Merge branch 'master' into master

langchain-ai · Apr 24, 2024 · 761e97e · 761e97e
2 parents 72e49cf + 13751c3
commit 761e97e
Show file tree

Hide file tree

Showing 10 changed files with 704 additions and 102 deletions.
diff --git a/docs/docs/integrations/graphs/tigergraph.mdx b/docs/docs/integrations/graphs/tigergraph.mdx
@@ -0,0 +1,37 @@
+# TigerGraph
+
+>[TigerGraph](https://www.tigergraph.com/tigergraph-db/) is a natively distributed and high-performance graph database.
+> The storage of data in a graph format of vertices and edges leads to rich relationships, 
+> ideal for grouding LLM responses.
+ 
+A big example of the `TigerGraph` and `LangChain` integration [presented here](https://github.com/tigergraph/graph-ml-notebooks/blob/main/applications/large_language_models/TigerGraph_LangChain_Demo.ipynb).
+
+## Installation and Setup
+
+Follow instructions [how to connect to the `TigerGraph` database](https://docs.tigergraph.com/pytigergraph/current/getting-started/connection).
+
+Install the Python SDK:
+
+```bash
+pip install pyTigerGraph
+```
+
+## Example
+
+To utilize the `TigerGraph InquiryAI` functionality, you can import `TigerGraph` from `langchain_community.graphs`.
+
+```python
+import pyTigerGraph as tg
+
+conn = tg.TigerGraphConnection(host="DATABASE_HOST_HERE", graphname="GRAPH_NAME_HERE", username="USERNAME_HERE", password="PASSWORD_HERE")
+
+### ==== CONFIGURE INQUIRYAI HOST ====
+conn.ai.configureInquiryAIHost("INQUIRYAI_HOST_HERE")
+
+from langchain_community.graphs import TigerGraph
+
+graph = TigerGraph(conn)
+result = graph.query("How many servers are there?")
+print(result)
+```
+
diff --git a/docs/docs/integrations/llms/predibase.ipynb b/docs/docs/integrations/llms/predibase.ipynb
@@ -63,12 +63,13 @@
    "source": [
     "from langchain_community.llms import Predibase\n",
     "\n",
-    "# With a fine-tuned adapter hosted at Predibase (adapter_version can be specified; omitting it is equivalent to the most recent version).\n",
+    "# With a fine-tuned adapter hosted at Predibase (adapter_version must be specified).\n",
     "model = Predibase(\n",
     "    model=\"mistral-7b\",\n",
+    "    predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\"),\n",
+    "    predibase_sdk_version=None,  # optional parameter (defaults to the latest Predibase SDK version if omitted)\n",
     "    adapter_id=\"e2e_nlg\",\n",
     "    adapter_version=1,\n",
-    "    predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\"),\n",
     ")"
    ]
   },
@@ -83,8 +84,9 @@
     "# With a fine-tuned adapter hosted at HuggingFace (adapter_version does not apply and will be ignored).\n",
     "model = Predibase(\n",
     "    model=\"mistral-7b\",\n",
-    "    adapter_id=\"predibase/e2e_nlg\",\n",
     "    predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\"),\n",
+    "    predibase_sdk_version=None,  # optional parameter (defaults to the latest Predibase SDK version if omitted)\n",
+    "    adapter_id=\"predibase/e2e_nlg\",\n",
     ")"
    ]
   },
@@ -122,7 +124,9 @@
     "from langchain_community.llms import Predibase\n",
     "\n",
     "model = Predibase(\n",
-    "    model=\"mistral-7b\", predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\")\n",
+    "    model=\"mistral-7b\",\n",
+    "    predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\"),\n",
+    "    predibase_sdk_version=None,  # optional parameter (defaults to the latest Predibase SDK version if omitted)\n",
     ")"
    ]
   },
@@ -136,12 +140,13 @@
    },
    "outputs": [],
    "source": [
-    "# With a fine-tuned adapter hosted at Predibase (adapter_version can be specified; omitting it is equivalent to the most recent version).\n",
+    "# With a fine-tuned adapter hosted at Predibase (adapter_version must be specified).\n",
     "model = Predibase(\n",
     "    model=\"mistral-7b\",\n",
+    "    predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\"),\n",
+    "    predibase_sdk_version=None,  # optional parameter (defaults to the latest Predibase SDK version if omitted)\n",
     "    adapter_id=\"e2e_nlg\",\n",
     "    adapter_version=1,\n",
-    "    predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\"),\n",
     ")"
    ]
   },
@@ -154,8 +159,9 @@
     "# With a fine-tuned adapter hosted at HuggingFace (adapter_version does not apply and will be ignored).\n",
     "llm = Predibase(\n",
     "    model=\"mistral-7b\",\n",
-    "    adapter_id=\"predibase/e2e_nlg\",\n",
     "    predibase_api_key=os.environ.get(\"PREDIBASE_API_TOKEN\"),\n",
+    "    predibase_sdk_version=None,  # optional parameter (defaults to the latest Predibase SDK version if omitted)\n",
+    "    adapter_id=\"predibase/e2e_nlg\",\n",
     ")"
    ]
   },
@@ -247,13 +253,14 @@
     "\n",
     "model = Predibase(\n",
     "    model=\"my-base-LLM\",\n",
-    "    adapter_id=\"my-finetuned-adapter-id\",  # Supports both, Predibase-hosted and HuggingFace-hosted model repositories.\n",
-    "    # adapter_version=1,  # optional (returns the latest, if omitted)\n",
     "    predibase_api_key=os.environ.get(\n",
     "        \"PREDIBASE_API_TOKEN\"\n",
     "    ),  # Adapter argument is optional.\n",
+    "    predibase_sdk_version=None,  # optional parameter (defaults to the latest Predibase SDK version if omitted)\n",
+    "    adapter_id=\"my-finetuned-adapter-id\",  # Supports both, Predibase-hosted and HuggingFace-hosted adapter repositories.\n",
+    "    adapter_version=1,  # required for Predibase-hosted adapters (ignored for HuggingFace-hosted adapters)\n",
     ")\n",
-    "# replace my-finetuned-LLM with the name of your model in Predibase"
+    "# replace my-base-LLM with the name of your choice of a serverless base model in Predibase"
    ]
   },
   {

diff --git a/docs/docs/integrations/providers/predibase.md b/docs/docs/integrations/providers/predibase.md
@@ -17,7 +17,11 @@ os.environ["PREDIBASE_API_TOKEN"] = "{PREDIBASE_API_TOKEN}"
 
 from langchain_community.llms import Predibase
 
-model = Predibase(model="mistral-7b"", predibase_api_key=os.environ.get("PREDIBASE_API_TOKEN"))
+model = Predibase(
+    model="mistral-7b",
+    predibase_api_key=os.environ.get("PREDIBASE_API_TOKEN"),
+    predibase_sdk_version=None,  # optional parameter (defaults to the latest Predibase SDK version if omitted)
+)
 
 response = model("Can you recommend me a nice dry wine?")
 print(response)
@@ -31,8 +35,14 @@ os.environ["PREDIBASE_API_TOKEN"] = "{PREDIBASE_API_TOKEN}"
 
 from langchain_community.llms import Predibase
 
-# The fine-tuned adapter is hosted at Predibase (adapter_version can be specified; omitting it is equivalent to the most recent version).
-model =  Predibase(model="mistral-7b"", adapter_id="e2e_nlg", adapter_version=1, predibase_api_key=os.environ.get("PREDIBASE_API_TOKEN"))
+# The fine-tuned adapter is hosted at Predibase (adapter_version must be specified).
+model = Predibase(
+    model="mistral-7b",
+    predibase_api_key=os.environ.get("PREDIBASE_API_TOKEN"),
+    predibase_sdk_version=None,  # optional parameter (defaults to the latest Predibase SDK version if omitted)
+    adapter_id="e2e_nlg",
+    adapter_version=1,
+)
 
 response = model("Can you recommend me a nice dry wine?")
 print(response)
@@ -47,7 +57,12 @@ os.environ["PREDIBASE_API_TOKEN"] = "{PREDIBASE_API_TOKEN}"
 from langchain_community.llms import Predibase
 
 # The fine-tuned adapter is hosted at HuggingFace (adapter_version does not apply and will be ignored).
-model =  Predibase(model="mistral-7b"", adapter_id="predibase/e2e_nlg", predibase_api_key=os.environ.get("PREDIBASE_API_TOKEN"))
+model = Predibase(
+    model="mistral-7b",
+    predibase_api_key=os.environ.get("PREDIBASE_API_TOKEN"),
+    predibase_sdk_version=None,  # optional parameter (defaults to the latest Predibase SDK version if omitted)
+    adapter_id="predibase/e2e_nlg",
+)
 
 response = model("Can you recommend me a nice dry wine?")
 print(response)

diff --git a/docs/docs/integrations/providers/tigergraph.mdx b/docs/docs/integrations/providers/tigergraph.mdx
@@ -1,15 +1,13 @@
 # TigerGraph
 
-What is `TigerGraph`?
-
-**TigerGraph in a nutshell:**
-
-- `TigerGraph` is a natively distributed and high-performance graph database.
-- The storage of data in a graph format of vertices and edges leads to rich relationships, ideal for grouding LLM responses.
-- Get started quickly with `TigerGraph` by visiting [their website](https://tigergraph.com/).
+>[TigerGraph](https://www.tigergraph.com/tigergraph-db/) is a natively distributed and high-performance graph database.
+> The storage of data in a graph format of vertices and edges leads to rich relationships, 
+> ideal for grouding LLM responses.
 
 ## Installation and Setup
 
+Follow instructions [how to connect to the `TigerGraph` database](https://docs.tigergraph.com/pytigergraph/current/getting-started/connection).
+
 Install the Python SDK:
 
 ```bash
@@ -18,22 +16,10 @@ pip install pyTigerGraph
 
 ## Graph store
 
-### TigerGraph Store
+### TigerGraph
 
-To utilize the `TigerGraph InquiryAI` functionality, you can import `TigerGraph` from `langchain_community.graphs`.
+See a [usage example](/docs/integrations/graphs/tigergraph).
 
 ```python
-import pyTigerGraph as tg
-
-conn = tg.TigerGraphConnection(host="DATABASE_HOST_HERE", graphname="GRAPH_NAME_HERE", username="USERNAME_HERE", password="PASSWORD_HERE")
-
-### ==== CONFIGURE INQUIRYAI HOST ====
-conn.ai.configureInquiryAIHost("INQUIRYAI_HOST_HERE")
-
 from langchain_community.graphs import TigerGraph
-
-graph = TigerGraph(conn)
-result = graph.query("How many servers are there?")
-print(result)
 ```
-
diff --git a/docs/docs/integrations/vectorstores/sap_hanavector.ipynb b/docs/docs/integrations/vectorstores/sap_hanavector.ipynb
@@ -357,6 +357,179 @@
     "print(len(docs))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Advanced filtering\n",
+    "In addition to the basic value-based filtering capabilities, it is possible to use more advanced filtering.\n",
+    "The table below shows the available filter operators.\n",
+    "\n",
+    "| Operator | Semantic                 |\n",
+    "|----------|-------------------------|\n",
+    "| `$eq`    | Equality (==)           |\n",
+    "| `$ne`    | Inequality (!=)         |\n",
+    "| `$lt`    | Less than (<)           |\n",
+    "| `$lte`   | Less than or equal (<=) |\n",
+    "| `$gt`    | Greater than (>)        |\n",
+    "| `$gte`   | Greater than or equal (>=) |\n",
+    "| `$in`    | Contained in a set of given values  (in)    |\n",
+    "| `$nin`   | Not contained in a set of given values  (not in)  |\n",
+    "| `$between` | Between the range of two boundary values |\n",
+    "| `$like`  | Text equality based on the \"LIKE\" semantics in SQL (using \"%\" as wildcard)  |\n",
+    "| `$and`   | Logical \"and\", supporting 2 or more operands |\n",
+    "| `$or`    | Logical \"or\", supporting 2 or more operands |"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Prepare some test documents\n",
+    "docs = [\n",
+    "    Document(\n",
+    "        page_content=\"First\",\n",
+    "        metadata={\"name\": \"adam\", \"is_active\": True, \"id\": 1, \"height\": 10.0},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"Second\",\n",
+    "        metadata={\"name\": \"bob\", \"is_active\": False, \"id\": 2, \"height\": 5.7},\n",
+    "    ),\n",
+    "    Document(\n",
+    "        page_content=\"Third\",\n",
+    "        metadata={\"name\": \"jane\", \"is_active\": True, \"id\": 3, \"height\": 2.4},\n",
+    "    ),\n",
+    "]\n",
+    "\n",
+    "db = HanaDB(\n",
+    "    connection=connection,\n",
+    "    embedding=embeddings,\n",
+    "    table_name=\"LANGCHAIN_DEMO_ADVANCED_FILTER\",\n",
+    ")\n",
+    "\n",
+    "# Delete already existing documents from the table\n",
+    "db.delete(filter={})\n",
+    "db.add_documents(docs)\n",
+    "\n",
+    "\n",
+    "# Helper function for printing filter results\n",
+    "def print_filter_result(result):\n",
+    "    if len(result) == 0:\n",
+    "        print(\"<empty result>\")\n",
+    "    for doc in result:\n",
+    "        print(doc.metadata)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Filtering with `$ne`, `$gt`, `$gte`, `$lt`, `$lte`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "advanced_filter = {\"id\": {\"$ne\": 1}}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))\n",
+    "\n",
+    "advanced_filter = {\"id\": {\"$gt\": 1}}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))\n",
+    "\n",
+    "advanced_filter = {\"id\": {\"$gte\": 1}}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))\n",
+    "\n",
+    "advanced_filter = {\"id\": {\"$lt\": 1}}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))\n",
+    "\n",
+    "advanced_filter = {\"id\": {\"$lte\": 1}}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Filtering with `$between`, `$in`, `$nin`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "advanced_filter = {\"id\": {\"$between\": (1, 2)}}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))\n",
+    "\n",
+    "advanced_filter = {\"name\": {\"$in\": [\"adam\", \"bob\"]}}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))\n",
+    "\n",
+    "advanced_filter = {\"name\": {\"$nin\": [\"adam\", \"bob\"]}}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Text filtering with `$like`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "advanced_filter = {\"name\": {\"$like\": \"a%\"}}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))\n",
+    "\n",
+    "advanced_filter = {\"name\": {\"$like\": \"%a%\"}}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Combined filtering with `$and`, `$or`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "advanced_filter = {\"$or\": [{\"id\": 1}, {\"name\": \"bob\"}]}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))\n",
+    "\n",
+    "advanced_filter = {\"$and\": [{\"id\": 1}, {\"id\": 2}]}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))\n",
+    "\n",
+    "advanced_filter = {\"$or\": [{\"id\": 1}, {\"id\": 2}, {\"id\": 3}]}\n",
+    "print(f\"Filter: {advanced_filter}\")\n",
+    "print_filter_result(db.similarity_search(\"just testing\", k=5, filter=advanced_filter))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},