Skip to content

updates for 0.4.0 #6937

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jul 18, 2023
Merged

updates for 0.4.0 #6937

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
63d99a3
updates for 0.4.0
jeffchuber Jul 16, 2023
6098095
changelog
logan-markewich Jul 18, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@
### New Features
- specify `embed_model="local"` to use default local embbeddings in the service context (#6806)
- Add async `acall` endpoint to `BasePydanticProgram` (defaults to sync version). Implement for `OpenAIPydanticProgram`
- Add support for chroma v0.4.0 (#6937)

### Bug Fixes / Nits
- fix null metadata for searching existing vector dbs (#6912)
Expand Down
4 changes: 2 additions & 2 deletions docs/community/integrations/vector_stores.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -207,8 +207,8 @@ import chromadb
from llama_index.vector_stores import ChromaVectorStore

# Creating a Chroma client
# By default, Chroma will operate purely in-memory.
chroma_client = chromadb.Client()
# EphemeralClient operates purely in-memory, PersistentClient will also save to disk
chroma_client = chromadb.EphemeralClient()
chroma_collection = chroma_client.create_collection("quickstart")

# construct vector store
Expand Down
102 changes: 30 additions & 72 deletions docs/examples/vector_stores/ChromaIndexDemo.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,20 +70,20 @@
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 1,
"id": "b3df0b97",
"metadata": {},
"outputs": [],
"source": [
"!pip install llama-index\n",
"!pip install chromadb\n",
"!pip install sentence-transformers\n",
"!pip install pydantic==1.10.11"
"# !pip install llama-index chromadb --quiet\n",
"# !pip install chromadb\n",
"# !pip install sentence-transformers\n",
"# !pip install pydantic==1.10.11"
]
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 2,
"id": "d48af8e1",
"metadata": {},
"outputs": [],
Expand All @@ -100,7 +100,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 3,
"id": "374a148b",
"metadata": {},
"outputs": [],
Expand All @@ -117,10 +117,18 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 4,
"id": "667f3cb3-ce18-48d5-b9aa-bfc1a1f0f0f6",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/jeff/.pyenv/versions/3.10.10/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
},
{
"data": {
"text/markdown": [
Expand All @@ -137,7 +145,7 @@
],
"source": [
"# create client and a new collection\n",
"chroma_client = chromadb.Client()\n",
"chroma_client = chromadb.EphemeralClient()\n",
"chroma_collection = chroma_client.create_collection(\"quickstart\")\n",
"\n",
"# define embedding function\n",
Expand Down Expand Up @@ -174,22 +182,20 @@
"\n",
"Extending the previous example, if you want to save to disk, simply initialize the Chroma client and pass the directory where you want the data to be saved to. \n",
"\n",
"`Caution`: Chroma makes a best-effort to automatically save data to disk, however multiple in-memory clients can stomp each other's work. As a best practice, only have one client per path running at any given time.\n",
"\n",
"`Protip`: Sometimes you can call `db.persist()` to force a save. "
"`Caution`: Chroma makes a best-effort to automatically save data to disk, however multiple in-memory clients can stomp each other's work. As a best practice, only have one client per path running at any given time."
]
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 5,
"id": "9c3a56a5",
"metadata": {},
"outputs": [
{
"data": {
"text/markdown": [
"<b>\n",
"Growing up, the author wrote short stories, programmed on an IBM 1401, and wrote programs on a TRS-80 microcomputer. He also took painting classes at Harvard and worked as a de facto studio assistant for a painter. He also tried to start a company to put art galleries online, and wrote software to build online stores.</b>"
"The author grew up taking painting classes at Harvard and freelancing as a Lisp hacker. He also wrote a book on Lisp and moved to New York to be closer to his teacher, Idelle Weber.</b>"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
Expand All @@ -201,24 +207,18 @@
],
"source": [
"# save to disk\n",
"from chromadb.config import Settings\n",
"\n",
"db = chromadb.Client(\n",
" Settings(chroma_db_impl=\"duckdb+parquet\", persist_directory=\"./chroma_db\")\n",
")\n",
"db = chromadb.PersistentClient(path=\"./chroma_db\")\n",
"chroma_collection = db.get_or_create_collection(\"quickstart\")\n",
"vector_store = ChromaVectorStore(chroma_collection=chroma_collection)\n",
"storage_context = StorageContext.from_defaults(vector_store=vector_store)\n",
"service_context = ServiceContext.from_defaults(embed_model=embed_model)\n",
"index = VectorStoreIndex.from_documents(\n",
" documents, storage_context=storage_context, service_context=service_context\n",
")\n",
"db.persist()\n",
"\n",
"# load from disk\n",
"db2 = chromadb.Client(\n",
" Settings(chroma_db_impl=\"duckdb+parquet\", persist_directory=\"./chroma_db\")\n",
")\n",
"db2 = chromadb.PersistentClient(path=\"./chroma_db\")\n",
"chroma_collection = db2.get_or_create_collection(\"quickstart\")\n",
"vector_store = ChromaVectorStore(chroma_collection=chroma_collection)\n",
"storage_context = StorageContext.from_defaults(vector_store=vector_store)\n",
Expand Down Expand Up @@ -253,39 +253,15 @@
},
{
"cell_type": "code",
"execution_count": 43,
"execution_count": 6,
"id": "d6c9bd64",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"INFO:chromadb.telemetry.posthog:Anonymized telemetry enabled. See https://docs.trychroma.com/telemetry for more information.\n",
"Anonymized telemetry enabled. See https://docs.trychroma.com/telemetry for more information.\n",
"Anonymized telemetry enabled. See https://docs.trychroma.com/telemetry for more information.\n",
"INFO:llama_index.token_counter.token_counter:> [build_index_from_nodes] Total LLM token usage: 0 tokens\n",
"> [build_index_from_nodes] Total LLM token usage: 0 tokens\n",
"> [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: 17038 tokens\n",
"> [build_index_from_nodes] Total embedding token usage: 17038 tokens\n",
"> [build_index_from_nodes] Total embedding token usage: 17038 tokens\n"
]
}
],
"outputs": [],
"source": [
"# create the chroma client and add our data\n",
"import chromadb\n",
"from chromadb.config import Settings\n",
"\n",
"remote_db = chromadb.Client(\n",
" Settings(\n",
" chroma_api_impl=\"rest\",\n",
" chroma_server_host=\"localhost\",\n",
" chroma_server_http_port=\"8000\",\n",
" )\n",
")\n",
"remote_db.reset() # resets the database\n",
"remote_db = chromadb.HttpClient()\n",
"chroma_collection = remote_db.get_or_create_collection(\"quickstart\")\n",
"vector_store = ChromaVectorStore(chroma_collection=chroma_collection)\n",
"storage_context = StorageContext.from_defaults(vector_store=vector_store)\n",
Expand All @@ -297,33 +273,15 @@
},
{
"cell_type": "code",
"execution_count": 44,
"execution_count": 7,
"id": "88e10c26",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"INFO:llama_index.token_counter.token_counter:> [retrieve] Total LLM token usage: 0 tokens\n",
"> [retrieve] Total LLM token usage: 0 tokens\n",
"> [retrieve] Total LLM token usage: 0 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [retrieve] Total embedding token usage: 8 tokens\n",
"> [retrieve] Total embedding token usage: 8 tokens\n",
"> [retrieve] Total embedding token usage: 8 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [get_response] Total LLM token usage: 1874 tokens\n",
"> [get_response] Total LLM token usage: 1874 tokens\n",
"> [get_response] Total LLM token usage: 1874 tokens\n",
"INFO:llama_index.token_counter.token_counter:> [get_response] Total embedding token usage: 0 tokens\n",
"> [get_response] Total embedding token usage: 0 tokens\n",
"> [get_response] Total embedding token usage: 0 tokens\n"
]
},
{
"data": {
"text/markdown": [
"<b>\n",
"The author grew up writing essays, learning Italian, exploring Florence, painting people, working with computers, studying at RISD, living in a rent-controlled apartment, building an online store builder, editing code, publishing essays online, writing essays, working on spam filters, cooking for groups, buying a building, and attending parties.</b>"
"Growing up, the author wrote short stories, programmed on an IBM 1401, and wrote programs on a TRS-80 microcomputer. He also took painting classes at Harvard and worked as a de facto studio assistant for a painter. He also tried to start a company to put art galleries online, and wrote software to build online stores.</b>"
],
"text/plain": [
"<IPython.core.display.Markdown object>"
Expand Down Expand Up @@ -357,15 +315,15 @@
},
{
"cell_type": "code",
"execution_count": 60,
"execution_count": 8,
"id": "d9411826",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"{'node_info': '{\"start\": 0, \"end\": 4040, \"_node_type\": \"1\"}', 'relationships': '{\"1\": \"a0294b91-ff5f-45fe-b249-5596a18cc952\", \"3\": \"95771df1-9ec9-4128-9a11-ac92b768e2e3\"}', 'document_id': 'a0294b91-ff5f-45fe-b249-5596a18cc952', 'doc_id': 'a0294b91-ff5f-45fe-b249-5596a18cc952', 'ref_doc_id': 'a0294b91-ff5f-45fe-b249-5596a18cc952', 'author': 'Paul Graham'}\n",
"{'_node_content': '{\"id_\": \"be08c8bc-f43e-4a71-ba64-e525921a8319\", \"embedding\": null, \"metadata\": {}, \"excluded_embed_metadata_keys\": [], \"excluded_llm_metadata_keys\": [], \"relationships\": {\"1\": {\"node_id\": \"2cbecdbb-0840-48b2-8151-00119da0995b\", \"node_type\": null, \"metadata\": {}, \"hash\": \"4c702b4df575421e1d1af4b1fd50511b226e0c9863dbfffeccb8b689b8448f35\"}, \"3\": {\"node_id\": \"6a75604a-fa76-4193-8f52-c72a7b18b154\", \"node_type\": null, \"metadata\": {}, \"hash\": \"d6c408ee1fbca650fb669214e6f32ffe363b658201d31c204e85a72edb71772f\"}}, \"hash\": \"b4d0b960aa09e693f9dc0d50ef46a3d0bf5a8fb3ac9f3e4bcf438e326d17e0d8\", \"text\": \"\", \"start_char_idx\": 0, \"end_char_idx\": 4050, \"text_template\": \"{metadata_str}\\\\n\\\\n{content}\", \"metadata_template\": \"{key}: {value}\", \"metadata_seperator\": \"\\\\n\"}', 'author': 'Paul Graham', 'doc_id': '2cbecdbb-0840-48b2-8151-00119da0995b', 'document_id': '2cbecdbb-0840-48b2-8151-00119da0995b', 'ref_doc_id': '2cbecdbb-0840-48b2-8151-00119da0995b'}\n",
"count before 20\n",
"count after 19\n"
]
Expand Down Expand Up @@ -406,7 +364,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.6"
"version": "3.10.10"
},
"vscode": {
"interpreter": {
Expand Down
Loading