Skip to content

Commit

Permalink
Milvus load and guide fix (#3378)
Browse files Browse the repository at this point in the history 
Signed-off-by: Filip Haltmayer <[email protected]>
  • Loading branch information
@filip-halt
filip-halt authored May 15, 2023
1 parent 8ae9fa8 commit afbeacf
Show file tree
Hide file tree
Showing 2 changed files with 46 additions and 145 deletions.
188 changes: 43 additions & 145 deletions docs/examples/vector_stores/MilvusIndexDemo.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -109,13 +109,13 @@
"name": "stdout",
"output_type": "stream",
"text": [
"Document ID: 933666c4-2833-475a-a3d5-d279a0c174fa Document Hash: 77ae91ab542f3abb308c4d7c77c9bc4c9ad0ccd63144802b7cbe7e1bb3a4094e\n"
"Document ID: 05b6691b-d567-43a2-94e1-e9ca81cd4624 Document Hash: 77ae91ab542f3abb308c4d7c77c9bc4c9ad0ccd63144802b7cbe7e1bb3a4094e\n"
]
}
],
"source": [
"# load documents\n",
"documents = SimpleDirectoryReader('../paul_graham_essay/data').load_data()\n",
"documents = SimpleDirectoryReader('../data/paul_graham/').load_data()\n",
"print('Document ID:', documents[0].doc_id, 'Document Hash:', documents[0].doc_hash)"
]
},
Expand Down Expand Up @@ -153,16 +153,7 @@
"is_executing": true
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total LLM token usage: 0 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total embedding token usage: 17617 tokens\n"
]
}
],
"outputs": [],
"source": [
"# Create an index over the documnts\n",
"from llama_index.storage.storage_context import StorageContext\n",
Expand Down Expand Up @@ -193,101 +184,47 @@
"start_time": "2023-02-10T12:20:33.822688Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:llama_index.token_counter.token_counter:> [query] Total LLM token usage: 4028 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [query] Total embedding token usage: 6 tokens\n"
]
}
],
"source": [
"query_engine = index.as_query_engine()\n",
"response = query_engine.query(\"What did the author learn?\")"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "bedbb693-725f-478f-be26-fa7180ea38b2",
"metadata": {
"ExecuteTime": {
"end_time": "2023-02-10T12:20:51.337062Z",
"start_time": "2023-02-10T12:20:51.330857Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" The author learned that working on things that are not prestigious can be a good thing, as it can\n",
"lead to discovering something real and avoiding the wrong track. The author also learned that\n",
"ignorance can be beneficial, as it can lead to discovering something new and unexpected. The author\n",
"also learned the importance of working hard, even at the parts of the job they don't like, in order\n",
"to set an example for others. The author also learned the value of unsolicited advice, as it can be\n",
"beneficial in unexpected ways, such as when Robert Morris suggested that the author should make sure\n",
"Y Combinator wasn't the last cool thing they did.\n"
" The author learned that the AI programs of the time were not capable of understanding natural\n",
"language, and that the field of AI was a hoax. He also learned that he could make art, and that he\n",
"could pass the entrance exam for the Accademia di Belli Arti in Florence. He also learned Lisp\n",
"hacking and wrote his dissertation on applications of continuations.\n"
]
}
],
"source": [
"query_engine = index.as_query_engine()\n",
"response = query_engine.query(\"What did the author learn?\")\n",
"print(textwrap.fill(str(response), 100))"
]
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 6,
"id": "99212d33",
"metadata": {
"ExecuteTime": {
"end_time": "2023-02-10T12:21:10.337294Z",
"start_time": "2023-02-10T12:20:51.338718Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:llama_index.token_counter.token_counter:> [query] Total LLM token usage: 4072 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [query] Total embedding token usage: 9 tokens\n"
]
}
],
"source": [
"response = query_engine.query(\"What was a hard moment for the author?\")"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "1a720ad6",
"metadata": {
"ExecuteTime": {
"end_time": "2023-02-10T12:21:10.355872Z",
"start_time": "2023-02-10T12:21:10.343486Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" A hard moment for the author was when he was dealing with urgent problems during YC and about 60%\n",
"of them had to do with Hacker News, a news aggregator he had created. He was overwhelmed by the\n",
"amount of work he had to do to keep Hacker News running, and it was taking away from his ability to\n",
"focus on other projects. He was also haunted by the idea that his own work ethic set the upper bound\n",
"for how hard everyone else worked, so he felt he had to work very hard. He was also dealing with\n",
"disputes between cofounders, figuring out when people were lying to them, and fighting with people\n",
"who maltreated the startups. On top of this, he was given unsolicited advice from Robert Morris to\n",
"make sure Y Combinator wasn't the last cool thing he did, which made him consider quitting.\n"
" A hard moment for the author was when he realized that the AI programs of the time were a hoax and\n",
"that there was an unbridgeable gap between what they could do and actually understanding natural\n",
"language.\n"
]
}
],
"source": [
"response = query_engine.query(\"What was a hard moment for the author?\")\n",
"print(textwrap.fill(str(response), 100))"
]
},
Expand All @@ -302,25 +239,14 @@
},
{
"cell_type": "code",
"execution_count": 15,
"execution_count": 7,
"id": "8d641e24",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total LLM token usage: 0 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total embedding token usage: 5 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [query] Total LLM token usage: 44 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [query] Total embedding token usage: 5 tokens\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Res: \n",
"The author is unknown.\n"
]
Expand All @@ -329,12 +255,10 @@
"source": [
"vector_store = MilvusVectorStore(overwrite=True)\n",
"storage_context = StorageContext.from_defaults(vector_store=vector_store)\n",
"index = GPTVectorStoreIndex.from_documents([Document(\"The answer is ten.\")], storage_context)\n",
"index = GPTVectorStoreIndex.from_documents([Document(\"The number that is being searched for is ten.\")], storage_context)\n",
"query_engine = index.as_query_engine()\n",
"res = query_engine.query(\"Who is the author?\")\n",
"\n",
"print(flush=True)\n",
"print(\"Res:\", res, flush=True)"
"print(\"Res:\", res)"
]
},
{
Expand All @@ -348,74 +272,48 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 8,
"id": "a5c429a4",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:llama_index.token_counter.token_counter:> [query] Total LLM token usage: 44 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [query] Total embedding token usage: 5 tokens\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"The answer is ten.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total LLM token usage: 0 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total embedding token usage: 17617 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [query] Total LLM token usage: 41 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [query] Total embedding token usage: 5 tokens\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"Ten.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:llama_index.token_counter.token_counter:> [query] Total LLM token usage: 3720 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [query] Total embedding token usage: 5 tokens\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"The author of the text is Paul Graham, co-founder of Y Combinator.\n"
"Res: \n",
"The number is ten.\n"
]
}
],
"source": [
"del index\n",
"\n",
"query_engine = index.as_query_engine()\n",
"print(query_engine.query(\"What is the answer.\"))\n",
"del index, vector_store, storage_context, query_engine\n",
"\n",
"vector_store = MilvusVectorStore(overwrite=False)\n",
"storage_context = StorageContext.from_defaults(vector_store=vector_store)\n",
"index = GPTVectorStoreIndex.from_documents(documents, storage_context=storage_context)\n",
"query_engine = index.as_query_engine()\n",
"print(query_engine.query(\"What is the answer?\"))\n",
"print(query_engine.query(\"Who is the author?\"))\n"
"res = query_engine.query(\"What is the number?\")\n",
"print(\"Res:\", res)"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "e5287c2d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Res: \n",
"The author is Paul Graham.\n"
]
}
],
"source": [
"res = query_engine.query(\"Who is the author?\")\n",
"print(\"Res:\", res)"
]
}
],
Expand Down
3 changes: 3 additions & 0 deletions llama_index/vector_stores/milvus.py
View file
Original file line number Diff line number Diff line change
Expand Up @@ -310,6 +310,9 @@ def add(self, embedding_results: List[NodeWithEmbedding]) -> List[str]:
assert self.collection is not None
self.collection.load()

elif len(embedding_results) == 0:
return []

ids = []
doc_ids = []
texts = []
Expand Down

0 comments on commit afbeacf

Please sign in to comment.