n",
33-
"# To activate T4:\n",
34-
"# 1. click on the \"Runtime\" tab\n",
35-
"# 2. click on \"Change runtime type\"\n",
36-
"# 3. select T4 GPU under Hardware Accelerator\n",
37-
"# NOTE: there is a weekly usage limit on using T4 for free"
38-
],
39-
"metadata": {
40-
"id": "eQk5Dv3jyheg"
41-
}
42-
},
43-
{
44-
"cell_type": "code",
45-
"source": [
46-
"!pip install llmware"
47-
],
48-
"metadata": {
49-
"id": "td7dVt4fD_j6"
50-
},
51-
"execution_count": null,
52-
"outputs": []
53-
},
54-
{
55-
"cell_type": "code",
56-
"source": [
57-
"!pip install --upgrade huggingface_hub\n"
58-
],
59-
"metadata": {
60-
"id": "IY8ysw9FElZR"
61-
},
62-
"execution_count": null,
63-
"outputs": []
64-
},
65-
{
66-
"cell_type": "code",
67-
"execution_count": 8,
68-
"metadata": {
69-
"id": "AeR-LvVXD27i"
70-
},
71-
"outputs": [],
72-
"source": [
73-
"\n",
74-
"\"\"\" This example shows a complex multi-part research analysis. In this example, we will:\n",
75-
"\n",
76-
" 1. Build a \"research\" library.\n",
77-
" 2. Query the research library to identify topics of interest.\n",
78-
" 3. Create an agent with several analytical tools: sentiment, emotions, topic, entities analysis\n",
79-
" 4. Pass the results of our query to the agent to conduct multifaceted analysis.\n",
80-
" 5. Apply a top-level filter ('sentiment') on the results from the query\n",
81-
" 6. For any of the passages with negative sentiment, we will run a follow-up set of analyses.\n",
82-
" 7. Finally, we will assemble the follow-up analysis into a list of detailed reports.\n",
83-
"\"\"\"\n",
84-
"\n",
85-
"import os\n",
86-
"import shutil\n",
87-
"\n",
88-
"from llmware.agents import LLMfx\n",
89-
"from llmware.library import Library\n",
90-
"from llmware.retrieval import Query\n",
91-
"from llmware.configs import LLMWareConfig\n",
92-
"from llmware.setup import Setup\n",
93-
"\n",
94-
"\n",
95-
"\n",
96-
"\n"
97-
]
98-
},
99-
{
100-
"cell_type": "code",
101-
"source": [
102-
"def multistep_analysis():\n",
103-
"\n",
104-
" \"\"\" In this example, our objective is to research Microsoft history and rivalry in the 1980s with IBM. \"\"\"\n",
105-
"\n",
106-
" # step 1 - assemble source documents and create library\n",
107-
"\n",
108-
" print(\"update: Starting example - agent-multistep-analysis\")\n",
109-
"\n",
110-
" # note: lines 38-49 attempt to automatically pull sample document into local path\n",
111-
" # depending upon permissions in your environment, you may need to set up directly\n",
112-
" # if you pull down the samples files with Setup().load_sample_files(), in the Books folder,\n",
113-
" # you will find the source: \"Bill-Gates-Biography.pdf\"\n",
114-
" # if you have pulled sample documents in the past, then to update to latest: set over_write=True\n",
115-
"\n",
116-
" print(\"update: Loading sample files\")\n",
117-
"\n",
118-
" sample_files_path = Setup().load_sample_files(over_write=False)\n",
119-
" bill_gates_bio = \"Bill-Gates-Biography.pdf\"\n",
120-
" path_to_bill_gates_bio = os.path.join(sample_files_path, \"Books\", bill_gates_bio)\n",
121-
"\n",
122-
" microsoft_folder = os.path.join(LLMWareConfig().get_tmp_path(), \"example_microsoft\")\n",
123-
"\n",
124-
" print(\"update: attempting to create source input folder at path: \", microsoft_folder)\n",
125-
"\n",
126-
" if not os.path.exists(microsoft_folder):\n",
127-
" os.mkdir(microsoft_folder)\n",
128-
" os.chmod(microsoft_folder, 0o777)\n",
129-
" shutil.copy(path_to_bill_gates_bio,os.path.join(microsoft_folder, bill_gates_bio))\n",
130-
"\n",
131-
" # create library\n",
132-
" print(\"update: creating library and parsing source document\")\n",
133-
"\n",
134-
" LLMWareConfig().set_active_db(\"sqlite\")\n",
135-
" my_lib = Library().create_new_library(\"microsoft_history_0210_1\")\n",
136-
" my_lib.add_files(microsoft_folder)\n",
137-
"\n",
138-
" # run our first query - \"ibm\"\n",
139-
" query = \"ibm\"\n",
140-
" search_results = Query(my_lib).text_query(query)\n",
141-
" print(f\"update: executing query to filter to key passages - {query} - results found - {len(search_results)}\")\n",
142-
"\n",
143-
" # create an agent and load several tools that we will be using\n",
144-
" agent = LLMfx()\n",
145-
" agent.load_tool_list([\"sentiment\", \"emotions\", \"topic\", \"tags\", \"ner\", \"answer\"])\n",
146-
"\n",
147-
" # load the search results into the agent's work queue\n",
148-
" agent.load_work(search_results)\n",
149-
"\n",
150-
" while True:\n",
151-
"\n",
152-
" agent.sentiment()\n",
153-
"\n",
154-
" if not agent.increment_work_iteration():\n",
155-
" break\n",
156-
"\n",
157-
" # analyze sections where the sentiment on ibm was negative\n",
158-
" follow_up_list = agent.follow_up_list(key=\"sentiment\", value=\"negative\")\n",
159-
"\n",
160-
" for job_index in follow_up_list:\n",
161-
"\n",
162-
" # follow-up 'deep dive' on selected text that references ibm negatively\n",
163-
" agent.set_work_iteration(job_index)\n",
164-
" agent.exec_multitool_function_call([\"tags\", \"emotions\", \"topics\", \"ner\"])\n",
165-
" agent.answer(\"What is a brief summary?\", key=\"summary\")\n",
166-
"\n",
167-
" my_report = agent.show_report(follow_up_list)\n",
168-
"\n",
169-
" activity_summary = agent.activity_summary()\n",
170-
"\n",
171-
" for entries in my_report:\n",
172-
" print(\"my report entries: \", entries)\n",
173-
"\n",
174-
" return my_report"
175-
],
176-
"metadata": {
177-
"id": "qG3lAj2nM372"
178-
},
179-
"execution_count": 9,
180-
"outputs": []
181-
},
182-
{
183-
"cell_type": "code",
184-
"source": [
185-
"\n",
186-
"if __name__ == \"__main__\":\n",
187-
"\n",
188-
" multistep_analysis()\n",
189-
"\n"
190-
],
191-
"metadata": {
192-
"id": "NDKDVuEoM9rL"
193-
},
194-
"execution_count": null,
195-
"outputs": []
196-
}
197-
]
198-
}
10+
{
11+
"cell_type": "markdown",
12+
"metadata": {
13+
"id": "eQk5Dv3jyheg"
14+
},
15+
"source": [
16+
"# If you are using Colab for free, we highly recommend you activate the T4 GPU\n",
17+
"# hardware accelerator. Our models are designed to run with at least 16GB\n",
18+
"# of RAM, activating T4 will grant the notebook 16GB of GDDR6 RAM as opposed\n",
19+
"# to the ~13GB Colab gives automatically.\n",
20+
"# To activate T4:\n",
21+
"# 1. click on the \"Runtime\" tab\n",
22+
"# 2. click on \"Change runtime type\"\n",
23+
"# 3. select T4 GPU under Hardware Accelerator\n",
24+
"# NOTE: there is a weekly usage limit on using T4 for free"
25+
]
26+
},
27+
{
28+
"cell_type": "code",
29+
"execution_count": null,
30+
"metadata": {
31+
"id": "td7dVt4fD_j6"
32+
},
33+
"outputs": [],
34+
"source": [
35+
"!pip install llmware"
36+
]
37+
},
38+
{
39+
"cell_type": "code",
40+
"execution_count": null,
41+
"metadata": {
42+
"id": "IY8ysw9FElZR"
43+
},
44+
"outputs": [],
45+
"source": [
46+
"!pip install --upgrade huggingface_hub\n"
47+
]
48+
},
49+
{
50+
"cell_type": "code",
51+
"execution_count": 8,
52+
"metadata": {
53+
"id": "AeR-LvVXD27i"
54+
},
55+
"outputs": [],
56+
"source": [
57+
"\n",
58+
"\"\"\" This example shows a complex multi-part research analysis. In this example, we will:\n",
59+
"\n",
60+
" 1. Build a \"research\" library.\n",
61+
" 2. Query the research library to identify topics of interest.\n",
62+
" 3. Create an agent with several analytical tools: sentiment, emotions, topic, entities analysis\n",
63+
" 4. Pass the results of our query to the agent to conduct multifaceted analysis.\n",
64+
" 5. Apply a top-level filter ('sentiment') on the results from the query\n",
65+
" 6. For any of the passages with negative sentiment, we will run a follow-up set of analyses.\n",
66+
" 7. Finally, we will assemble the follow-up analysis into a list of detailed reports.\n",
67+
"\"\"\"\n",
68+
"\n",
69+
"import os\n",
70+
"import shutil\n",
71+
"\n",
72+
"from llmware.agents import LLMfx\n",
73+
"from llmware.library import Library\n",
74+
"from llmware.retrieval import Query\n",
75+
"from llmware.configs import LLMWareConfig\n",
76+
"from llmware.setup import Setup\n",
77+
"\n",
78+
"\n",
79+
"\n",
80+
"\n"
81+
]
82+
},
83+
{
84+
"cell_type": "code",
85+
"execution_count": 9,
86+
"metadata": {
87+
"id": "qG3lAj2nM372"
88+
},
89+
"outputs": [],
90+
"source": [
91+
"def multistep_analysis():\n",
92+
"\n",
93+
" \"\"\" In this example, our objective is to research Microsoft history and rivalry in the 1980s with IBM. \"\"\"\n",
94+
"\n",
95+
" # step 1 - assemble source documents and create library\n",
96+
"\n",
97+
" print(\"update: Starting example - agent-multistep-analysis\")\n",
98+
"\n",
99+
" # note: lines 38-49 attempt to automatically pull sample document into local path\n",
100+
" # depending upon permissions in your environment, you may need to set up directly\n",
101+
" # if you pull down the samples files with Setup().load_sample_files(), in the Books folder,\n",
102+
" # you will find the source: \"Bill-Gates-Biography.pdf\"\n",
103+
" # if you have pulled sample documents in the past, then to update to latest: set over_write=True\n",
104+
"\n",
105+
" print(\"update: Loading sample files\")\n",
106+
"\n",
107+
" sample_files_path = Setup().load_sample_files(over_write=False)\n",
108+
" bill_gates_bio = \"Bill-Gates-Biography.pdf\"\n",
109+
" path_to_bill_gates_bio = os.path.join(sample_files_path, \"Books\", bill_gates_bio)\n",
110+
"\n",
111+
" microsoft_folder = os.path.join(LLMWareConfig().get_tmp_path(), \"example_microsoft\")\n",
112+
"\n",
113+
" print(\"update: attempting to create source input folder at path: \", microsoft_folder)\n",
114+
"\n",
115+
" if not os.path.exists(microsoft_folder):\n",
116+
" os.mkdir(microsoft_folder)\n",
117+
" os.chmod(microsoft_folder, 0o777)\n",
118+
" shutil.copy(path_to_bill_gates_bio,os.path.join(microsoft_folder, bill_gates_bio))\n",
119+
"\n",
120+
" # create library\n",
121+
" print(\"update: creating library and parsing source document\")\n",
122+
"\n",
123+
" LLMWareConfig().set_active_db(\"sqlite\")\n",
124+
" my_lib = Library().create_new_library(\"microsoft_history_0210_1\")\n",
125+
" my_lib.add_files(microsoft_folder)\n",
126+
"\n",
127+
" # run our first query - \"ibm\"\n",
128+
" query = \"ibm\"\n",
129+
" search_results = Query(my_lib).text_query(query)\n",
130+
" print(f\"update: executing query to filter to key passages - {query} - results found - {len(search_results)}\")\n",
131+
"\n",
132+
" # create an agent and load several tools that we will be using\n",
133+
" agent = LLMfx()\n",
134+
" agent.load_tool_list([\"sentiment\", \"emotions\", \"topic\", \"tags\", \"ner\", \"answer\"])\n",
135+
"\n",
136+
" # load the search results into the agent's work queue\n",
137+
" agent.load_work(search_results)\n",
138+
"\n",
139+
" while True:\n",
140+
"\n",
141+
" agent.sentiment()\n",
142+
"\n",
143+
" if not agent.increment_work_iteration():\n",
144+
" break\n",
145+
"\n",
146+
" # analyze sections where the sentiment on ibm was negative\n",
147+
" follow_up_list = agent.follow_up_list(key=\"sentiment\", value=\"negative\")\n",
148+
"\n",
149+
" for job_index in follow_up_list:\n",
150+
"\n",
151+
" # follow-up 'deep dive' on selected text that references ibm negatively\n",
152+
" agent.set_work_iteration(job_index)\n",
153+
" agent.exec_multitool_function_call([\"tags\", \"emotions\", \"topics\", \"ner\"])\n",
154+
" agent.answer(\"What is a brief summary?\", key=\"summary\")\n",
155+
"\n",
156+
" my_report = agent.show_report(follow_up_list)\n",
157+
"\n",
158+
" activity_summary = agent.activity_summary()\n",
159+
"\n",
160+
" for entries in my_report:\n",
161+
" print(\"my report entries: \", entries)\n",
162+
"\n",
163+
" return my_report"
164+
]
165+
},
166+
{
167+
"cell_type": "code",
168+
"execution_count": null,
169+
"metadata": {
170+
"id": "NDKDVuEoM9rL"
171+
},
172+
"outputs": [],
173+
"source": [
174+
"\n",
175+
"if __name__ == \"__main__\":\n",
176+
"\n",
177+
" multistep_analysis()\n",
178+
"\n"
179+
]
180+
}
181+
],
182+
"metadata": {
183+
"accelerator": "GPU",
184+
"colab": {
185+
"gpuType": "T4",
186+
"provenance": []
187+
},
188+
"kernelspec": {
189+
"display_name": "Python 3",
190+
"name": "python3"
191+
},
192+
"language_info": {
193+
"name": "python"
194+
}
195+
},
196+
"nbformat": 4,
197+
"nbformat_minor": 0
198+
}

0 commit comments

Comments
 (0)