The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
Added docs for add-v2 (#2381)
Prateek Chhikara954583646923
diff --git a/docs/docs.json b/docs/docs.jsonindex 4cd8f3c6a..6168a36a0 100644--- a/docs/docs.json+++ b/docs/docs.json@@ -47,6 +47,7 @@"pages": ["features/platform-overview","features/advanced-retrieval",+ "features/contextual-add","features/multimodal-support","features/selective-memory","features/custom-categories",diff --git a/docs/features/contextual-add.mdx b/docs/features/contextual-add.mdxnew file mode 100644index 000000000..846e2232d--- /dev/null+++ b/docs/features/contextual-add.mdx@@ -0,0 +1,205 @@+---+title: Contextual Add (ADD v2)+icon: "square-plus"+iconType: "solid"+---++Mem0 now supports an contextual add version (v2). To use it, set `version="v2"` during the add call. The default version is v1, which is deprecated now. We recommend migrating to `v2` for new applications.++## Key Differences Between v1 and v2++### Version 1 (Legacy)+In v1 (default), users needed to pass either the entire conversation history or past k messages with each new message to generate properly contextualized memories. This approach required:++- Manually tracking and sending previous messages using a sliding window approach+- Increased payload sizes as conversations grew longer, requiring careful window size management++<CodeGroup>++```python Python+# First interaction+messages1 = [+ {"role": "user", "content": "Hi, I'm Alex and I live in San Francisco."},+ {"role": "assistant", "content": "Hello Alex! Nice to meet you. San Francisco is a beautiful city."}+]+client.add(messages1, user_id="alex")++# Second interaction - must include previous messages for context+messages2 = [+ {"role": "user", "content": "Hi, I'm Alex and I live in San Francisco."},+ {"role": "assistant", "content": "Hello Alex! Nice to meet you. San Francisco is a beautiful city."},+ {"role": "user", "content": "I like to eat sushi, and yesterday I went to Sunnyvale to eat sushi with my friends."},+ {"role": "assistant", "content": "Sushi is really a tasty choice. What did you do this weekend?"}+]+client.add(messages2, user_id="alex")+```++```javascript JavaScript+// First interaction+const messages1 = [+ {"role": "user", "content": "Hi, I'm Alex and I live in San Francisco."},+ {"role": "assistant", "content": "Hello Alex! Nice to meet you. San Francisco is a beautiful city."}+];+client.add(messages1, { user_id: "alex" })+ .then(response => console.log(response))+ .catch(error => console.error(error));++// Second interaction - must include previous messages for context+const messages2 = [+ {"role": "user", "content": "Hi, I'm Alex and I live in San Francisco."},+ {"role": "assistant", "content": "Hello Alex! Nice to meet you. San Francisco is a beautiful city."},+ {"role": "user", "content": "I like to eat sushi, and yesterday I went to Sunnyvale to eat sushi with my friends."},+ {"role": "assistant", "content": "Sushi is really a tasty choice. What did you do this weekend?"}+];+client.add(messages2, { user_id: "alex" })+ .then(response => console.log(response))+ .catch(error => console.error(error));+```++</CodeGroup>++### Version 2 (Recommended)+In v2, Mem0 automatically manages conversation context. Users only need to send new messages, and the system will:++- Automatically retrieve relevant conversation history+- Generate properly contextualized memories+- Reduce payload sizes and simplify integration++<CodeGroup>++```python Python+# First interaction+messages1 = [+ {"role": "user", "content": "Hi, I'm Alex and I live in San Francisco."},+ {"role": "assistant", "content": "Hello Alex! Nice to meet you. San Francisco is a beautiful city."}+]+client.add(messages1, user_id="alex", version="v2")++# Second interaction - only need to send new messages+messages2 = [+ {"role": "user", "content": "I like to eat sushi, and yesterday I went to Sunnyvale to eat sushi with my friends."},+ {"role": "assistant", "content": "Sushi is really a tasty choice. What did you do this weekend?"}+]+client.add(messages2, user_id="alex", version="v2")+```++```javascript JavaScript+// First interaction+const messages1 = [+ {"role": "user", "content": "Hi, I'm Alex and I live in San Francisco."},+ {"role": "assistant", "content": "Hello Alex! Nice to meet you. San Francisco is a beautiful city."}+];+client.add(messages1, { user_id: "alex", version: "v2" })+ .then(response => console.log(response))+ .catch(error => console.error(error));++// Second interaction - only need to send new messages+const messages2 = [+ {"role": "user", "content": "I like to eat sushi, and yesterday I went to Sunnyvale to eat sushi with my friends."},+ {"role": "assistant", "content": "Sushi is really a tasty choice. What did you do this weekend?"}+];+client.add(messages2, { user_id: "alex", version: "v2" })+ .then(response => console.log(response))+ .catch(error => console.error(error));+```++</CodeGroup>++## Benefits of Using v2++1. **Simplified Integration**: No need to track and manage conversation history+2. **Reduced Payload Size**: Only send new messages, not the entire conversation+3. **Improved Memory Quality**: Automatic context retrieval ensures better memory generation++## Understanding ID Parameters in v2++When using contextual add v2, you have different options for how to organize and retrieve memories:++### Using Only `user_id`++When you provide only a `user_id`:++- Memories are associated with this user's long-term memory store+- The system will automatically retrieve relevant context from all of the user's previous conversations+- These memories persist indefinitely across all of the user's sessions+- Ideal for maintaining persistent user information (preferences, personal details, etc.)++<CodeGroup>++```python Python+# Adding to long-term user memory+messages = [+ {"role": "user", "content": "I'm allergic to peanuts and shellfish."},+ {"role": "assistant", "content": "I've noted your allergies to peanuts and shellfish."}+]+client.add(messages, user_id="alex", version="v2")+```++```javascript JavaScript+// Adding to long-term user memory+const messages = [+ {"role": "user", "content": "I'm allergic to peanuts and shellfish."},+ {"role": "assistant", "content": "I've noted your allergies to peanuts and shellfish."}+];+client.add(messages, { user_id: "alex", version: "v2" })+ .then(response => console.log(response))+ .catch(error => console.error(error));+```++</CodeGroup>++### Using `user_id` with `run_id`++When you provide both `user_id` and `run_id`:++- Memories are associated with a specific conversation session or interaction+- The system will retrieve context primarily from this specific session+- These memories are still tied to the user but are organized by the specific session+- Ideal for maintaining context within a specific conversation flow or task+- Helps prevent context from different conversations from interfering with each other++<CodeGroup>++```python Python+# Adding to a specific conversation session+messages = [+ {"role": "user", "content": "For this trip to Paris, I want to focus on art museums."},+ {"role": "assistant", "content": "Great! I'll help you plan your Paris trip with a focus on art museums."}+]+client.add(messages, user_id="alex", run_id="paris-trip-2024", version="v2")++# Later in the same conversation session+messages2 = [+ {"role": "user", "content": "I'd like to visit the Louvre on Monday."},+ {"role": "assistant", "content": "The Louvre is a great choice for Monday. Would you like information about opening hours?"}+]+client.add(messages2, user_id="alex", run_id="paris-trip-2024", version="v2")+```++```javascript JavaScript+// Adding to a specific conversation session+const messages = [+ {"role": "user", "content": "For this trip to Paris, I want to focus on art museums."},+ {"role": "assistant", "content": "Great! I'll help you plan your Paris trip with a focus on art museums."}+];+client.add(messages, { user_id: "alex", run_id: "paris-trip-2024", version: "v2" })+ .then(response => console.log(response))+ .catch(error => console.error(error));++// Later in the same conversation session+const messages2 = [+ {"role": "user", "content": "I'd like to visit the Louvre on Monday."},+ {"role": "assistant", "content": "The Louvre is a great choice for Monday. Would you like information about opening hours?"}+];+client.add(messages2, { user_id: "alex", run_id: "paris-trip-2024", version: "v2" })+ .then(response => console.log(response))+ .catch(error => console.error(error));+```++</CodeGroup>++Using `run_id` helps you organize memories into logical sessions or tasks, making it easier to maintain context for specific interactions while still associating everything with the user's overall profile.++If you have any questions, please feel free to reach out to us using one of the following methods:++<Snippet file="get-help.mdx" />\ No newline at end of filediff --git a/docs/features/platform-overview.mdx b/docs/features/platform-overview.mdxindex 6cb86d387..e5280d265 100644--- a/docs/features/platform-overview.mdx+++ b/docs/features/platform-overview.mdx@@ -12,6 +12,9 @@ Learn about the key features and capabilities that make Mem0 a powerful platform<Card title="Advanced Retrieval" icon="magnifying-glass" href="/features/advanced-retrieval">Superior search results using state-of-the-art algorithms, including keyword search, reranking, and filtering capabilities.</Card>+ <Card title="Contextual Add" icon="square-plus" href="/features/contextual-add">+ Only send your latest conversation history - we automatically retrieve the rest and generate properly contextualized memories.+ </Card><Card title="Multimodal Support" icon="photo-film" href="/features/multimodal-support">Process and analyze various types of content including images.</Card>diff --git a/docs/integrations/langchain-tools.mdx b/docs/integrations/langchain-tools.mdxindex 5c0216611..62b3b0d71 100644--- a/docs/integrations/langchain-tools.mdx+++ b/docs/integrations/langchain-tools.mdx@@ -95,7 +95,7 @@ add_input = {{"role": "user", "content": "Hi, I'm Alex. I'm a vegetarian and I'm allergic to nuts."},{"role": "assistant", "content": "Hello Alex! I've noted that you're a vegetarian and have a nut allergy."}],- "user_id": "alex123",+ "user_id": "alex","output_format": "v1.1","metadata": {"food": "vegan"}}@@ -173,7 +173,7 @@ search_input = {"filters": {"AND": [{"created_at": {"gte": "2024-07-20", "lte": "2024-12-10"}},- {"user_id": "alex123"}+ {"user_id": "alex"}]},"version": "v2"@@ -186,7 +186,7 @@ result = search_tool.invoke(search_input){"id": "1a75e827-7eca-45ea-8c5c-cfd43299f061","memory": "Name is Alex",- "user_id": "alex123",+ "user_id": "alex","hash": "d0fccc8fa47f7a149ee95750c37bb0ca","metadata": {"food": "vegan"@@ -255,7 +255,7 @@ get_all_input = {"version": "v2","filters": {"AND": [- {"user_id": "alex123"},+ {"user_id": "alex"},{"created_at": {"gte": "2024-07-01", "lte": "2024-12-31"}}]},@@ -274,7 +274,7 @@ get_all_result = get_all_tool.invoke(get_all_input){"id": "1a75e827-7eca-45ea-8c5c-cfd43299f061","memory": "Name is Alex",- "user_id": "alex123",+ "user_id": "alex","hash": "d0fccc8fa47f7a149ee95750c37bb0ca","metadata": {"food": "vegan"@@ -288,7 +288,7 @@ get_all_result = get_all_tool.invoke(get_all_input){"id": "91509588-0b39-408a-8df3-84b3bce8c521","memory": "Is a vegetarian",- "user_id": "alex123",+ "user_id": "alex","hash": "ce6b1c84586772ab9995a9477032df99","metadata": {"food": "vegan"@@ -303,7 +303,7 @@ get_all_result = get_all_tool.invoke(get_all_input){"id": "8d74f7a0-6107-4589-bd6f-210f6bf4fbbb","memory": "Is allergic to nuts",- "user_id": "alex123",+ "user_id": "alex","hash": "7873cd0e5a29c513253d9fad038e758b","metadata": {"food": "vegan"diff --git a/docs/openapi.json b/docs/openapi.jsonindex 4443ffb3f..4a7213a5c 100644--- a/docs/openapi.json+++ b/docs/openapi.json@@ -932,27 +932,27 @@"x-code-samples": [{"lang": "Python",- "source": "# To use the Python SDK, install the package:\n# pip install mem0ai\n\nfrom mem0 import MemoryClient\n\nclient = MemoryClient(api_key=\"your_api_key\", org_id=\"your_org_id\", project_id=\"your_project_id\")\n\nmessages = [\n {\"role\": \"user\", \"content\": \"<user-message>\"},\n {\"role\": \"assistant\", \"content\": \"<assistant-response>\"}\n]\n\nclient.add(messages, user_id=\"<user-id>\")"+ "source": "# To use the Python SDK, install the package:\n# pip install mem0ai\n\nfrom mem0 import MemoryClient\n\nclient = MemoryClient(api_key=\"your_api_key\", org_id=\"your_org_id\", project_id=\"your_project_id\")\n\nmessages = [\n {\"role\": \"user\", \"content\": \"<user-message>\"},\n {\"role\": \"assistant\", \"content\": \"<assistant-response>\"}\n]\n\nclient.add(messages, user_id=\"<user-id>\", version=\"v2\")"},{"lang": "JavaScript",- "source": "// To use the JavaScript SDK, install the package:\n// npm i mem0ai\n\nimport MemoryClient from 'mem0ai';\nconst client = new MemoryClient({ apiKey: \"your-api-key\" });\n\nconst messages = [\n { role: \"user\", content: \"Hi, I'm Alex. I'm a vegetarian and I'm allergic to nuts.\" },\n { role: \"assistant\", content: \"Hello Alex! I've noted that you're a vegetarian and have a nut allergy. I'll keep this in mind for any food-related recommendations or discussions.\" }\n];\n\nclient.add(messages, { user_id: \"<user_id>\" })\n .then(result => console.log(result))\n .catch(error => console.error(error));"+ "source": "// To use the JavaScript SDK, install the package:\n// npm i mem0ai\n\nimport MemoryClient from 'mem0ai';\nconst client = new MemoryClient({ apiKey: \"your-api-key\" });\n\nconst messages = [\n { role: \"user\", content: \"Hi, I'm Alex. I'm a vegetarian and I'm allergic to nuts.\" },\n { role: \"assistant\", content: \"Hello Alex! I've noted that you're a vegetarian and have a nut allergy. I'll keep this in mind for any food-related recommendations or discussions.\" }\n];\n\nclient.add(messages, { user_id: \"<user_id>\", version: \"v2\" })\n .then(result => console.log(result))\n .catch(error => console.error(error));"},{"lang": "cURL",- "source": "curl --request POST \\\n --url https://api.mem0.ai/v1/memories/ \\\n --header 'Authorization: Token <api-key>' \\\n --header 'Content-Type: application/json' \\\n --data '{\n \"messages\": [\n {}\n ],\n \"agent_id\": \"<string>\",\n \"user_id\": \"<string>\",\n \"app_id\": \"<string>\",\n \"run_id\": \"<string>\",\n \"metadata\": {},\n \"includes\": \"<string>\",\n \"excludes\": \"<string>\",\n \"infer\": true,\n \"custom_categories\": {}, \n \"org_id\": \"<string>\",\n \"project_id\": \"<string>\"\n}'"+ "source": "curl --request POST \\\n --url https://api.mem0.ai/v1/memories/ \\\n --header 'Authorization: Token <api-key>' \\\n --header 'Content-Type: application/json' \\\n --data '{\n \"messages\": [\n {}\n ],\n \"agent_id\": \"<string>\",\n \"user_id\": \"<string>\",\n \"app_id\": \"<string>\",\n \"run_id\": \"<string>\",\n \"metadata\": {},\n \"includes\": \"<string>\",\n \"excludes\": \"<string>\",\n \"infer\": true,\n \"custom_categories\": {}, \n \"org_id\": \"<string>\",\n \"project_id\": \"<string>\",\n \"version\": \"v2\"\n}'"},{"lang": "Go",- "source": "package main\n\nimport (\n\t\"fmt\"\n\t\"strings\"\n\t\"net/http\"\n\t\"io/ioutil\"\n)\n\nfunc main() {\n\n\turl := \"https://api.mem0.ai/v1/memories/\"\n\n\tpayload := strings.NewReader(\"{\n \\\"messages\\\": [\n {}\n ],\n \\\"agent_id\\\": \\\"<string>\\\",\n \\\"user_id\\\": \\\"<string>\\\",\n \\\"app_id\\\": \\\"<string>\\\",\n \\\"run_id\\\": \\\"<string>\\\",\n \\\"metadata\\\": {},\n \\\"includes\\\": \\\"<string>\\\",\n \\\"excludes\\\": \\\"<string>\\\",\n \\\"infer\\\": true,\n \\\"custom_categories\\\": {},\n \\\"org_id\\\": \\\"<string>\\\",\n \\\"project_id\\\": \\\"<string>\"\n}\")\n\n\treq, _ := http.NewRequest(\"POST\", url, payload)\n\n\treq.Header.Add(\"Authorization\", \"Token <api-key>\")\n\treq.Header.Add(\"Content-Type\", \"application/json\")\n\n\tres, _ := http.DefaultClient.Do(req)\n\n\tdefer res.Body.Close()\n\tbody, _ := ioutil.ReadAll(res.Body)\n\n\tfmt.Println(res)\n\tfmt.Println(string(body))\n\n}"+ "source": "package main\n\nimport (\n\t\"fmt\"\n\t\"strings\"\n\t\"net/http\"\n\t\"io/ioutil\"\n)\n\nfunc main() {\n\n\turl := \"https://api.mem0.ai/v1/memories/\"\n\n\tpayload := strings.NewReader(\"{\n \\\"messages\\\": [\n {}\n ],\n \\\"agent_id\\\": \\\"<string>\\\",\n \\\"user_id\\\": \\\"<string>\\\",\n \\\"app_id\\\": \\\"<string>\\\",\n \\\"run_id\\\": \\\"<string>\\\",\n \\\"metadata\\\": {},\n \\\"includes\\\": \\\"<string>\\\",\n \\\"excludes\\\": \\\"<string>\\\",\n \\\"infer\\\": true,\n \\\"custom_categories\\\": {},\n \\\"org_id\\\": \\\"<string>\\\",\n \\\"project_id\\\": \\\"<string>\",\n \\\"version\\\": \"v2\"\n}\")\n\n\treq, _ := http.NewRequest(\"POST\", url, payload)\n\n\treq.Header.Add(\"Authorization\", \"Token <api-key>\")\n\treq.Header.Add(\"Content-Type\", \"application/json\")\n\n\tres, _ := http.DefaultClient.Do(req)\n\n\tdefer res.Body.Close()\n\tbody, _ := ioutil.ReadAll(res.Body)\n\n\tfmt.Println(res)\n\tfmt.Println(string(body))\n\n}"},{"lang": "PHP",- "source": "<?php\n\n$curl = curl_init();\n\ncurl_setopt_array($curl, [\n CURLOPT_URL => \"https://api.mem0.ai/v1/memories/\",\n CURLOPT_RETURNTRANSFER => true,\n CURLOPT_ENCODING => \"\",\n CURLOPT_MAXREDIRS => 10,\n CURLOPT_TIMEOUT => 30,\n CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,\n CURLOPT_CUSTOMREQUEST => \"POST\",\n CURLOPT_POSTFIELDS => \"{\n \\\"messages\\\": [\n {}\n ],\n \\\"agent_id\\\": \\\"<string>\\\",\n \\\"user_id\\\": \\\"<string>\\\",\n \\\"app_id\\\": \\\"<string>\\\",\n \\\"run_id\\\": \\\"<string>\\\",\n \\\"metadata\\\": {},\n \\\"includes\\\": \\\"<string>\\\",\n \\\"excludes\\\": \\\"<string>\\\",\n \\\"infer\\\": true,\n \\\"custom_categories\\\": {}, \n \\\"org_id\\\": \\\"<string>\\\",\n \\\"project_id\\\": \\\"<string>\"\n}\",\n CURLOPT_HTTPHEADER => [\n \"Authorization: Token <api-key>\",\n \"Content-Type: application/json\"\n ],\n]);\n\n$response = curl_exec($curl);\n$err = curl_error($curl);\n\ncurl_close($curl);\n\nif ($err) {\n echo \"cURL Error #:\" . $err;\n} else {\n echo $response;\n}"+ "source": "<?php\n\n$curl = curl_init();\n\ncurl_setopt_array($curl, [\n CURLOPT_URL => \"https://api.mem0.ai/v1/memories/\",\n CURLOPT_RETURNTRANSFER => true,\n CURLOPT_ENCODING => \"\",\n CURLOPT_MAXREDIRS => 10,\n CURLOPT_TIMEOUT => 30,\n CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,\n CURLOPT_CUSTOMREQUEST => \"POST\",\n CURLOPT_POSTFIELDS => \"{\n \\\"messages\\\": [\n {}\n ],\n \\\"agent_id\\\": \\\"<string>\\\",\n \\\"user_id\\\": \\\"<string>\\\",\n \\\"app_id\\\": \\\"<string>\\\",\n \\\"run_id\\\": \\\"<string>\\\",\n \\\"metadata\\\": {},\n \\\"includes\\\": \\\"<string>\\\",\n \\\"excludes\\\": \\\"<string>\\\",\n \\\"infer\\\": true,\n \\\"custom_categories\\\": {}, \n \\\"org_id\\\": \\\"<string>\\\",\n \\\"project_id\\\": \\\"<string>\",\n \\\"version\\\": \"v2\"\n}\",\n CURLOPT_HTTPHEADER => [\n \"Authorization: Token <api-key>\",\n \"Content-Type: application/json\"\n ],\n]);\n\n$response = curl_exec($curl);\n$err = curl_error($curl);\n\ncurl_close($curl);\n\nif ($err) {\n echo \"cURL Error #:\" . $err;\n} else {\n echo $response;\n}"},{"lang": "Java",- "source": "HttpResponse<String> response = Unirest.post(\"https://api.mem0.ai/v1/memories/\")\n .header(\"Authorization\", \"Token <api-key>\")\n .header(\"Content-Type\", \"application/json\")\n .body(\"{\n \\\"messages\\\": [\n {}\n ],\n \\\"agent_id\\\": \\\"<string>\\\",\n \\\"user_id\\\": \\\"<string>\\\",\n \\\"app_id\\\": \\\"<string>\\\",\n \\\"run_id\\\": \\\"<string>\\\",\n \\\"metadata\\\": {},\n \\\"includes\\\": \\\"<string>\\\",\n \\\"excludes\\\": \\\"<string>\\\",\n \\\"infer\\\": true,\n \\\"custom_categories\\\": {}, \n \\\"org_id\\\": \\\"<string>\\\",\n \\\"project_id\\\": \\\"<string>\"\n}\")\n .asString();"+ "source": "HttpResponse<String> response = Unirest.post(\"https://api.mem0.ai/v1/memories/\")\n .header(\"Authorization\", \"Token <api-key>\")\n .header(\"Content-Type\", \"application/json\")\n .body(\"{\n \\\"messages\\\": [\n {}\n ],\n \\\"agent_id\\\": \\\"<string>\\\",\n \\\"user_id\\\": \\\"<string>\\\",\n \\\"app_id\\\": \\\"<string>\\\",\n \\\"run_id\\\": \\\"<string>\\\",\n \\\"metadata\\\": {},\n \\\"includes\\\": \\\"<string>\\\",\n \\\"excludes\\\": \\\"<string>\\\",\n \\\"infer\\\": true,\n \\\"custom_categories\\\": {}, \n \\\"org_id\\\": \\\"<string>\\\",\n \\\"project_id\\\": \\\"<string>\",\n \\\"version\\\": \"v2\"\n}\")\n .asString();"}],"x-codegen-request-body-name": "data"@@ -4809,6 +4809,12 @@"title": "Project id","type": "string","nullable": true+ },+ "version": {+ "description": "The version of the memory to use. The default version is v1, which is deprecated. We recommend using v2 for new applications.",+ "title": "Version",+ "type": "string",+ "nullable": true}}},diff --git a/docs/platform/quickstart.mdx b/docs/platform/quickstart.mdxindex 81316c805..19283ed9d 100644--- a/docs/platform/quickstart.mdx+++ b/docs/platform/quickstart.mdx@@ -87,10 +87,10 @@ messages = []# The default output_format is v1.0-client.add(messages, user_id="alex", output_format="v1.0")+client.add(messages, user_id="alex", output_format="v1.0", version="v2")# To use the latest output_format, set the output_format parameter to "v1.1"-client.add(messages, user_id="alex", output_format="v1.1", metadata={"food": "vegan"})+client.add(messages, user_id="alex", output_format="v1.1", metadata={"food": "vegan"}, version="v2")``````javascript JavaScript@@ -98,7 +98,7 @@ const messages = [{"role": "user", "content": "Hi, I'm Alex. I'm a vegetarian and I'm allergic to nuts."},{"role": "assistant", "content": "Hello Alex! I've noted that you're a vegetarian and have a nut allergy. I'll keep this in mind for any food-related recommendations or discussions."}];-client.add(messages, { user_id: "alex", output_format: "v1.1", metadata: { food: "vegan" } })+client.add(messages, { user_id: "alex", output_format: "v1.1", metadata: { food: "vegan" }, version: "v2" }).then(response => console.log(response)).catch(error => console.error(error));```@@ -116,7 +116,8 @@ curl -X POST "https://api.mem0.ai/v1/memories/" \"output_format": "v1.1","metadata": {"food": "vegan"- }+ },+ "version": "v2"}'```@@ -191,10 +192,10 @@ messages = []# The default output_format is v1.0-client.add(messages, user_id="alex123", run_id="trip-planning-2024", output_format="v1.0")+client.add(messages, user_id="alex", run_id="trip-planning-2024", output_format="v1.0", version="v2")# To use the latest output_format, set the output_format parameter to "v1.1"-client.add(messages, user_id="alex123", run_id="trip-planning-2024", output_format="v1.1")+client.add(messages, user_id="alex", run_id="trip-planning-2024", output_format="v1.1", version="v2")``````javascript JavaScript@@ -204,7 +205,7 @@ const messages = [{"role": "user", "content": "Yes, please! Especially in Tokyo."},{"role": "assistant", "content": "Great! I'll remember that you're interested in vegetarian restaurants in Tokyo for your upcoming trip. I'll prepare a list for you in our next interaction."}];-client.add(messages, { user_id: "alex123", run_id: "trip-planning-2024", output_format: "v1.1" })+client.add(messages, { user_id: "alex", run_id: "trip-planning-2024", output_format: "v1.1", version: "v2" }).then(response => console.log(response)).catch(error => console.error(error));```@@ -220,9 +221,10 @@ curl -X POST "https://api.mem0.ai/v1/memories/" \{"role": "user", "content": "Yes, please! Especially in Tokyo."},{"role": "assistant", "content": "Great! I'll remember that you're interested in vegetarian restaurants in Tokyo for your upcoming trip. I'll prepare a list for you in our next interaction."}],- "user_id": "alex123",+ "user_id": "alex","run_id": "trip-planning-2024",- "output_format": "v1.1"+ "output_format": "v1.1",+ "version": "v2"}'```@@ -274,10 +276,10 @@ messages = []# The default output_format is v1.0-client.add(messages, agent_id="ai-tutor", output_format="v1.0")+client.add(messages, agent_id="ai-tutor", output_format="v1.0", version="v2")# To use the latest output_format, set the output_format parameter to "v1.1"-client.add(messages, agent_id="ai-tutor", output_format="v1.1")+client.add(messages, agent_id="ai-tutor", output_format="v1.1", version="v2")``````javascript JavaScript@@ -285,7 +287,7 @@ const messages = [{"role": "system", "content": "You are an AI tutor with a personality. Give yourself a name for the user."},{"role": "assistant", "content": "Understood. I'm an AI tutor with a personality. My name is Alice."}];-client.add(messages, { agent_id: "ai-tutor", output_format: "v1.1" })+client.add(messages, { agent_id: "ai-tutor", output_format: "v1.1", version: "v2" }).then(response => console.log(response)).catch(error => console.error(error));```@@ -300,7 +302,8 @@ curl -X POST "https://api.mem0.ai/v1/memories/" \{"role": "assistant", "content": "Understood. I'm an AI tutor with a personality. My name is Alice."}],"agent_id": "ai-tutor",- "output_format": "v1.1"+ "output_format": "v1.1",+ "version": "v2"}'```@@ -368,7 +371,7 @@ messages = [{"role": "assistant", "content": "That's great! I'm going to Dubai next month."},]-client.add(messages=messages, user_id="user1", agent_id="agent1")+client.add(messages=messages, user_id="user1", agent_id="agent1", version="v2")``````javascript JavaScript@@ -377,7 +380,7 @@ const messages = [{"role": "assistant", "content": "That's great! I'm going to Dubai next month."},]-client.add(messages, { user_id: "user1", agent_id: "agent1" })+client.add(messages, { user_id: "user1", agent_id: "agent1", version: "v2" }).then(response => console.log(response)).catch(error => console.error(error));```@@ -392,7 +395,8 @@ curl -X POST "https://api.mem0.ai/v1/memories/" \{"role": "assistant", "content": "That's great! I'm going to Dubai next month."},],"user_id": "user1",- "agent_id": "agent1"+ "agent_id": "agent1",+ "version": "v2"}'```@@ -1004,17 +1008,17 @@ curl -X GET "https://api.mem0.ai/v1/memories/?agent_id=ai-tutor&page=1&page_size<CodeGroup>```python Python-short_term_memories = client.get_all(user_id="alex123", run_id="trip-planning-2024", page=1, page_size=50)+short_term_memories = client.get_all(user_id="alex", run_id="trip-planning-2024", page=1, page_size=50)``````javascript JavaScript-client.getAll({ user_id: "alex123", run_id: "trip-planning-2024", page: 1, page_size: 50 })+client.getAll({ user_id: "alex", run_id: "trip-planning-2024", page: 1, page_size: 50 }).then(memories => console.log(memories)).catch(error => console.error(error));``````bash cURL-curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&run_id=trip-planning-2024&page=1&page_size=50" \+curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex&run_id=trip-planning-2024&page=1&page_size=50" \-H "Authorization: Token your-api-key"```@@ -1027,7 +1031,7 @@ curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&run_id=trip-planni{"id":"06d8df63-7bd2-4fad-9acb-60871bcecee0","memory":"Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",- "user_id":"alex123",+ "user_id":"alex","hash":"d2088c936e259f2f5d2d75543d31401c","metadata":None,"immutable": false,@@ -1038,7 +1042,7 @@ curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&run_id=trip-planni{"id":"b4229775-d860-4ccb-983f-0f628ca112f5","memory":"Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",- "user_id":"alex123",+ "user_id":"alex","hash":"d2088c936e259f2f5d2d75543d31401c","metadata":None,"immutable": false,@@ -1049,7 +1053,7 @@ curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&run_id=trip-planni{"id":"df1aca24-76cf-4b92-9f58-d03857efcb64","memory":"Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",- "user_id":"alex123",+ "user_id":"alex","hash":"d2088c936e259f2f5d2d75543d31401c","metadata":None,"immutable": false,@@ -1072,7 +1076,7 @@ curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&run_id=trip-planni{"id": "06d8df63-7bd2-4fad-9acb-60871bcecee0","memory": "Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",- "user_id": "alex123",+ "user_id": "alex","hash": "d2088c936e259f2f5d2d75543d31401c","metadata":None,"immutable": false,@@ -1083,7 +1087,7 @@ curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&run_id=trip-planni{"id": "b4229775-d860-4ccb-983f-0f628ca112f5","memory": "Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",- "user_id": "alex123",+ "user_id": "alex","hash": "d2088c936e259f2f5d2d75543d31401c","metadata":None,"immutable": false,@@ -1094,7 +1098,7 @@ curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&run_id=trip-planni{"id": "df1aca24-76cf-4b92-9f58-d03857efcb64","memory": "Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",- "user_id": "alex123",+ "user_id": "alex","hash": "d2088c936e259f2f5d2d75543d31401c","metadata":None,"immutable": false,@@ -1133,7 +1137,7 @@ curl -X GET "https://api.mem0.ai/v1/memories/582bbe6d-506b-48c6-a4c6-5df3b1e6342{"id":"06d8df63-7bd2-4fad-9acb-60871bcecee0","memory":"Planning a trip to Japan next month. Interested in vegetarian restaurants in Tokyo.",- "user_id":"alex123",+ "user_id":"alex","hash":"d2088c936e259f2f5d2d75543d31401c","metadata":"None","immutable": false,@@ -1152,55 +1156,55 @@ You can filter memories by their categories when using get_all:```python Python# Get memories with specific categories-memories = client.get_all(user_id="alex123", categories=["likes"])+memories = client.get_all(user_id="alex", categories=["likes"])# Get memories with multiple categories-memories = client.get_all(user_id="alex123", categories=["likes", "food_preferences"])+memories = client.get_all(user_id="alex", categories=["likes", "food_preferences"])# Custom pagination with categories-memories = client.get_all(user_id="alex123", categories=["likes"], page=1, page_size=50)+memories = client.get_all(user_id="alex", categories=["likes"], page=1, page_size=50)# Get memories with specific keywords-memories = client.get_all(user_id="alex123", keywords="to play", page=1, page_size=50)+memories = client.get_all(user_id="alex", keywords="to play", page=1, page_size=50)``````javascript JavaScript// Get memories with specific categories-client.getAll({ user_id: "alex123", categories: ["likes"] })+client.getAll({ user_id: "alex", categories: ["likes"] }).then(memories => console.log(memories)).catch(error => console.error(error));// Get memories with multiple categories-client.getAll({ user_id: "alex123", categories: ["likes", "food_preferences"] })+client.getAll({ user_id: "alex", categories: ["likes", "food_preferences"] }).then(memories => console.log(memories)).catch(error => console.error(error));// Custom pagination with categories-client.getAll({ user_id: "alex123", categories: ["likes"], page: 1, page_size: 50 })+client.getAll({ user_id: "alex", categories: ["likes"], page: 1, page_size: 50 }).then(memories => console.log(memories)).catch(error => console.error(error));// Get memories with specific keywords-client.getAll({ user_id: "alex123", keywords: "to play", page: 1, page_size: 50 })+client.getAll({ user_id: "alex", keywords: "to play", page: 1, page_size: 50 }).then(memories => console.log(memories)).catch(error => console.error(error));``````bash cURL# Get memories with specific categories-curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&categories=likes" \+curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex&categories=likes" \-H "Authorization: Token your-api-key"# Get memories with multiple categories-curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&categories=likes,food_preferences" \+curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex&categories=likes,food_preferences" \-H "Authorization: Token your-api-key"# Custom pagination with categories-curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&categories=likes&page=1&page_size=50" \+curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex&categories=likes&page=1&page_size=50" \-H "Authorization: Token your-api-key"# Get memories with specific keywords-curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&keywords=to play&page=1&page_size=50" \+curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex&keywords=to play&page=1&page_size=50" \-H "Authorization: Token your-api-key"```@@ -1213,7 +1217,7 @@ curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&keywords=to play&p{"id": "06d8df63-7bd2-4fad-9acb-60871bcecee0","memory": "Likes pizza and pasta",- "user_id": "alex123",+ "user_id": "alex","hash": "d2088c936e259f2f5d2d75543d31401c","metadata": null,"immutable": false,@@ -1224,7 +1228,7 @@ curl -X GET "https://api.mem0.ai/v1/memories/?user_id=alex123&keywords=to play&p{"id": "b4229775-d860-4ccb-983f-0f628ca112f5","memory": "Likes to travel to beach destinations",- "user_id": "alex123",+ "user_id": "alex","hash": "d2088c936e259f2f5d2d75543d31401c","metadata": null,"immutable": false,@@ -1585,7 +1589,7 @@ curl -X GET "https://api.mem0.ai/v1/memories/<memory-id-here>/history/" \],"old_memory":"None","new_memory":"Turned vegetarian.",- "user_id":"alex123456",+ "user_id":"alex","event":"ADD","metadata":"None","created_at":"2024-07-26T01:02:41.737310-07:00",